Since large articulated vehicles have uncertainties in trailer articulation angle as well as dynamic complexity, it is not easy to accurately establish a reliable motion plan. In this paper, two geometric path plans constructed based on the empirical rules of driving experts are presented so that articulated vehicles can automatically perform perpendicular parking on a reverse path. By analyzing the empirical parking methods of professional drivers, these path plans were constructed by appropriately combining several standardized simple basic motions to facilitate implementation in real vehicles. In addition, path plans included appropriate complementary motions to effectively respond to uncertainties arising from articulation angles, etc. The complementary motions developed in this study are based on the results of qualitative analysis on the behavior of articulated vehicles. The usefulness of the proposed articulated vehicle parking method has been proven through hundreds of experimental tests using a 1:10 ratio model automated vehicle.

A very high parking occupancy can negatively influence the traffic performance of an area by causing very long cruising times. A very low parking occupancy, on the other hand, is inefficient from a space utilization perspective. Thus, this paper proposes a framework to compute the optimal parking occupancy rate over a given time horizon based on a macroscopic traffic and parking model. This rate is set high enough to ensure an efficient usage of the parking infrastructure. However, it should also guarantee a high likelihood of finding parking in order to eliminate the drivers’ time wasted in cruising for parking and the added congestion it causes. The model outputs are based on small data collection efforts and low computational costs, and they can be generated without complex simulation software using a simple numerical solver. Multiple vehicle types are included into our methodology allowing us to generate insights about the optimal parking occupancy with or without differentiated parking (i.e., parking for specific vehicles, such as fuel and electric vehicles). In times of a modal shift towards electric vehicles, cities can use our model to evaluate how much parking supply (with battery charging opportunities) they would like to dedicate to electric vehicles in order to achieve optimal traffic and parking results, and whether a differentiated or semi-differentiated parking policy is desirable. We illustrate our framework in a case study of a central area within the city of Zurich, Switzerland, showing the traffic and parking impacts (e.g., average searching time for parking, total revenue created by parking fees, optimal parking occupancy rate) for different proportions of fuel and electric vehicles in the parking demand and/or supply. Our results confirm that optimal occupancy rates are between and for most realistic scenarios. We then discuss how these rates might change depending on various demand and supply relationships, and according to different parking policies. We show that equal proportions between electric vehicles in the demand and their parking spaces in the supply lead to the best traffic performance in the area. We also provide the tools for cities to analyze their loss in performance if they do not react, e.g., to an increasing demand for electric vehicles over time. Moreover, we illustrate how some of these risks can be mitigated by having more flexible parking policies, e.g., allowing electric vehicles to use parking spaces for fuel vehicles.

The narrow parking space will result in difficulties in path planning and spot turning caused by sudden changes and discontinuities in path curvature. To address the problem, this paper investigates the performance of three path planning algorithms and proposes a path optimization algorithm. First, the narrow parking space is defined based on single-step parking of the arc-line combination parking algorithm. Second, to compare the arc-line combination algorithm, Hybrid A* algorithm, and particle swarm optimization parking algorithm under different narrow parking spaces, a multi-objective evaluation function is proposed, including three evaluation indicators, namely, the path length, the number of positive and negative conversions of vehicle speed, and the smoothness of the path. Their performance is compared by simulation conducted in MATLAB, the results show that the Hybrid A* algorithm is the better than others for narrow parking spaces. Third, to smooth the planning path, a path optimization algorithm based on the cubic B-spline curve and gradient descent is proposed. Finally, the simulation is conducted between the proposed algorithm and Hybrid A* algorithm, the result shows that the proposal can effectively eliminate the curvature mutation point and constrain the path curvature to meet the requirements of a smooth path.

In Thailand, parking time violation is a major problem, especially for mini-marts. At present the task of detecting parking time violation is mainly conducted manually using Closed-Circuit Television (CCTV). This method requires additional human labour to track incoming and outgoing vehicles. Therefore, low cost time violation tracking is needed. To the best of our knowledge, there has not been any research for parking violation detection and tracking conducted for parking time limits. This paper introduces a novel parking time violation detection algorithm using the Yolov8 and DeepSORT tracking algorithms to track vehicles in consecutive frames. The presented parking violation tracking algorithm can provide a guideline for research in parking time violation detection.

Efficient fixed crane position analysis is critical in precast buildings construction to maximize lifting efficiency for precast elements. The primary objective is to minimize the travel distances of fixed cranes, thereby enhancing operational efficiency and cost control. This involves strategically reducing the distances between the transport truck parking, where elements are stored, the fixed crane, and the construction installation point. Despite its significance, existing studies often overlook the dynamic movement efficiency of transport trucks, particularly when dealing with multiple transport trucks and various models of fixed cranes, rendering the opti-mization of this scenario a challenging NP-hard problem susceptible to combinatorial explosion. This study presents a novel mathematical model leveraging the Genetic Algorithm (GA). The model aims to solve optimal model and position of fixed cranes, along with identifying ideal positions for transport truck parking. The study's methodology is validated and demonstrated through a project case study. Comparative analyses between the proposed model and the original planning underscore a noteworthy 6% reduction in both duration and costs when lifting elements directly from transport trucks, as opposed to establishing an on-site stock yard. Furthermore, the developed GA exhibits a substantial improvement in final solutions, achieving a remarkable 30% reduction in both operational duration and costs. This research contributes valuable insights into fixed crane position analysis of precast building construction, providing foundation for enhanced operational efficiency and cost-effectiveness in the industry.

Time evolution of the quantum correlation of the hybrid qubit-qutrit system in multilocal and global dephasing under the effect of a classical noises environment is presented. We considered the qutrit in z direction and the qubit x direction. In addition, our system presents two configurations: the different and the common environment and our discussion involves three types of noises: A Static Noise (SN), Random Telegraph Noise (RTN) and Ornstein- Uhlenbeck noise (OU). By using the density matrix approach to determine the evolution of the state of the system, the found that the static noise is fatal for the quantum entanglement, the quantum correlation and for RTN and OU noises the quantum entanglement, the quantum correlation decreases monotonically with a sufficiently long time. Therefore, we can say that, entanglement and the quantum correlation are more robust to the noise precisely those Random telegraph noise and Ornstein-Uhlenbeck noise.

Time-domain spectroscopy (TDS) in the Terahertz (THz) frequency range is gaining in importance in nondestructive testing of dielectric materials. One application is the layer thickness measurement of a coating layer. To determine the thickness from the measurement data, the refractive index of the coating layer must be known in the surveyed frequency range. For perpendicular incidence of the radiation, methods exist to extract the refractive index from the measurement data itself without prior knowledge. This paper extends these methods for non-perpendicular incidence, where the polarization of the radiation becomes important. Furthermore, modifications considering effects of surface roughness of the coating are introduced. The new methods are verified using measurement data of a sample of Inconel steel coated with yttria-stabilized zirconia (YSZ) and with COMSOL simulations of the measurement setup. To validate the thickness measurements, scanning electron microscopy (SEM) images of the layer structure are used. The results show good agreement with an average error of 1% for the simulation data and under 4% for the experimental data compared to reference measurements.

The perpendicular exchange bias effect is observed in the ferromagnetic Co/Ni multilayers adjacent to the antiferromagnetic FeRh layer. It is found that as the antiferromagnetic FeRh thickness increases from 10 Å to 50 Å, the hysteresis loop is gradually changed from the symmetric shape to the asymmetric shape shifted by some amount corresponding to the exchange-biased field at the thickness of 25 Å. Also, the magnetic domain observation experiment confirms that the domain reversals in the increasing and the decreasing field regions of the sample with the thickness of 50 Å exhibit the same single domain wall motion even though they have the different coercivities.

The supply chain has incorporated products by putting them into hair scarfs. This study introduces the use of mini chips in health and beauty products and can reduce fatigue through enhanced sleep patterns. The mini chip could be placed in the scarf and used as a prototype. RFID technology provides the supply chain with specific information that is used to identify products and make communication easier. (Muhammad, et. al. 2013) This paper presents a new tool herein referred to as a scarf prototype which is developed to analyse EMG (electromyogram), ECG (electrocardiography), EEG (electroencephalogram), and EOG (electro-oculogram) signals that focuses in the area of sleep disorders. The mini chips used can be used to determine a solution for sleep disruption by using automated analytics. This could lead to improvement in our understanding of sleep disruption and overall sleep physiology. Automated technology allows repeated measurements, evaluation of sleep patterns, and provide suggestions to improve a person’s quality of sleep. This analysis compares the use of polysomnography and the scarf prototype. The analytics provide models and shows correlation between variables, such as EMG, ECG, EEG, and EOG. This study shows that the results from the scarf prototype is just as reliable as the original method, polysomnography.

Due to the tremendous progress in the automotive industry, the growth of the urban population, the number of vehicles is increasing and this creates parking challenges. Intelligent parking management systems offer an optimal solution for finding empty parking space so that drivers can quickly find their car parking space. To solve these problems, it is necessary to design an intelligent parking system, in addition to providing comfort to drivers, which is also economically viable. This paper proposes an intelligent multi-storey car parking system with the help of RFID technology and examining user preferences that can effectively solve car parking problems. The proposed method is a multi-objective decision-making method to reduce the problem of car parking, which is called MODM-RPCP. Therefore, the proposed MODM-RPCP method can allocate the best space for their stopping place by using the decision-making system and based on the priorities considered by the users. The simulation results show that the MODM-RPCP reduces the average booking time more than 19.2% and 27.1%, and decreases the response time of central parking management server more than 20.1% and 29.78% compared to MOGWOLA and ODPP approaches.

The blood count is crucial for assessing bone marrow's cell production and differentiation during infections, gauging disease severity, and monitoring therapeutic responses. The profile of blood count in chronic form of paracoccidioidomycosis (PCM) has been insufficiently explored. To better understand the changes in hematological cells in different stages of the PCM chronic form, we evaluated the blood count, including immature blood cells in automated equipment, before and during the treatment follow-up of 62 chronic PCM patients. Predominantly male (96.8%) with an average age of 54.3 (SD 6.9) years, participants exhibited pre-treatment conditions such as anemia (45.2%), monocytosis (38.7%), and leukocytosis (17.7%) which became less frequent after clinical cure. Anemia was more prevalent in severe cases. Notably, hemoglobin and reticulocyte hemoglobin content increased, while leukocytes, monocytes, neutrophils, immature granulocytes, and platelets decreased. Chronic PCM induced manageable hematological abnormalities, mainly in the red blood series. Monocytosis, indicating monocytes' role in PCM's immune response, was frequent. Post-treatment, especially after achieving clinical cure, significant improvements were observed in various hematological indices, including immature granulocytes and reticulocyte hemoglobin content, underscoring the impact of infection on these parameters.

As traffic congestion gets worse year by year in metropolitan areas, cities search for solutions to improve their traffic performance and reduce their environmental impacts. This paper focuses on parking pricing and congestion pricing and their short-term effects not only on traffic congestion but also on the potential revenue for a city. We develop an easy to implement multimodal macroscopic traffic and parking search model for a central area based on aggregated data at the network level. Our methodology allows us to analyze how introducing parking pricing inside a network, or a congestion toll combined with a park and ride (P+R) scheme can affect the drivers’ decision between entering the network by car (private vehicle) or using P+R instead. This decision directly influences the number of drivers using P+R, and this impacts, in turn, the traffic performance. Based on such analysis, a city can get valuable insights to evaluate whether congestion pricing is a necessity or if the traffic improvements resulting from implementing parking pricing strategies are sufficient when combined with P+R facilities. A search algorithm is used to find the best trade-off between the parking fees and the congestion toll. Any additional revenue collected through these schemes can then be used to improve public transport or the P+R facilities themselves. With minor data collection efforts and little computational costs compared to most existing parking and congestion pricing models, we illustrate our proposed framework in a case study of an area with a high parking demand for public parking spaces within the city of Zurich, Switzerland. Results show that parking pricing combined with P+R is indeed a viable option compared to congestion pricing for improving traffic performance, even if parking pricing schemes do not target all the drivers.

This article attempts to assess the light pollution of parking lots, using the proprietary measure-ment method with a drone. The main requirements, reflective features of parking lots and typical light curves of luminaires used in lighting this type of areas were presented. Calculations and simulations for various types of luminaires were performed, and then the obtained results were verified in real conditions. The main factors influencing the increase in light pollution were pre-sented and it was proved that it is possible to use the developed measurement method in order to assess the light pollution degree.

Recent technological advancements in conservation genetics and genomics have resulted in diverse tools for aiding conservation of species. The precision and resolution of high throughput sequencing technologies provide valuable insights to aid conservation decisions, but these technologies are often financially unfeasible or unavailable in resource constrained countries. Inter-Simple Sequence Repeat (ISSR) markers, when combined with sensitive automated detection systems, provide a simple, cheap means to investigate genetic diversity and discriminate closely related species. Here we apply this technology to assess genetic diversity and taxonomic delimitation in the Encephalartos eugene-maraisii species complex, a highly threatened, taxonomically dubious group of cycads in South Africa. Silica dried cycad leaflets were extracted using the Oktopure robot employing Sbeadex chemistry and amplified with fluorescently tagged ISSR primers. Band presence was scored with an ABI 3130 genetic sequencer under three different fluorescence cut-off values. Phenetic analyses were performed in NTSYS software while Bayesian analysis was performed in STRUCTURE, and haplotype network analysis, AMOVA and Tajima’s D statistic was computed with PopART. Our analyses support taxonomic singularity of E. dyerianus, E. dolomiticus and E. eugene-maraisii. Relationships between E. nubimontanus and E. cupidus remain uncertain. E. middelburgensis samples showed no clustering but had poor amplification success. This study demonstrated the suitability of automated ISSR fingerprinting as a method for plant conservation studies, especially in resource-constrained countries.

The chicken poultry business is becoming a crucial sector for our nation's sustainable food supply. To increase the health of chickens in coops and maybe increase the output of chicken meat and eggs, several innovations and inventions have been developed. Therefore, the creation of an automated chicken feeding device might be highly beneficial for the expansion of the poultry sector. This equipment may take the role of a worker in the chicken feeding process, solving the industry's labor shortage and introducing a semi-automatic procedure. The main processor of the automated chicken feeding system is a Raspberry Pi 3 Model B+. The machine consists of five main components: a Raspberry Pi with an amplifier that makes noise to draw the attention of free-range chickens, a Raspberry Pi with a pi camera that counts and detects the chickens, a Raspberry Pi with a servomotor that moves the food from storage to a container, a Raspberry Pi with a load cell that controls the number of feeds to avoid waste on foods, and a Raspberry Pi with a temperature sensor that monitors the food's freshness. This enhances the coop's atmosphere while lowering labor costs, conserving food, and ensuring that the chickens are fed on time. It also regulates the temperature sensor to ensure that the chicken food is fresh and prevents food from becoming polluted by insects and chicken excrement.

This paper investigates the efficacy of YOLOv8 variants for vehicle detection and license plate detection within smart parking applications, emphasizing performance under varying ambient lighting conditions. The proposed system is to seize full video frames, extracts regions of interest containing vehicles, and feeds them into separate, pre-trained YOLOv8 models – one dedicated to vehicle detection and another for license plate detection. Four YOLOv8 variants, nano, small, medium, and large, are evaluated. As a pre-processing step, the images are processed with the help of OpenCV and Pillow libraries to adjust the luminosity and increase the images’ DPI so that they would be easy to perceive by the Tesseract OCR engine. Sixteen potential combinations arise from pairing the four YOLOv8 models for vehicle and license plate detection tasks. To identify the most suitable combinations, we employ the Multi-Criteria Decision-Making method, specifically Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) analysis. This analysis considers 4 critical metrics: Precision, mean average precision at 95% Intersection of Union threshold, Recall and Total Inference Time. The objective is to achieve an optimal balance between high accuracy and real-time processing. Following the selection of optimal YOLOv8 combinations through TOPSIS analysis, we assess their performance under varying ambient light intensity (measured in lux). This evaluation aims to identify the most robust model combinations that ensure accurate vehicle and license plate recognition across the diverse lighting conditions encountered in real-world environment.

Autonomous vehicles (AVs) may not only reduce parking demand, but also free up on-street parking spaces. From the perspective of bus priority, converting on-street parking lots into dedicated bus lanes can both ensure bus priority and accommodate non-bus traffic, helping to reduce congestion and pollution. In order to study the impact of conversion of on-street parking lots to bus lanes on traffic flow, a microscopic simulation framework based on VISSIM is proposed in this paper. Data was collected using the floating car method and video recording method to quantify the factors affecting traffic flow due to the conversion of on-street parking. The VISSIM simulation model was then calibrated. According to the proportion of the on-street parking lots into a bus lane, the on-street parking lots conversion simulation model of different scenarios was established, and the influence of different on-street parking lots conversion ratio on traffic efficiency and pollution emission was quantitatively analyzed. Finally, the optimization method based on bus lane network connectivity is discussed. The results indicate that: When the on-street parking lots conversion ratio is approximately 100%, bus speed increases by 21.03%, bus delays decrease by 14.27%, and bus parking instances decrease by 11.31%. Total emissions are negatively correlated with vehicle speed. As the conversion rate of on-street parking increases, the emissions of road segments and the entire road network gradually decrease. At a conversion ratio of 100%, the average total emissions for road segments have the highest reduction rate, decreasing by 4.12%. At a conversion ratio of 50%, the average emission total for the road network shows the largest reduction, falling by 2.88%.

Timely and accurate identification of change detection for areas depicted on nautical charts constitutes a key task for marine cartographic agencies in supporting maritime safety. Such a task is usually achieved through manual or semi-automated processes, based on best practices developed over the years requiring a substantial level of human commitment (i.e., to visually compare the chart with the new collected data or to analyze the result of intermediate products). This work describes an algorithm that aims to largely automate the change identification process as well as to reduce its subjective component. Through the selective derivation of a set of depth points from a nautical chart, a triangulated irregular network is created to apply a preliminary tilted-triangle test to all the input survey soundings. Given the complexity of a modern nautical chart, a set of feature-specific, point-in-polygon tests are then performed. As output, the algorithm provides danger-to-navigation candidates, chart discrepancies, and a subset of features that requires human evaluation. The algorithm has been successfully tested with real-world electronic navigational charts and survey datasets. In parallel to the research development, a prototype application implementing the algorithm was created and made publicly available.

Pharmacy personnel often answer telephones to respond to pharmacy customers (subjects) who received messages from automated systems. This research examines the communication process in terms of how users interact and engage with pharmacies after receiving automated messages. No study has directly addressed automated telephone calls and subjects’ interactions. The purpose of this study is to test the interpersonal communication (IC) process of uncertainty in subjects in receipt of automated telephone calls from pharmacies. Subjects completed a survey of validated scales for Satisfaction (S); Relevance (R); Quality (Q); Need for Cognitive Closure (NFC). Relationships between S, R, Q, NFC, and subject preference to an automated telephone call (ATC) were analyzed to determine whether subjects contacting pharmacies display information seeking behavior. This research demonstrates that seeking information occurs if subjects: are dissatisfied with the content of the ATC; perceive that the Q of the ATC is high; perceive that the Q of ATC is high, and like receiving the ATC or with high NFC, and do not like receiving ATCs. Other interactions presented complexities amongst uncertainty and tolerance of NFC within the IC process.

Urban transportation in the next few decades will shift worldwide towards electrification and automation, with the final aim of increasing energy efficiency and safety for passengers. Such a big change requires strong collaboration and efforts among public administration, research and stakeholders in developing, testing and promoting these technologies in the public transportation. Working in this direction, in the present work the impact of the introduction of driverless electric minibuses, for the first and last mile transportation, in the public service is studied. More specifically, this paper covers a state of the art in terms of technological background for automation, energy efficiency via electrification, and the current state of the legal framework in Europe with focus on the Baltic Sea Region.

This article presents an automated vision-based algorithm for the die-scale inspection of wafer images captured using scanning acoustic tomography (SAT). This algorithm can find defective and abnormal die-scale patterns, and produce a wafer map to visualize the distribution of defects and anomalies on the wafer. The main procedures include standard template extraction, die detection through template matching, pattern candidate prediction through clustering, and pattern classification through deep learning. To conduct the template matching, we first introduce a two-step method to obtain a standard template from the original SAT image. Subsequently, a majority of the die patterns are detected through template matching. Thereafter, the columns and rows arranged from the detected dies are predicted using a clustering method; thus, an initial wafer map is produced. This map is composed of detected die patterns and predicted pattern candidates. In the final phase of the proposed algorithm, we implement a deep learning-based model to determine defective and abnormal patterns in the wafer map. The experimental results verified the effectiveness and efficiency of our proposed algorithm. In conclusion, the proposed method performs well in identifying defective and abnormal die patterns, and produces a wafer map that presents important information for solving wafer fabrication issues.

Despite the growing capabilities of large language models, concerns exist about the biases they develop. In this paper, we propose a novel, automated mechanism for debiasing through specified dataset augmentation in the lens of bias producers that can be useful in a variety of industries, especially ones that are “restricted” and have limited data. We consider that bias can occur due to intrinsic model architecture and dataset quality. The two aspects are evaluated using two different metrics we created. We show that our dataset augmentation algorithm reduces bias as measured by our metrics.

Automated charging technologies are becoming increasingly important in the electrification of heavy road freight transport, especially in combination with autonomous driving. This study provides a comprehensive analysis of automated charging technologies for electric heavy-duty vehicles (HDVs). It encompasses the entire spectrum of feasible technologies, including static and dynamic approaches, with each charging technology evaluated for its advantages, potentials, challenges, and technology readiness level (TRL). Static conductive charging methods such as charging robots, underbody-couplers or pantographs show good potential, with pantographs being the most mature option. These technologies are progressing towards higher TRLs, with a focus on standardization and adaptability. While static wireless charging is operational for some prototype solutions, it encounters challenges related to implementation and efficiency. Dynamic conductive charging through an overhead contact line or contact rails holds promise for high-traffic HDV routes with the overhead contact line being the most developed option. Dynamic wireless charging, although facing efficiency challenges, offers potential for seamless integration into roads and minimal wear and tear. Battery swapping is emerging as a practical solution to reduce downtime for charging, with varying levels of readiness across different implementations. To facilitate large-scale deployment further standardization efforts are required. The study emphasizes the necessity for continued research and development to enhance efficiency, decrease costs, and ensure seamless integration into existing infrastructures. Technologies that achieve this best will have the highest potential to significantly contribute to the creation of an efficiently automated and environmentally friendly transport sector.

The rapid evolution of information and communication technologies, notably the Internet, has yielded substantial benefits while posing challenges to information system security. With an increasing frequency of cyber threats—from unauthorized access to data breaches—the digital landscape's vulnerability is evident. Addressing the financial impact of cybercrime, this study delves into the role of Artificial Intelligence (AI) and Machine Learning (ML) technologies in cybersecurity. Analyzing advancements and outcomes, the research explores practical techniques for anomaly detection, threat prediction, and automated response. By investigating prior research and real-world implementations, the study provides valuable insights into the potential of AI/ML, uncovering current trends, challenges, and prospects in enhancing cybersecurity tactics amid a dynamically changing threat landscape.

The capability of extracting information and analyze it into a common format is essential for performing predictions, comparing projects through cost benchmarking, and for having a deeper understanding of the project costs. However, the lack of standardization and the manual inclusion of the data makes this process very time-consuming, unreliable, and inefficient. To tackle this problem, a novel approach with a big impact is presented combining the benefits of data mining, statistics, and machine learning to extract and analyze the information related to railway costs infrastructure data. To validate the suggested approach, data from 23 real historical projects from the client network rail was extracted, allowing their costs to be comparable. Finally, some machine learning and data analytics methods were implemented to identify the most relevant factors allowing for costs benchmarking. The presented method proves the benefits of data extraction being able to gather, analyze and benchmark each project in an efficient manner, and deeply understand the relationships and the relevant factors that matter in infrastructure costs.

Crack inspection is important to monitor the structural health of pavement structures and to facilitate an easier rehabilitation process. Currently, pavement crack inspection is conducted manually, which is inefficient and costly at the same time. For solving the problem, this work has developed a robotic system for automated data collection and analysis in real-time. The robotic system navigates on the pavement and collects visual images from the surface. A deep learning-based semantic segmentation framework named RCDNet was proposed and implemented on the onboard computer of the robot to identify cracks from the visual images. Simulation results show that the deep learning model obtained 96.29% accuracy for predicting the images. The proposed robotic system was tested on both indoor and outdoor environments and was observed that it can complete inspecting a 3m × 2m grid within 10 minutes and a 2.5m × 1m grid within 6 minutes. This outcome shows that the proposed robotic method can drastically reduce the time of manual inspection. Furthermore, a severity map based on the results from visual images was also generated to provide an idea of which locations should be paid more attention to repair in a test grid.

In recent years, ontology plays an important role in facilitating the semantic description of images which consists of describing the image by a set of words to describe the scene which signifies the belonging of the image. This description specified in several archaeological fields such as cultural, religious objects and heritage objects of France. However, the description of archaeological images is not yet exploited because this field is very diverse. In this article, we present a panel of ontology construction methods as well as archaeological ontologies. Also, we show our own OntunAr ontology to describe Tunisian archaeological images. In addition, we integrate OnTunAr into the automatic annotation of Tunisian archaeological images.

Many studies in the field of robot navigation have focused on environment representation and localization. The goal of map representation is to summarize spatial information in topological and geometrical abstracts. By providing strong priors, maps improve the performance and reliability of automated robots. Due to the transition to fully automated driving in recent years, there has been a constant effort to design methods and technologies to improve the precision of road participants and the environment's information. Among these efforts is the High Definition (HD) Map concept. Making HD maps requires accuracy, completeness, verifiability, and extensibility. Because of the complexity of HD mapping, it is currently expensive and difficult to implement, particularly in an urban environment. In an urban traffic system, the road model is at least a map with sets of roads, lanes, and lane markers. While more research is being dedicated to mapping and localization, a comprehensive review of the various types of map representation is still required. This paper presents a brief overview of map representation, followed by a detailed literature review of HD Map for automated vehicles. The current state of AV mapping is encouraging, the field has matured to a point where detailed maps of complex environments are built in real-time and have been proved useful. Many existing techniques are robust to noise and can cope with a large range of environments. Nevertheless, there are still open problems for future research. AV mapping will continue to be a highly active research area essential to the goal of achieving full autonomy.

Modern agent-based models (ABM) and other simulation models require evaluation and testing of many different parameters. Managing that testing for large scale parameter sweeps (grid searches) as well as storing simulation data requires multiple, potentially customizable steps that may vary across simulations. Furthermore, parameter testing, processing, and analysis are slowed if simulation and processing jobs cannot be shared across teammates or computational resources. While high-performance computing (HPC) has become increasingly available, models can often be tested faster through the use of multiple computers and HPC resources. To address these issues, we created the Distributed Automated Parameter Testing (DAPT) Python package. By hosting parameters in an online (and often free) "database", multiple individuals can run parameter sets simultaneously in a distributed fashion, enabling ad hoc crowdsourcing of computational power. Combining this with a flexible, scriptable tool set, teams can evaluate models and assess their underlying hypotheses quickly. Here we describe DAPT and provide an example demonstrating its use.

Since the 1970s, the application of microprocessor in industrial machinery and the development of computer systems have transformed the manufacturing landscape. The rapid integration and automation of production systems have outpaced the development of suitable human design criteria, creating a deepening gap where human factor was seen as an important source of errors and disruptions. Today the situation seems different: the scientific and public debate about the concept of Industry 4.0 has raised the awareness about the central role humans have to play in manufacturing systems, to the design of which they must be considered from the very beginning. The future of industrial systems, as represented by Industry 4.0, will rely on the convergence of several research fields such as Intelligent Manufacturing Systems (IMS), Cyber-Physical Systems (CPS), Internet of things (IoT), but also socio-technical fields such as social approaches within technical systems. This article deals with different Human dimensions associated with CPS and IoT and focuses on their conceptual evolution of automatization to improve the sociability of such automated production systems and consequently puts again the human in the loop. Hereby, our aim is to take stock of current research trends, and to show the importance of integrating human operators as a part of a socio-technical system based autonomous and intelligent products or resources. As results, different models of sociability as way to integrate human into the broad sense and/or the development of future automated production systems, were identified from the literature and analysed.

Visualising textual content could be helpful to professionals as well as amateurs across several fields. However, training a text-to-image generator in the mainstream domain requires large amounts of paired text-image and data, which is too expensive to collect since labeling millions of images and videos can be tiresome. GANs like StackGAN and StyleGAN can be considered as solutions to generate images from text. But the images generated may be of low accuracy and resolution, and the entire processing can be highly time-consuming. Moreover, image generation is a notion that is still being researched. Hence, the process of developing a Video Generation model necessitates substantial research. Despite the need for such a model, modern technology has lagged behind the solutions to this problem. This proposal suggests combining two methods, Text modification for Action Definition (TexAD) and SeQuential Image Generation for Video Synthesis (SQIGen). The proposed solution synthesises a sequence of images from textual information feeds and combines these images to create a video. TexAD uses Natural Language Processing and Deep Learning techniques to process, classify and modify text data. SQIGen is an extension of the VQGAN+CLIP neural network architecture that generates a sequence of images from the modified text data

Dysprosody is a commonly described feature of speech deterioration due to Parkinson’s disease. Descriptions of the tonal movements underlying dysprosody have been attempted but has not afforded automation. The current study assessed a fully automated acoustic analysis pipeline in terms of its ability to predict human raters’ perception of dysprosody in patients with Parkinson’s disease. Read speech samples of 68 speakers with PD (45 male and 23 female) aged 65.0±9.8 years were assessed by four human clinical experts in terms of dysprosody severity. The recordings were also submitted to a speech processing pipeline in which portions with speech were identified and provided with a parametrization of intonation. Five models were trained and tuned based on 75% of utterances and their perceptual evaluations in a 10-fold cross-validation procedure and evaluated in terms of their ability to predict the perceptual assessments of recordings not included in the training. The performances of models were compared to human raters’ agreement with the majority vote on a speech sample. The results showed that human raters’ assessments of dysprosody can be approximated by the automated procedure. Variability in pitch does not adequately describe the level of dysprosody due to Parkinson’s disease.

The systems for automated monitoring of a human’s personal carbon footprint and CO2-equivalent emissions at industrial enterprises were developed in the article. The personal carbon footprint monitoring system includes data collection subsystems based on energy consumption metering devices, data storage and transmission, and calculation subsystems. To measure the consumption of water, electricity, thermal energy, IoT control sensors were selected. The calculation of the individual carbon footprint of a person is proposed. The system for automated monitoring of the carbon footprint of an enterprise includes a subsystem of devices for monitoring the use of energy resources, a subsystem for data transmission, calculation and prompt display of the carbon footprint. Selected devices for monitoring the consumption of water, energy and heat resources with data transfer to the SCADA system. An algorithm for calculating the carbon footprint of an enterprise is proposed. Structural schemes for automated carbon footprint control have been developed.

The rapid growth of Artificial Intelligence (AI) has led to considerable progress in Automated Fact Verification (AFV). This process involves collecting evidence for a statement, assessing its relevance, and predicting its accuracy. Recently, research has begun to explore automatic explanations as an integral part of the accuracy analysis process. However, the explainability within AFV is lagging compared to the wider field of explainable AI (XAI), which aims at making AI decisions more transparent. This study looks at the notion of explainability as a topic in the field of XAI, with a focus on how it applies to the specific task of Automatic Fact Verification. It examines the explainability of AFV, taking into account architectural, methodological, and dataset-related elements, with the aim of making AI more comprehensible and acceptable to the general society. Although there is a general consensus on the need for AI systems to be explainable, there a dearth of systems and processes to achieve it. In this research, we investigate the concept of explainable AI in general and demonstrate its various aspects through the particular task of Automated Fact Verification. We explore topic of faithfulness in the context of local and global explainability and how these correspond with architectural, methodological and data-based ways of achieving it. We examine these concepts for the specific case of AFV and analyze the current datasets used for AFV and how they can be adapted to further the identified aims on XAI. The paper concludes by highlighting the gaps and limitations in current data science practices and possible recommendations for modifications in architectural and data curation processes that would further the goals of XAI.

There is a strong need and demand from the United Nations, public institutions, and private sector for classifying government publications, policy briefs, academic literature, and corporate social responsibility reports according to their relevance to the Sustainable Development Goals (SDGs). It is well understood that the SDGs play a major role in the strategic objectives of various entities. However, linking projects and activities to the SDGs has not always been straightforward or possible with existing methodologies. Natural language processing (NLP) techniques offer a new avenue to identify linkages for SDGs from text data. This research examines various machine learning approaches optimized for NLP-based text classification tasks for their success in classifying reports according to their relevance to the SDGs. Extensive experiments have been performed with the recently released Open Source SDG (OSDG) Community Dataset, which contains texts with their related SDG label as validated by the community volunteers. Results demonstrate that especially RoBERTa achieves very high performance in the attempted task, which is promising for automated processing of large collections of sustainability reports for detection of relevance to SDGs.

Graphically-rich applications such as games are ubiquitous with attractive visual effects of Graphical User Interface (GUI) that offers a bridge between software applications and end-users. However, various types of graphical glitches may arise from such GUI complexity and have become one of the main component of software compatibility issues. Our study on bug reports from game development teams in NetEase Inc. indicates that graphical glitches frequently occur during the GUI rendering and severely degrade the quality of graphically-rich applications such as video games. Existing automated testing techniques for such applications focus mainly on generating various GUI test sequences and check whether the test sequences can cause crashes. These techniques require constant human attention to captures non-crashing bugs such as bugs causing graphical glitches. In this paper, we present the first step in automating the test oracle for detecting non-crashing bugs in graphically-rich applications. Specifically, we propose GLIB based on a code-based data augmentation technique to detect game GUI glitches. We perform an evaluation of GLIB on 20 real-world game apps (with bug reports available) and the result shows that GLIB can achieve 100\% precision and 99.5\% recall in detecting non-crashing bugs such as game GUI glitches. Practical application of GLIB on another 14 real-world games (without bug reports) further demonstrates that GLIB can effectively uncover GUI glitches, with 48 of 53 bugs reported by GLIB having been confirmed and fixed so far.

The world's growing population is highly dependent on animal agriculture. Animal products provide nutrient-packed meals that help to sustain individuals of all ages in communities across the globe. As the human demand for animal proteins grows, the agricultural industry must continue to advance its efficiency and quality of production. One of the most commonly farmed livestock is poultry and their significance is felt on a global scale. Current poultry farming practices result in the premature death and rejection of billions of chickens on an annual basis before they are processed for meat. This loss of life is concerning regarding animal welfare, agricultural efficiency, and economic impacts. The best way to prevent these losses is through the individualistic and/or group level assessment of animal on a continuous basis. On large-scale farms, such attention to detail was generally considered to be inaccurate and inefficient, but with the integration of Artificial Intelligence (AI) assisted technology individualized and per-herd assessments of livestock are possible and accurate. Various studies have shown cameras linked with specialized systems of AI can properly analyze flocks for health concerns, thus improving the survival rate and product quality of farmed poultry. Building on the recent advancements, this review explores the aspects of AI in the detection, counting and tracking of the poultry in commercial and research-based applications.

The quantitative and qualitative assessment of gold grains from samples of glacial till is a well-established method for exploring gold deposits hidden under glaciated cover. This method, widely used by the industry and which produced numerous successes in locating gold deposits in glaciated terrain, is still based on artisanal gravity separation techniques and visual identification. However, being artisanal, it is limited by inconsistent recoveries and the difficulty to visually identify the predominantly occurring small gold grains. These limitations hinder its capability to deceipher subtle or complex signal. To improve detection limits through recovery of small gold grains, a new approach has recently been introduced in the industry (commercially referred as “ARTGold” procedure) using an optimized miniature sluice box coupled with an automated scanning electron microscopy routine. The capabilities of this improved method are highlighted by comparing till surveys conducted around the Borden gold deposit (Ontario, Canada) using the conventional and improved methods at both local and regional scales. Relative to the conventional approach, the improved method recovered almost one order of magnitude more gold grains from samples (regional and down-ice mineralization), dominantly in small size fractions. Increasing the counts in low-abundance regional samples enables better discrimination between background signals and significant dispersions. The method offers an alternative to improve characterization of gold dispersal in glaciated terrain and the related gold deposit footprints.

This study describes the development of an automated bag valve mask (BVM) compression system, which, during acute shortages and supply chain disruptions can serve as a temporary emergency ventilator. The resuscitation system is based on the Arduino controller with a real-time operating system installed on a largely RepRap 3-D printable parametric component-based structure. The cost of the system is under $170, which makes it affordable for replication by makers around the world. The device provides a controlled breathing mode with tidal volumes from 100 to 800 milliliters, breathing rates from 5 to 40 breaths/minute, and inspiratory-to-expiratory ratio from 1:1 to 1:4. The system is designed for reliability and scalability of measurement circuits through the use of the serial peripheral interface and has the ability to connect additional hardware due to the object-oriented algorithmic approach. Experimental results demonstrate repeatability and accuracy exceeding human capabilities in BVM-based manual ventilation. Future work is necessary to further develop and test the system to make it acceptable for deployment outside of emergencies in clinical environments, however, the nature of the design is such that desired features are relatively easy to add with the test using protocols and parametric design files provided.

Recent researches proved that the underbridge geometry can be reconstructed by mounting a 3D laser scanner on a motorized cart travelling on a walkway located under the bridge. The walkway is moved by a truck and the accuracy of the bridge model depends on the accuracy of the trajectory of the scanning head with respect to a fixed reference system. In this paper, we describe the metrological characterization of a method that uses non-contact systems to identify the relative motion of the cart with respect to the walkway; the orientation of the walkway with respect to the bridge is determined using inclinometers and optical rails, while the position of the truck with respect to the bridge is measured using a conventional odometer. The measurement uncertainty of the proposed system was initially evaluated by numerical simulations and successively verified by experiments in laboratory conditions. The complete system has then been tested in operative conditions; the validity of the proposed approach has been demonstrated by comparing the geometry of buildings reconstructed with the proposed system with the geometry obtained with a static scan. Results evidenced that the errors are approximately 6 mm.

1) Introduction: Brain parcellation is an important processing step in the analysis of structural brain MRI. Existing software implementations are optimized for fully developed adult brains, and provide inadequate results when applied to neonatal brain imaging. 2) Methods: We developed a semi-automated pipeline, NeBSS, for extracting 50 discrete brain structures from neonatal brain MRI, using an atlas registration method that leverages the existing ALBERT neonatal atlas 3) Results: We demonstrate a simple linear workflow for neonatal brain parcellation. NeBSS is robust to variation in imaging acquisition protocol and magnet field strength. 4) Conclusion: NeBSS is a robust pipeline capable of parcellating neonatal brain MRIs using a simple processing workflow. NeBSS fills a need in clinical translational research in neonatal imaging, where existing automated or semi-automated implementations are too rigid to be successfully applied to multi-center neuroprotection studies and clinically heterogeneous cohorts. The software is open source and freely available.

Lateral vehicle control is a high importance in automated vehicles as it directly influences the vehicle’s performance and safety during operation. The Linear Quadratic Regulator (LQR) controller stands out due to its high-performance characteristics and is used in the open source for self driving functions. However, a notable limitation of the current approach is the manual calibration of LQR controllers based on the experience and intuition of the designers, leading to empirical uncertainties. To address this issue and enhance the lateral control performance, this paper concentrates on refining the LQR by employing three optimization algorithms: Artificial Bee Colony Optimization (ABC), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). These algorithms aim to overcome the reliance on empirical methods and enable a data-driven approach to LQR calibration. By comparing the outcomes of these optimization algorithms to the manual LQR controller within an offline multibody simulation as testing platform, the study highlights the superiority of the best-performing optimization approach. Following this, the optimal algorithm is implemented on a real-time system for the full vehicle level, revealing the Model-in-the-Loop and the Hardware-in-the-Loop gap up to 78,89% with lateral velocity when we use Relative Error Criterion (REC) method to validate and 2.35m with lateral displacement when considering by maximum absolute value method.

Recent global trends related to the increasing use of e-commerce are becoming a challenge for courier transport especially in the last-mile process of delivering products to the final retail recipient. One of the delivery methods is the personal collection of the parcel in an automated post box, available 24/7 for the customer. This research aims to define the most important attributes of the courier services quality, including the delivery of parcels through automated sending and receiving parcel lockers, leveraging advanced technologies, data, and connectivity to enhance the quality of life, sustainability, and efficiency for city residents. The research was based on a preliminary selection of the most important features of parcel lockers’ service quality, which were extracted from the analysis of scientific literature and previous research. The analysis was carried out by conducting a survey among city parcel locker users that provided data coded according to the dimensions of the Kano model. This allowed to conclude that the location of parcel stations, ensuring improvements for the disabled, adjusting the size of the parcel to the size of the box, proper placement of the parcel in the box and a properly functioning dedicated application are the most important features in the process of automatic delivery of parcels to recipients in urban areas. This paper enriches the literature on customer service quality of self-service technologies for last-mile delivery with the use of automated parcel lockers.

To solve two key problems in the identification of people who are infected with COVID-19: the first problem is that the identification accuracy is not high enough. The second problem is that present identification method such as nucleic acid testing is expensive in many countries. Methods: So, I decided to design a fast identification method for COVID-19 patients which is based on deep learning. After the model (CoughNet) learns more than 6,000 cough spectrograms of both COVID-19 patients and normal people, the accuracy rate of identification of COVID-19 patients and normal people is higher than 99% in the test set. Structure: This paper is mainly divided into three parts: the first part introduces the main background and research status of the research; The second part introduces the research methods; The third part introduces the specific process of the experiment.

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under report. Visual analysis of a 24 hour EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We study a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology to reduce the EEG dataset by classifying part of the data automatically, while retaining 100% detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when automatically classifying around 90% (60%) of the data. Perfect DS can be achieved when automatically classifying 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are used to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

Next-generation sequencing (NGS) has been a widely-used technology in biomedical research for understanding the role of molecular genetics of cells in health and disease. A variety of computational tools have been developed to analyse the vastly growing NGS data, which often require bioinformatics skills, tedious work and significant amount of time. To facilitate data processing steps minding the gap between biologists and bioinformaticians, we developed CSI NGS Portal, an online platform which gathers established bioinformatics pipelines to provide fully automated NGS data analysis and sharing in a user-friendly website. The portal currently provides 16 standard pipelines for analysing data from DNA, RNA, smallRNA, ChIP, RIP, 4C, SHAPE, circRNA, eCLIP, Bisulfite and scRNA sequencing, and is flexible to expand with new pipelines. The users can upload raw data in fastq format and submit jobs in a few clicks, and the results will be self-accessible via the portal to view/download/share in real-time. The output can be readily used as the final report or as input for other tools depending on the pipeline. Overall, CSI NGS Portal helps researchers rapidly analyse their NGS data and share results with colleagues without the aid of a bioinformatician. The portal is freely available at: https://csibioinfo.nus.edu.sg/csingsportal

Accurate inundation maps for flooded wetlands and rivers are a critical resource for their management and conservation. In this paper we automate a method (thresholding of the short-wave infrared band) for classifying inundation, using Landsat imagery and Google Earth Engine. We demonstrate the method in the Okavango Delta, northern Botswana, a complex case study due to the spectral overlap between inundated areas covered with aquatic vegetation and dryland vegetation classes on satellite imagery. Inundation classifications in the Okavango Delta have predominately been implemented on broad spatial resolution images. We present the longest time series to date (1990-2019) of inundation maps at high spatial resolution (30m) for the Okavango Delta. We validated the maps using image-based and in situ data accuracy assessments, with accuracy ranging from 91.5 - 98.1%. Use of Landsat imagery resulted in consistently lower estimates of inundation extent than previous studies, likely due to the increased number of mixed pixels that occur when using broad spatial resolution imagery, which can lead to overestimations of the size of inundated areas. We provide the inundation maps and Google Earth Engine code for public use.

Τhe concept of remote insect surveillance at large spatial scales for a number of serious insect pests of agricultural and medical importance is introduced in a series of our papers. We augment typical, low-cost plastic traps for many insect pests with the necessary optoelectronic sensors to guard the entrance of the trap in order to detect, time-stamp, GPS tag, and –in relevant cases- identify the species of the incoming insect from their wingbeat. For every important crop pest there are monitoring protocols to be followed in order to decide when to initiate a treatment procedure before a serious infestation occurs. Monitoring protocols are mainly based on specifically designed insect traps. Traditional insect monitoring suffers in that the scope of such monitoring: is curtailed by its cost, requires intensive labor, is time consuming, an expert is often needed for sufficient accuracy and can sometimes raise safety issues for humans. These disadvantages reduce the extent to which manual insect monitoring is applied and therefore its accuracy, which finally results in significant crop loss due to damage caused by pests. With the term ‘surveillance’ we intend to push the monitoring idea to unprecedented levels of information extraction regarding the presence, time-stamping detection events, species identification and population density of targeted insect pests. Insect counts as well as environmental parameters that correlate with insect’s population development are wirelessly transmitted to the central monitoring agency in real time, are visualized and streamed to statistical methods to assist enforcement of security control to insect pests. In this work we emphasize on how the traps can be self-organized in networks that collectively report data at local, regional, country, continental, and global scales using the emerging technology of the Internet of Things (IoT). This research is necessarily interdisciplinary and falls at the intersection of entomology, optoelectronic engineering, data-science and crop science and encompasses the design and implementation of low-cost, low-power technology to help reduce the extent of quantitative and qualitative crop losses by many the most significant agricultural pests. We argue that smart traps communicating through IoT to report in real-time the level of the pest population from the field straight to a human controlled agency can, in the very near future, have a profound impact on the decision making process in crop protection and will be disruptive of existing manual practices. In the present study, three cases are investigated : monitoring Rhynchophorus ferrugineus (Olivier) (Coleoptera: Curculionidae) using a) Picusan and b) Lindgren trap, and c) monitoring various stored grain beetle pests using the pitfall trap.

Diagnosing melanocytic lesions is among the most challenging problems in the practice of pathology. The difficulty of physically masking melanin pigment and the similarity of its color to commonly used chromogens often complicate examination of the cytomorphology and immunohistochemical staining results for tumor cells. Melanin bleach can be very helpful for histopathological diagnosis of heavily pigmented melanocytic lesions. Although various depigmentation methods have been reported, no standardized methods have been developed. This study developed a fully automated platform that incorporates hydrogen peroxide-based melanin depigmentation in an automated immunohistochemical analysis. The utility of the method was tested in one cell block of malignant melanoma cells in pleural effusion, ten ocular melanoma tissue samples, and ten cutaneous melanoma tissue samples. Our results demonstrated that the proposed method, which can be performed in only 3 hours, effectively preserves cell cytomorphology and immunoreactivity. The method is particularly effective for removing melanin pigment to facilitate histopathological examination of cytomorphology and for obtaining an unmasked tissue section for immunohistochemical analysis.

Regular inspections during construction work verify that the work completed is consistent with the plans and specifications and ensure that it is within the planned time and budget. This requires frequent physical site observations to independently measure and verify the completion percentage of the construction progress performed over periods of time. The current computer vision-based (CV) techniques for the measurement of as-built elements, predominantly use 3D laser scanning or 3D Photogrammetry modelling to determine the geometrical properties of as-built elements on construction sites. Both techniques require data acquisition from several positions and angles to generate sufficient information about the element’s coordinates making the deployment of these techniques on dynamic construction project sites a challenging task. In this paper, we propose a pipeline for automating the measurement of as-built components using artificial intelligence (AI) and computer vision (CV) techniques. The pipeline requires a single image obtained with a stereo-camera system to measure the size of selected objects or as-built components. We demonstrate our approach by measuring the size of concrete walls and columns. The novelty of this work is attributed to the fully automated CV-based method for measuring any given element using a single image only. The proposed solution is suitable for use in measuring the sizes of as-built components of built assets. It has the potential to be further developed and integrated with BIM models for use on construction projects for progress monitoring.

This study aims to develop novel automated computer vision algorithms and systems for component replacement inspection for Printed Circuit Boards (PCBs). The proposed algorithms are able to identify locations as well as sizes of different components. They are object detection algorithms based on keypoints of the target components. The algorithms can be implemented as neural networks consisting of two portions: frontend networks and backend networks. The frontend networks are used for the feature extractions of input images. The backend networks are adopted for producing component inspection results. Each component class can has its own frontend and backend networks. In this way, the neural model for the component class can be effectively reused for different PCBs. To reduce the computation time for the inference of the networks, different component classes can share the same frontend networks. A two-stage training process is proposed for effectively exploring features of different components for accurate component inspection. The proposed algorithm has the advantages of the simplicity for training data collection, high accuracy for defect detection, and high reusability and flexibility for online inspection. The algorithm is an effective alternative for the automated inspection in smart factory with growing demand for product quality and diversification.

Nowadays, power sector is an area that gather great scientific interest, due to events such as the increase in electricity prices in the wholesale energy market and new investments due to technological development in various sectors. These new challenges have in turn created new needs, such as the accurate prediction of the electrical load of the end users. On the occasion of the new challenges, Artificial Neural Networks approaches have become increasingly popular due to their ability to adopt efficiently to time-series predictions. In this paper, it is presented the development of a model which, through an automated process, will provide an accurate prediction of electrical load for the island of Thira in Greece. Through an automated application, deep learning load forecasting models have been created, such as Multilayer Perceptron, Long Short-Term Memory (LSTM), Convolutional Neural Network One Dimensional (CNN-1D), CNN-LSTM, Temporal Convolutional Network (TCN) and a proposed hybrid model called Convolutional LSTM Encoder-Decoder. The results in terms of prediction accuracy show satisfactory performances for all models, with the proposed hybrid model achieving the best accuracy.

Many spatial decision support systems suffer from user adoption issues in practice due to lack of trust, technical expertise, and resources. Automated machine learning has recently allowed non-experts to explore and apply machine learning models in the industry without requiring abundant expert knowledge and resources. This paper reviews recent literature from 136 papers, and proposes a general framework for integrating spatial decision support systems with automated machine learning to lower major user adoption barriers. Challenges of data quality, model interpretability, and practical usefulness were discussed as general considerations for system implementation. Research opportunities related to spatially explicit models in AutoML, and resource-aware, collaborative/connected, and human-centered systems were also discussed to address these challenges. This paper argues that integrating spatial decision support systems with automated machine learning can not only encourage user adoption, but also mutually benefit research in both fields — bridging human-related and technical advancements for fostering future developments in spatial decision support systems and automated machine learning.

During the past few years many projects and initiatives were undertaken deploying and testing automated vehicles for public transportation and logistics. However in spite of their ambition, all of these deployments stayed on the level of elaborated experimentation deploying no more than 4 maximum 5 AVs in rather small sites (few Kms of roads) and never really reached the level of large scale “commercial” deployment of transport services. The reasons for this are many, but the most important being the lack of economically viability and commercially realistic models, the lack of scalability of the business and operating models, and the lack of inclusive citizen/user centric services required for the large end-user acceptation and adoption of the solutions. In this paper, based on the experience gained in the H2020 AVENUE project, we present the missing pieces of the puzzle, ad which will be addressed in the Horizon Europe project ULTIMO.

Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high performance end-to-end machine learning pipelines with minimal effort from the user. However, despite AutoML showing great promise for computer vision tasks, to the best of our knowledge, no study has used AutoML for image-based plant phenotyping. To address this gap in knowledge, we examined the application of AutoML for image-based plant phenotyping using wheat lodging assessment with UAV imagery as an example. We compared the performance of an open-source AutoML framework, AutoKeras in image classification and regression tasks to transfer learning using modern convolutional neural network (CNN) architectures. For image classification which classified plot images as lodged or non-lodged, transfer learning with Xception and DenseNet-201 achieved best classification accuracy of 93.2%, whereas Autokeras had 92.4% accuracy. For image regression which predicted lodging scores from plot images, transfer learning with DenseNet-201 had the best performance (R2=0.8303, RMSE=9.55, MAE=7.03, MAPE=12.54%), followed closely by AutoKeras (R2=0.8273, RMSE=10.65, MAE=8.24, MAPE=13.87%). Interestingly, in both tasks, AutoKeras models had up to 40-fold faster inference times compared to the pretrained CNNs. The merits and drawbacks of AutoML compared to transfer learning for image-based plant phenotyping are discussed.

Malware analysis is fundamental for defending against prevalent cyber security threats, and requires a means to deploy and study behavioural software traits as more sophisticated malware is developed. Traditionally, virtual machines are used to provide an environment that is isolated from production systems so as to not cause any adverse impact on existing infrastructure. Malware developers are fully aware of this and so will often develop evasion techniques to avoid detection within sandbox environments. In this paper, we conduct an investigation of anti-evasion malware triggers for uncovering malware that may attempt to conceal itself when deployed in a traditional sandbox environment. To facilitate our investigation, we developed a tool called MORRIGU that couples together both automated and human-driven analysis for systematic testing of anti-evasion methods using dynamic sandbox reconfiguration techniques. This is further supported by visualisation methods for performing comparative analysis of system activity when malware is deployed under different sandbox configurations. Our study reveals a variety of anti-evasion traits that are shared amongst different malware families, such as sandbox `wear-and-tear', and Reverse Turing Tests (RTT), as well as more sophisticated malware samples that require multiple anti-evasion checks to be deployed. We also perform a comparative study using Cuckoo sandbox to demonstrate the limitations of adopting only automated analysis tools, to justify the exploratory analysis provided by MORRIGU. By adopting a clearer systematic process for uncovering anti-evasion malware triggers, as supported by tools like MORRIGU, this study helps to further the research of evasive malware analysis so that we can better defend against such future attacks.

In this work, an algorithm for the scheduling of household appliances to reduce the energy cost and the peak-power consumption is proposed. The system architecture of a home energy management system (HEMS) is presented to operate the appliances. The dynamics of thermal and non-thermal appliances is represented into state-space model to formulate the scheduling task into a mixed-integer-linear-programming (MILP) optimization problem. Model predictive control (MPC) strategy is used to operate the appliances in real-time. The HEMS schedules the appliances in a dynamic manner without any a priori knowledge of the load-consumption pattern. At the same time, HEMS responds to the real-time electricity market and the external environmental conditions (solar radiation, ambient temperature etc). Simulation results exhibit the benefits of proposed HEMS by showing the reduction of up to 47% in electricity cost and up to 48% in peak power consumption.

Remediation of IT issues encoded into domain-specific or user-defined alerts occurring in cloud environments and customer ecosystems in a vast majority of cases suffers from accurate recommendations which could be timely supplied for recovery of performance degradations. That, of course, is hard to realize through furnishing those abnormality definitions with an appropriate expert knowledge which varies from one environment to another. At the same time, in a large proportion of support cases, the reported problems under Global Support Services (GSS) or Site Reliability Engineering (SRE) treatment ultimately go down to the product teams making them waste costly development hours on investigating self-monitoring metrics of our solutions. Therefore, the mean-time-to-resolution (MTTR) rates of problems/alerts are significantly impacted from lack of a systematic approach towards adopting AI Ops. That would imply building, maintaining, and continuously improving/annotating a data store of insights that ML models are trained and generalized across the whole customer base and corporate cloud services. Our ongoing study is in line with such a vision and validates an approach that learns the alert resolution patterns in such a global setting and explains them using interpretable AI methodologies. The knowledge store of causative rules is then applied in predicting potential sources of the application degradation reflected in an active alert instance. In this communication, we share our experiences with a prototype solution and up to date analysis demonstrating how root conditions are discovered with a high accuracy for a specific type of problem. It is validated against the historical data of resolutions performed by heavy manual development efforts. We also offer a Dempster-Shafer theory-based rule verification framework for experts as a what-if analysis tool to test their hypotheses about underlying environment.

Abstract Purpose: To analyze the correspondence between refractive astigmatism and corneal astigmatism in pseudophakic eyes with non-toric intraocular lenses. Setting: Yeouido St. Mary hospital, Seoul, South Korea Design: Evaluation of a diagnostic test instrument. Methods: This retrospective study included 95 eyes of 95 patients. Corneal astigmatism was measured with an automated keratometer (RK-5, Canon) and Scheimpflug tomography (Pentacam HR, Oculus). Refractive astigmatism was compared to keratometric astigmatism (based on anterior corneal measurements only), Equivalent K Reading and total corneal astigmatism (both based on anterior and posterior corneal measurements). Vector analysis was carried out by Næser’s polar value method. The accuracy was defined as the average magnitude of the vectorial difference in astigmatism (DA). Each corneal measurement was optimized in retrospect by a multiple linear regression equation between refractive and corneal astigmatism. Results: Keratometric astigmatism overestimated with-the-rule (WTR) refractive astigmatism and underestimated against-the-rule (ATR) refractive astigmatism. Several measurements based on both corneal surfaces values did not show any statistically significant difference with respect to refractive astigmatism. The mean corneal astigmatism by total corneal refractive power (TCRP) at 4.0 mm (zone/pupil) produced the lowest mean arithmetic DA and the highest percentage of eyes with a DA ≤0.50 diopter. After optimization, the accuracies of automated KA and TCRP 4.0 mm (zone/pupil) were similar. Conclusions: Total corneal astigmatism measured by the Scheimpflug tomography at 4.0 mm zone centered on pupil, accurately reflects the refractive astigmatism in pseudophakic eyes. However, the accuracy of total corneal astigmatism is not different from automated KA after optimization.

The pervasiveness of cardiovascular disease and physician misdiagnosis creates the urgent need for artificial intelligence models to improve diagnosis accuracy. The first objective of this study was to train machine learning models on publicly available data sets containing simple medical information of patients to diagnose cardiovascular disease. The Multilayer Perceptron (MLP) assembled for this task performed optimally with an F1 score of 0.8968. This prompted the creation of an open-source, automated cardiovascular disease diagnosis tool, powered by the MLP. The second objective of this study was to employ a meta-learning methodology called Local Interpretable Model-Agnostic Explanations (LIME) to understand the impact of different features on the model's diagnosis in the form of marginal probabilities. K-Means Clustering was employed to segment the data into ten clusters, after which each data example was passed through LIME. The resulting histograms depict the complex relationship between feature, cluster, and impact on diagnosis. A series of P-values with contrasting orders of magnitude shows the nuances in the MLP's understanding of patients from different clusters. The results of meta-learning analysis reveal that the most important features for cardiovascular disease diagnosis are fasting blood sugar, type of chest pain, and slope of the ST segment on an electrocardiogram. Future experiments should replicate the novel methodology introduced in this study on data sets containing more specialized medical features in order to gain practical medical insights about different types of cardiovascular disease represented by each cluster. Finally, feature engineering pathways should be explored with consideration of these results to create versatile diagnosis models not only for cardiovascular disease, but adaptable to other diseases as well.

The increasingly used approach of combining different simulation software in testing of automated driving systems (ADS) increases the need for potential and convenient software designs. Recently developed co-simulation platforms (CSP) provide the possibility to cover the high demand on testing kilometers for ADS by combining vehicle simulation software (VSS) with traffic flow simulation software (TFSS) environments. The emphasis on the demand of testing kilometers is not enough to choose a suitable CSP. The complexity level of the used vehicle, object, sensors and environment models is essential for valid and representative simulation results. Choosing a suitable CSP raises the question of how the test procedures should be defined and constructed and what the relevant test scenarios are. Parameters of the ADS, the environments, objects, sensors in VSS as well as traffic parameters in TFSS can be used to define and generate test scenarios. In order to generate a large number of scenarios in a systematic and automated way, suitable and appropriate software designs are required. In this paper we present a software design for CSP based on the Model-View-Controller (MVC) design pattern and implementation of a complex CSP for virtual testing of ADS. Based on this design, an implementation of a CSP is presented using the VSS from IPG Automotive called CarMaker and the TFSS from PTV Group called Vissim. The results have shown that the presented CSP design and the implementation of the co-simulation can be used to generate relevant scenarios for testing of ADS.

Gesture recognition has always been a technique to decrease the distance between the physical and the digital world. In this work, we introduce an Arduino based vehicle system which no longer require manual controlling of the cars. The proposed work is achieved by utilizing the Arduino microcontroller, accelerometer, RF sender/receiver, and Bluetooth. Two main contributions are presented in this work. Firstly, we show that the car can be controlled with hand-gestures according to the movement and position of the hand. Secondly, the proposed car system is further extended to be controlled by an android based mobile application having different modes (e.g., touch buttons mode, voice recognition mode). In addition, an automatic obstacle detection system is introduced to improve the safety measurements to avoid any hazards. The proposed systems are designed at lab-scale prototype to experimentally validate the efficiency, accuracy, and affordability of the systems. We remark that the proposed systems can be implemented under real conditions at large-scale in the future that will be useful in automobiles and robotics applications.

An automated discharge imaging system (ADIS), a non-intrusive and safe approach, was developed for measuring river flows during flash flood events. ADIS consists of dual cameras to capture complete surface images in the near and far fields. Surface velocities are accurately measured using the Large Scale Particle Image Velocimetry (LSPIV) technique. The stream discharges are then obtained from the depth-averaged velocity (based upon an empirical velocity-index relationship) and cross-section area. The ADIS was deployed at the Yu-Feng gauging station in Shimen Reservoir upper catchment, northern Taiwan. For a rigorous validation, surface velocity measurements were conducted using ADIS/LSPIV and other instruments. In terms of the averaged surface velocity, all measured results were in good agreement with small differences, i.e., 0.004 to 0.39 m/s and 0.023 to 0.345 m/s when compared to those from acoustic Doppler current profiler (ADCP) and surface velocity radar (SVR), respectively. The ADIS/LSPIV was further applied to measure surface velocities and discharges during typhoon events (i.e., Chan-Hom, Soudelor, Goni, and Dujuan) in 2015. The measured water level and surface velocity both showed rapid increases due to flash floods. The estimated discharges from ADIS/LSPIV and ADCP were compared, presenting good consistency with correlation coefficient R = 0.996 and normalized root mean square error NRMSE = 7.96%. The results of sensitivity analysis indicate that components till (τ) and roll (θ) of the camera are most sensitive parameter to affect the surface velocity using ADIS/LSPIV. Overall, the ADIS based upon LSPIV technique effectively measures surface velocities for reliable estimations of river discharges during typhoon events.

This paper presents novel feature descriptors and classification algorithms for automated scoring of HER2 in Whole Slide Images (WSI) of breast cancer histology slides. Since a large amount of processing is involved in analyzing WSI images, the primary design goal has been to keep the computational complexity to the minimum possible level and to use simple, yet robust feature descriptors that can provide accurate classification of the slides. We propose two types of feature descriptors that encode important information about staining patterns and the percentage of staining present in ImmunoHistoChemistry (IHC) stained slides. The first descriptor is called a characteristic curve which is a smooth non-increasing curve that represents the variation of percentage of staining with saturation levels. The second new descriptor introduced in this paper is an LBP feature curve which is also a non-increasing smooth curve that represents the local texture of the staining patterns. Both descriptors show excellent interclass variance and intraclass correlation, and are suitable for the design of automatic HER2 classification algorithms. This paper gives the detailed theoretical aspects of the feature descriptors and also provides experimental results and comparative analysis.

Document deskewing is a fundamental problem in document image processing. While existing methods have limitations, such as Hough Line Transformation that can deskew images upside down, and Deep Learning models that require huge amounts of human labour and computational resources and still fail to deskew while taking care of orientation, OCR-based methods also struggle to read text when it is tilted. In this paper, we propose a novel, simple, cost-effective deep learning method for fixing the skew and orientation of documents. Our approach reduces the search space for the machine learning model to predict whether an image is upside down or not, avoiding the huge search space of predicting an angle between 0 and 360. We finetuned a MobileNetV2 model, which was pre-trained on imagenet, using only 200 images and achieve good results. This method is useful for automation-based tasks, such as data extraction using OCR technology, and can greatly reduce manual labour.

Driver’s distractions are more prone to occur with automated driving vehicles, which might turn into cancelling some of their advantages. Traffic reports, naturalistic observations and in-lab tests are carried out to determine the influence of driver’s distractions in car crashes and to develop technology to detect and prevent them from happening. One of the best strategies to cope with this problem is education. In this work we propose a simulation environment to design laboratory experiments to study driver’s distractions as well as simple games to train drivers to take over the control of the vehicle when required. The result framework enables drivers to experience driving highly automated cars in their neighborhoods or in places of their choice with different levels of events to check their ability in taking over the control when required.

This paper explores the application of machine learning techniques for automated object grasping. Current electronic prosthetics often require extensive training for users to gain fine motor control over the prosthetic fingers, hindering their usability and acceptance. To address this challenge, this paper proposes an automated method that leverages computer vision-based techniques and machine learning algorithms. In this study, three reinforcement learning algorithms, namely Soft Actor-Critic (SAC), Deep Q-Network (DQN), and Proximal Policy Optimization (PPO), are employed to train agents for automated grasping tasks. The results indicate that the SAC algorithm achieves the highest success rate of 99% among the three algorithms at just under 200,000 timesteps. This research also shows that object’s physical characteristics can affect the agent’s ability to learn an optimal policy. Moreover, the findings highlight the potential of the SAC algorithm in developing intelligent prosthetic hands with automatic object gripping capabilities.

As the demands in reliability and high-degree of automation in industrial applications are increasing exponentially, the current Industry 4.0 trend lies in migrating towards smarter technologies that increase flexibility and provide autonomous operation. To tackle this, manufacturers shifted towards Real-Time Ethernet communication which supports autonomous operation, faster sensor/actuator configuration and high degree of determinism. Nevertheless, the uninterrupted operating principle of legacy industrial systems as well as the system complexity and heterogeneity constitutes the transition to Real-Time Ethernet very challenging. This article proposes a novel method allowing to automate the generation of executable code for Real-Time Ethernet architectures based on high-level programming models. The method is based on a programming model and modular code artifacts for the hardware architecture, employing Real-Time Ethernet communication. Through an tool-supported algorithm the high-level model is linked to the architecture's communication primitives and interfaces. The tool-support reduces significantly the development and debugging effort for Real-Time Ethernet applications and increases the application reliability, since the generated code is based on verified programming models. Additionally, the tool creates dedicated files, which allow automated industrial network configuration without any human intervention. Finally, by embedding firewall policies into the code generation process, the method guarantees cyber-resilience for the Real-Time Ethernet architecture. We demonstrate the proposed method in Programmable Logic Controllers (PLCs) of a Public Power Corporation's Hydroelectric Power Plant, which control the temperature and rotor speed of a power generator. The results demonstrate the method's ability to generate rapidly trustworthy and fault-tolerant code for the autonomous plant operation. The hurdles in time and effort for developing, configuring and debugging Real-Time Ethernet applications can be minimized through a high-level programming model that allows automated generation of executable code that is reusable for similar applications. Such time and effort reduction may pave the way towards the Industry 4.0 area.

Large-scale land cover plays a crucial role in global resource monitoring and management, as well as research on sustainable development. However, the complexity of the mapping process, coupled with significant computational and data storage requirements, often leads to delays between data processing and product publication, creating challenges for dynamic monitoring of large-scale land cover. Therefore, improving the efficiency of each stage in large-scale land cover mapping and automating the mapping process is currently an urgent and critical issue that needs to be addressed. We propose a high-performance automated large-scale land cover mapping framework(HALF) that introduces high-performance computing technology to the field of land cover production. HALF optimizes key processes, such as automated sample point extraction, sample-remote sensing image matching, and large-scale classification result mosaic and update. We selected several 10°×10° regions globally and the research makes several significant contributions:(1)We design HALF for land cover mapping based on docker and CWL-Airflow, which solves the heterogeneity of models between complex processes in land cover mapping and simplifies the model deployment process. By introducing workflow organization, this method achieves a high degree of decoupling between the production models of each stage and the overall process, enhancing the scalability of the framework. (2)HALF propose an automatic sample points method that generates a large number of samples by overlaying and analyzing multiple prior products, thus saving the cost of manual sample selection. Using high-performance computing technology improved the computational efficiency of sample-image matching and feature extraction phase, with 10 times faster than traditional matching methods.(3)HALF propose a high-performance classification result mosaic method based on the idea of grid division. By quickly establishing the spatial relationship between the image and the product and performing parallel computing, the efficiency of the mosaicking in large areas is significantly improved. The average processing time for a single image is around 6.5 seconds.

The vastness of chemical-space constrains traditional drug-discovery methods to the organic laws that are guiding the chemistry involved in filtering through candidates. Leveraging computing with machine-learning to intelligently generate compounds that meet a wide range of objectives can bring significant gains in time and effort needed to filter through a broad range of candidates. This paper details how the use of Generative-Adversarial-Networks, novel machine learning techniques to format the training dataset and the use of quantum computing offer new ways to expedite drug-discovery.

Functional mobility assessments (i.e., Timed Up and Go) are commonly used clinical tools for mobility and fall risk screening in the aging population. In this work, we proposed a new Mixed Reality (MR)-based assessment that utilized a Microsoft HoloLens^TM headset to automatically lead and track the performance of functional mobility tests, and subsequently evaluated its validity in comparison with reference inertial sensors. Twenty-two healthy adults (10 older, 12 young) participated in this study. An automated functional mobility assessment app was developed based on the HoloLens platform. Mobility performance was recorded with the headset built-in sensor and validated with reference inertial sensor (Opal, APDM) taped on the headset and lower back. Results indicate vertical kinematic measures by HoloLens was in good agreement with the reference sensor (Normalized RMSE ~ 10%). Additionally, the HoloLens-based test completion time was in perfect agreement with clinical standard stopwatch measure. Overall, our preliminary investigation indicates that it is possible to use an MR headset to automatically guide users to complete common mobility tests with good measurement accuracy, thus it has great potential to provide objective and efficient sensor-based mobility assessment.

Background: The variability of the obtained results of manual tests assessing the angle of strabismus depends on the experience, skills, and training of the examiner. The authors hope that the new measuring device will provide a more sensitive and repeatable method for detecting small strabismus angles compared to the gold standard – PCT. The purpose of this article is to present an innovative strabismus angle demonstration device, called Strabiscan, to present automated measurements of eye deviation, and to compare the obtained results of these measurements to the traditional manual method. Methods: In patients with the manifest strabismic disease (n = 30) and a group of healthy subjects (n = 30), a detailed history was taken and routine ophthalmologic examinations were performed, including best-corrected distance visual acuity, assessment of refractive error using an autorefractometer after cycloplegia, biomicroscopic evaluation of the anterior segment of the eye, and evaluation of the eye fundus by indirect ophthalmoscopy. Subsequently, each patient and healthy subjects were subjected to a prismatic cover-uncover test using a manual method, and then the presence of strabismus was detected and its angle assessed using demonstration Strabiscan device. Results: In the control group, using the Strabiscan demonstration device, small-angle latent strabismus ≤3DP was diagnosed in 83% of patients, and >3DP in 13%. In contrast, using the prismatic cover-uncover test, latent strabismus ≤3DP was diagnosed in only 13% of patients, and latent strabismus with an angle >3DP in 13% of patients. No statistically significant differences were noted in the measurements of strabismus angles made by the different methods. Conclusions: The Strabiscan demonstration device allows quick and accurate assessment of the strabismus angle. Compared to the prismatic cover-uncover test, it has a higher sensitivity for detecting low-angle latent strabismus. Measurements with the Strabiscan do not require the presence of additional co-assistants for the test.

During geomagnetic storms, which are a result of solar wind interaction with the Earth’s magnetosphere, geomagnetically induced currents (GICs) begin to flow in the long-distance high-voltage power grids on the Earth’s surface. It causes a number of negative phenomena that affect the normal operation of the entire electric power system. To investigate the nature of the phenomenon and its possible effects on transformers, a GIC monitoring system was created in 2011, the devices of which were installed at five substations of the Kola-Karelian power transit in northwestern Russia. Over 12 years of operating the system a large amount of data has been accumulated, which cannot be analyzed manually within a reasonable amount of time. To analyze the constantly growing volume of recorded data effectively, a method for automatic classification of GIC in autotransformer neutral was proposed. The method is based on a continuous wavelet transform of the neutral current data combined with a convolutional neural network (CNN) to classify the obtained scalogram images. As the result of comparing four CNNs with different architectures, a model that showed excellent GIC classification performance on the validation set (100.00% accuracy and loss of 0.0115) was chosen.

Fractures of the talar neck and body are associated with spine fractures and scoliosis deformity, which affect cosmetic appearance and cause difficulty in ambulation. The implant design for talus surgery is thriving as a functional alternative in case of severe talar destruction, focusing on segmentation and reconstruction of the talus’s shape. However, manual segmentation of the talus is time-consuming and subjective. In this study we exploited the automatic segmentation framework to efficiently train a deep learning-based model to accurately segment the talus based on computed tomography imaging. We developed three model configurations with nnU-Net and investigated their Dice similarity coefficients (DSC) and 95% Hausdorff distances (HD95) for talus segmentation on a CT image dataset. The three configurations performed well (DSC > 0.95, HD95 < 0.6). When tested on the same samples, one of the configurations was more efficient while ensuring higher accuracy. We propose to focus on talus anatomic variations with increasing age based on this framework and apply it to clinical trials at the next stage.

One of the most common forms of dementia is Alzheimer’s disease (AD), which leads to progressive mental deterioration. Unfortunately, there is no definitive diagnosis and cure that can stop the condition progressing. The diagnosis is often performed based on the clinical history and neuropsychological data, including magnetic resonance imaging (MRI). Deep neural networks (DNN) algorithms are gaining popularity for medical diagnosis, and have been used widely for the analysis of MRI data. DNNs can extract hidden features from thousands of training images automatically. However, they cannot judge how confident they are about their predictions. To use DNNs in safety-critical applications such as medical diagnosis, uncertainty quantification of DNNs predictions is crucial. For this purpose, Monte Carlo dropout (MCD) has been widely used, however, it may lead to overconfident and miss calibrated results. This paper proposes a framework in which the MCD algorithm’s hyper-parameters are optimized during training using Bayesian optimization for the first time. The conducted optimization leads to assigning high predictive entropy to erroneous predictions and making it possible to recognize risky predictions. The proposed framework is used for AD diagnosis, which has not been done before. We compare our method with some existing methods in the literature based on different uncertainty quantification criteria. The results of comprehensive experiments on the Kaggle dataset using a deep model pre-trained on the ImageNet dataset show that the proposed algorithm can quantify uncertainty much better than the existing methods.

InSAR and associated analytic methods can measure surface deformation from low earth orbit with a claimed accuracy of centimeters to millimeters. The realized accuracy depends on the area being measured and on the choice of analytic method, suggesting one choose a method in response to the area being measured. Here we consider a specific fixed analytic method and compare the results it produces to measurements gathered from other means in a variety of settings. In particular we compare Sentinel-1 InSAR with GPS at the Kilauea volcano around the 2018 eruption, with GPS in the city of Arica, Chile, and with public survey data at a decommissioned tailings mine. In addition, we compare two independent Sentinel-1 InSAR analyses for a railway station in Oslo, Norway. Our goal is estimate the accuracy of a fully automated Sentinel-1 InSAR pipeline in various settings. Our conclusions are that centimeter level accuracy is a reasonable claim in many, but not all settings, and that accuracy is typically not lost by using an automated pipeline, instead of hand-selecting and tuning parameters.

The basal ganglia (BG) are a central component of the brain, crucial to the initiation, execution and learning of adaptive actions. The BG are the major site of the action of dopamine. An important aspect of the BG architecture is the existence of two paths, direct and indirect, having different projection targets and dopamine receptor expression. To understand the BG, dopamine, and related disorders, it is imperative to understand the two paths. The standard account used in neuroscience research for decades posits that the role of the direct path is to support movements, while that of the indirect path is to suppress unselected or completed movements. This account is contradicted by converging evidence. Here, we explain why the arguments supporting the standard account are flawed, and present a new account, in which the role of the indirect path is completely opposite: to support automated execution. During acute events, the direct path allows coarse responses. These are refined by competition, and the resulting focused response is executed and learned by the indirect path, assisted by cholinergic interneurons and the subthalamic nucleus (STN). The new account allows a novel understanding of the symptoms of Parkinson's disease, in particular tremor and rigidity, and of its treatment by STN deep brain stimulation.

Building information modeling (BIM) is the digital representation of physical and functional characteristics (such as geometry, spatial relationship, and geographic information) of a facility to support decisions during its life cycle. BIM has been extended beyond 3D geometrical representations in recent years, and now includes time as a fourth dimension and cost as a fifth dimension, as well as such other applications as virtual reality and augmented reality. The Internet of Things (IoT) has been increasingly applied in various products (smart homes, wearables) to enhance work productivity, living comfort, and entertainment. However, research addressing the integration of these two technologies (BIM and IoT) is still very limited, and has focused exclusively on the automatic transmission of sensor information to BIM models. This paper describes an attempt to represent and visualize sensor data in BIM with multiple perspectives in order to support complex decisions requiring interdisciplinary information. The study uses a university campus as an example and includes several scenarios, such as an auditorium with a dispersed audience and energy saving options for rooms with different functions (mechanical/electric equipment, classrooms, and laboratory). This paper also discusses the design of a common platform allowing communication among sensors with different protocols (Arduino, Raspberry Pi), the use of Dynamo to accept sensor data as input and automatically redraw visualized information in BIM, and how visualization may help in making energy-saving management decisions.

Automated Electrocardiogram (ECG) processing is an important technique which helps in identifying abnormalities in the heart before any formal diagnosis. This research presents a real-time and lightweight R-assisted feature extraction algorithm and a heartbeat classification scheme which achieves highly accurate abnormality detection. In the proposed algorithm, we extract fifteen features from each heartbeat taken from raw Lead-II ECG signals. The features carry medically valuable information such as locations, amplitude and energy of ECG waves (P, Q, R, S, T waves) which are then used for detection of any abnormality that might be present in the heartbeat using various classification algorithms. We have used four popular databases from Physionet and extracted ten thousand ECG signals from each for training the models and benchmarking results. Four classification models i.e. Naïve Bays, k-Nearest Neighbor, Neural Network, Decision Tree were used for abnormality detection validating the efficiency of the system.

Due to its high power, high efficiency, low pollution, and compact size, permanent magnet synchronous motors (PMSMs) have been widely used in a variety of fields, including electric vehicles, aerospace, wind turbines, and marine devices which are used in renewable, sustainable, and environmentally friendly energy resources. However, in these practical scenarios, the motor operating conditions are complex and variable. Under high temperatures and high current conditions, PMSMs may experience demagnetization failures, not only leading to performance degradation but also inducing unexpected failures of the motors. To reduce the risk of unexpected losses caused by demagnetization faults and improve the safety and reliability of motor systems, it is necessary to apply automated monitoring of the magnet flux of the motor's permanent magnets and achieve real-time diagnosis of early demagnetization faults, ensuring the safe operation of the motor. This review article tries to summarize the current detecting methods of the automated monitoring of demagnetization faults in PMSMs. The main online monitoring technologies from both practical and academic perspectives were summarized and their benefits and challenges have been reviewed. Finally, the research trends and suggestions for future improvements are provided. This review article will not only shed light on the origins of the automated monitoring of demagnetization faults but also help to design highly effective and sustainable permanent magnet synchronous motors.

Background: Our objective was to conduct a comprehensive analysis of the reproducibility of foot and ankle anthropometric measurements with a three-dimensional (3D) optical scanner. Methods: We evaluated thirty-nine different anthropometric parameters obtained with 3D Laser UPOD-S Full-Foot Scanner in a healthy population of twenty subjects. We determined the variance of the measurements for each foot/ankle, and the average variance among different subjects. Results: For 40 feet and ankles (15 women and 5 men; mean age 35.62 +/- 9.54 years, range 9-75 years), the average variance was 1.4 ± 2 (range 0,1 to 8). Overall, the mean absolute measurement error was < 1 mm, with a maximum variance percentage of 8.3%. Forefoot and midfoot circumferences had a low variance < 2.5, with variance percentages < 1%. Hindfoot circumferences, malleolar heights, and the length of the first and fifth metatarsal to the ground contact points showed the highest variance (range 1 to 7). Conclusion: This optical scanner achieved a good reproducibility of a large set of foot and ankle anthropometric measurements. It is a valuable tool for clinical and research purposes.

Purpose: Nycthemeral (24-hour) glaucoma inpatient intraocular pressure (IOP) monitoring has been used in Europe for more than 100 years to detect peaks missed during regular office hours. Data supporting this practice is lacking, partially because it is difficult to correlate manually drawn IOP curves to objective glaucoma progression. To address this, we deployed automated IOP data extraction tools and tested for a correlation to a progressive retinal nerve fiber layer loss on spectral-domain optical coherence tomography (SDOCT). Methods: We created and deployed a machine-learning image analysis software to extract IOP data from hand-drawn, nycthemeral IOP curves of 225 retrospectively identified glaucoma patients. The relationship between demographic parameters, IOP and mean ocular perfusion pressure (MOPP) data to SDOCT data was analyzed. Sensitivities and specificities for the historical cut-off values of 15 mmHg and 22 mmHg in detecting glaucoma progression were calculated. Results: IOP data could be extracted efficiently. The IOP average was 15.2±4.0 mmHg, nycthemeral IOP variation was 6.9±4.2 mmHg, and MOPP was 59.1±8.9 mmHg. Peak IOP occurred at 10 AM and trough at 9 PM. Disease progression occurred mainly in the temporal-superior and -inferior SDOCT sectors. No correlation could be established between demographic, IOP, or MOPP parameters and SDOCT disease progression. The sensitivity and specificity of both cut-off points (15 and 22 mmHg) were insufficient to be clinically useful. Outpatient IOPs were non-inferior to nycthemeral IOPs. Conclusion: IOP data obtained during a single visit make for a poor diagnostic tool, no matter whether obtained using nycthemeral measurements or during outpatient hours.

Directed movement towards a target requires spatial working memory, including processing of sensory inputs and motivational drive. In a stimulus-driven, operant conditioning paradigm designed to train zebrafish, we present a pulse of light via LED’s and/or sounds via an underwater transducer. A webcam placed below a glass tank records fish swimming behavior. During operant conditioning, a fish must interrupt an infrared beam at one location to obtain a small food reward at the same or different location. A timing-gated interrupt activates robotic-arm and feeder stepper motors via custom software controlling a microprocessor (Arduino). “Ardulink”, a JAVA facility, implements Arduino-computer communication protocols. In this way, full automation of stimulus-conditioned directional swimming is achieved. Precise multi­day scheduling of training, including timing, location and intensity of stimulus parameters, and feeder control is accomplished via a user-friendly interface. Our training paradigm permits tracking of learning by monitoring, turning, location, response times and directional swimming of individual fish. This facilitates comparison of performance within and across a cohort of animals. We demonstrate the ability to train and test zebrafish using visual and auditory stimuli. Current methods used for associative conditioning often involve human intervention, which is labor intensive, stressful to animals, and introduces noise in the data. Our relatively simple yet flexible paradigm requires a simple apparatus and minimal human intervention. Our scheduling and control software and apparatus (NemoTrainer) can be used to screen neurologic drugs and test the effects of CRISPR­-based and optogenetic modification of neural circuits on sensation, locomotion, learning and memory.

Background (1) In the time of the 4th Industrial Revolution or Industry 4.0, a conglomerate of technical and social inventions, political contexts, socio-cultural circumstances, environmental policies, business models, and economic policies has emerged. Sustainability policy in theory and practice aims to deal with the effects of all these factors and to try to make decisions that ensure both social and economic development sustainably. The question is how to familiarize oneself with the current knowledge about the relationship between Industry 4.0 and sustainability?; (2) Methods: This research utilizes an automated content analysis method to analyses scientific journals, newspapers and magazines. The comparison of results of both research group shows that the scientific literature focuses more on changes in business models, production processes and technologies that enable sustainable development; (3) We found that the scientific literature focuses more on changes in business models, production processes and technologies that enable sustainable development. Newspapers and magazines articles write more about sustainable or green investment, sustainable standards and sustainable reporting. Newspapers and magazines articles write more about sustainable or green investment, sustainable standards and sustainable reporting. Newspapers, as well as some latest research journals, include articles of the COVID-19 outbreak and its effect on the economy and the environment. Indeed, the outbreak of the virus brings a new thought to the reorganization of the complex relationships between consumers, businesses and the state; (4) Conclusions: According to the comparison of the analyses of the results, it can is that the analyses of both types of literature, both scientific and professional, shows that there are common topics they write about, which are related to the field of clean production, emissions, renewable energy, climate change, sustainable investments and corporate sustainability. An urgent global issue that extends all over the world is the promotion of energy-saving technologies and reduction of carbon dioxide emissions.

The development and use of highly automated vehicles (HAV) in agriculture is a highly important task because of the lack of machine drivers and unsatisfactory level of their qualifications, reducing the impact of harmful factors on employees of agricultural enterprises. HAVs allow to avoid these problems: increase productivity and the efficiency of seasonal use of equipment, and reduce the impact of harmful factors on people. Modern HAVs in agriculture are based on the following methods: parallel driving according to geo coordinates without automatic turning and without obstacles tracking, and on technical vision without the use of a geographic information system (for example Cognitive AgroPilot) and a digital field map, which makes it impossible to generate the optimal path around the field.

One of the interactions that has been studied in recent decades under the ecohydrological approach is infiltration, which is difficult to determine because the existing methods for estimation depends on certain variables that are difficult to establish or identify, and in other cases, the implementation of instrumentation is expensive. Given this, saturated hydraulic conductivity has been the descriptive variable of the infiltration process by recent authors, being understood as the conduction of water that occurs through the soil and its composition through the vegetation cover. The present design generated an easily accessible portable instrumentation model for the monitoring and collection of infiltration data in situ for basins and ecosystems with different land uses, in an automated manner with the objective of determining the vegetation patterns necessary to sustain the infiltration function. The INDI-INECOL tension infiltrometer [1] was chosen as the reference instrument. It evaluates the saturated hydraulic conductivity based on a column of water that descends through the system and it is exchanged in the soil by the air between the pores. To automate data collection, a measurement system has been proposed through a SCADA system, which is defined as a control, action, decision, storage and data recording system. This system collects field data from a sensor VL053L0X connected to a master station, in our case an Arduino board UNO, connected through the serial port and by a graphical user interface programmed on Python, to display, storage and enrichment of the sensor data and finally to be exported in files suitable for Microsoft Excel.

The intracranial pressure (ICP) signal, as monitored on patients in intensive care units, contains pulses of cardiac origin where P1 and P2 subpeaks can often be observed. When calculable, the ratio of their relative amplitudes is an indicator of the patient’s cerebral compliance. This characterization is particularly informative on the overall state of the cerebrospinal system. We developed a recurrent neural network-based framework for P2/P1 ratio computation that only takes a raw ICP signal as an input. Two tasks are performed, namely pulse classification and subpeak designation. Pulse classification was achieved with an area under the curve of 0.90 on a 4,344-pulse testing dataset, while the peak designation algorithm identified pulses with a P2/P1 ratio > 1 with a 97.3% accuracy. Although it still needs to be evaluated on a larger number of labeled recordings, our automated P2/P1 ratio calculation framework appears to be a promising tool for improving bedside monitoring devices.

Automated lip reading is a research problem that has developed considerably in recent years. Lip reading is evaluated both visually and audibly in some cases. The lip reading model is a field of use for detecting specific words using images from security cameras, but it is not possible to use audio-visual databases in this situation. It is not possible to obtain the sound input of the pronounced word in all cases. We collected a new Turkish dataset with only the image in this study. The new dataset is produced using Youtube videos, which is an uncontrolled environment. For this reason, images have difficult parameters in terms of environmental factors such as light, angle, color, and personal characteristics of the face. Despite the different features on the human face such as mustache, beard, and make-up, the visual speech recognition problem was developed on 10 classes including single words and two-word phrases using Convolutional Neural Networks (CNN) without any intervention on the data. The proposed study using only-visual data obtained a model which is automated visual speech recognition with a deep learning approach. In addition, since this study uses only-visual data, the computational cost and resource usage is less than in multi-modal studies. It is also the first known study to address the lip reading problem with a deep learning algorithm using a new dataset belonging to the Ural-Altaic languages.

The number and size of computational models in biology have drastically increased over the past years and continue to grow. Modeled networks are becoming more complex, and reconstructing them from the beginning in an exchangeable and reproducible manner is challenging. Using precisely defined ontologies enables the encoding of field-specific knowledge and the association of disparate data types. In computational modeling, the medium for representing domain knowledge is the set of orthogonal structured controlled vocabularies named Systems Biology Ontology ( SBO). The SBO terms enable modelers to explicitly define and unambiguously describe model entities, including their roles and characteristics. Here, we present the first standalone tool that automatically assigns SBO terms to multiple entities of a given SBML model, named the SBOannotator. The main focus lies on the reactions, as the correct assignment of precise SBO annotations requires their extensive classification. Our implementation does not consider only top-level terms but examines the functionality of the underlying enzymes to allocate precise and highly specific ontology terms to biochemical reactions. Transport reactions are examined separately and are classified based on the mechanism of molecule transport. Pseudo-reactions that serve modeling purposes are given reasonable terms to distinguish between biomass production and the import or export of metabolites. Finally, other model entities, such as metabolites and genes, are annotated with appropriate terms. Including SBO annotations in the models will enhance the reproducibility, usability, and analysis of biochemical networks. Availability: The open-source project SBOannotator is freely available under the terms of LGPL version 3.0 from https://github.com/draeger-lab/SBOannotator/.

The current COVID19 pandemic has raised huge concerns for outdoor air quality due to expected lungs deterioration. These concerns include the challenges in the scalable prediction of harmful gases like carbon dioxide, iterative/repetitive inhaling due to mask and environmental temperature harshness. Even in the presence of air quality sensing devices, these challenges lead to failed planning and strategy against respiratory diseases, epidemics, and pandemics in severe cases. In this work, a dual time-series with bi-cluster sensor data-stream-based novel optimized regression algorithm was proposed with optimization predictors and optimization responses that use automated iterative optimization of the model based on the similarity coefficient index. The algorithm was implemented over SeReNoV2 sensor nodes data, i.e. multi-variate dual time-series of environmental and US Environmental Protection Agency standard sensor variables for air quality index measured from air quality sensors with geospatial profiling. The SeReNoV2 systems were placed at four locations that were 3 km apart to monitor air quality and their data was collected at Ubidots IoT platform over GSM. Results have shown that the proposed technique achieved a root mean square error (RMSE) of 1.0042 with a training time of 469.28 seconds for normal and RMSE of 1.646 in the training time of 28.53 seconds for optimization. The estimated R-Squared error of 0.03 with Mean-Square Error for temperature 1.0084 ᵒC and 293.98 ppm for CO2 was observed. Furthermore, the Mean-Absolute Error (MAE) for temperature 0.66226 ᵒC and 10.252 ppm for CO2 at a prediction speed of ~5100 observations/second for temperature 45000 observations/second for CO2 due to iterative optimization of the training time 469.28 seconds for temperature and 28.53 seconds for CO2 was very promising in forecasting COVID19 countermeasures before time.

Coronary optical coherence tomography (OCT) is an intravascular, near-infrared light-based imaging modality capable of reaching axial resolutions of 10-20 µm. This resolution allows for accurate determination of high-risk plaque features, such as thin cap fibroatheroma; however, visualisation of morphological features alone still provides unreliable positive predictive capability for plaque progression or future major adverse cardiovascular events (MACE). Biomechanical simulation could assist in this prediction, but this requires extracting morphological features from intravascular imaging to construct accurate three-dimensional simulations of patients’ arteries. Extracting these features is a laborious process, often carried out manually by trained experts. To address this challenge, numerous techniques have emerged to automate these processes while simultaneously overcoming difficulties associated with OCT imaging, such as its limited penetration depth. This systematic review summarises advances in automated segmentation techniques from the past five years (2016-2021) with a focus on their application to the three-dimensional reconstruction of vessels and their subsequent simulation. We discuss four categories based on the feature being processed, namely: coronary lumen; plaque characteristics and subtypes; artery layers; and stents. Areas for future innovation are also discussed as well as their potential for future translation.

Rigid-body visual tracking is an active research field with many practical applications including visual surveillance and intelligent transport system. In this paper, we define a new problem domain, called visual growth tracking, to track different parts of an object that grow non-uniformly over space and time for application in image-based plant phenotyping. The paper introduces a novel method to detect and track each leaf of a plant for automated leaf stage monitoring. The method has four phases: optimal view selection, plant architecture determination, leaf tracking and generation of a leaf status report. The proposed method uses a graph theoretic approach to reliably detect and track individual leaves by overcoming the challenge of leaf-losses based on temporal image sequence analysis for automatically generating the leaf status report containing the following phenotypes, i.e., the emergence timing of each leaf, total number of leaves present at any time, the day on which a particular leaf stopped growing, and the length and relative growth rate of individual leaves. The proposed method demonstrates high accuracy in detecting leaves and tracking them through the early vegetative stages of maize plants based on experimental evaluation on a publicly available benchmark dataset.

Autism Spectrum Disorder (ASD) is a neuro-developmental disorder that limits social interactions, cognitive skills, and abilities. Since ASD can last during an affected person's entire life cycle, the diagnosis at the early onset can yield a significant positive impact. The current medical diagnostic systems (e.g., DSM-5/ICD-10) are somewhat subjective; rely purely on the behavioral observation of symptoms, and hence, some individuals often go misdiagnosed or late-diagnosed. Therefore, researchers have focused on developing data-driven automated diagnosis systems with less screening time, low cost, and improved accuracy while significantly reducing professional intervention. Human Activity Analysis (HAA) is considered one of the most promising niches in computer vision research. This paper aims to analyze its potentialities in the automated detection of autism by tracking the exclusive characteristics of autistic individuals such as repetitive behavior, atypical walking style, and unusual visual saliency. This review provides a detailed inspection of HAA-based autism detection literature published in 2011 on-wards depicting core approaches, challenges, probable solutions, available resources, and scopes of future exploration in this arena. According to our study, deep learning outperforms machine learning in ASD detection with a classification accuracy of 76\% to 95\% on different datasets comprise of video, image, or skeleton data that recorded participants performing a large number of actions. However, machine learning provides satisfactory results on datasets with a small number of action classes and has a range of 60\% to 93\% accuracy among numerous studies. We hope this extensive review will provide a comprehensive guideline for researchers in this field.

Laser scanning systems make use of Light Detection and Ranging (LiDAR) technology to acquire accurately georeferenced sets of dense 3D point cloud data. The information acquired using these systems produces better knowledge about the terrain objects which are inherently 3D in nature. The LiDAR data acquired from mobile, airborne or terrestrial platforms provides several benefit over conventional sources of data acquisition in terms of accuracy, resolution and attributes. However, the large volume and scale of LiDAR data have inhibited the development of automated feature extraction algorithms due to the extensive computational cost involved in it. Moreover, the heterogeneously distributed point cloud, which represents objects with varying size, point density, holes and complicated structures pose a great challenge for data processing. Currently, geospatial database systems do not provide a robust solution for efficient storage and accessibility of raw data in a way that data processing could be applied based on optimal spatial extent. In this paper, we present Global LiDAR and Imagery Mobile Processing Spatial Environment (GLIMPSE) system that provides a framework for storage, management and integration of 3D LiDAR data acquired from multiple platforms. The system facilitates an efficient accessibility to the raw dataset, which is hierarchically represented in a geographically meaningful way. We utilise the GLIMPSE system to automatically extract road median from Airborne Laser Scanning (ALS) point cloud. In the first part of this paper, we detail an approach to efficiently retrieve the point cloud data from the GLIMPSE system for a particular geographic area based on user requirements. In the second part, we present an algorithm to automatically extract road median from the retrieved LiDAR data. The developed road median extraction algorithm utilises the LiDAR elevation and intensity attributes to distinguish the median from the road surface. We successfully tested our algorithms on two road sections consisting of distinct road median types based on concrete and grass-hedge barriers. The use of GLIMPSE improved the efficiency of the road median extraction in terms of fast accessibility to ALS point cloud data for the required road sections. The developed system and its associated algorithms provide a comprehensive solution to the user's requirement for an efficient storage, integration, retrieval and processing of large volumes of LiDAR point cloud data. These findings and knowledge contribute to a more rapid, cost-effective and comprehensive approach to surveying road networks.

The exceptional increase in molecular DNA sequence data in open repositories is mirrored by an ever-growing interest among evolutionary biologists to harvest and use those data for phylogenetic inference. Many quality issues, however, are known and the sheer amount and complexity of data available can pose considerable barriers to their usefulness. A key issue in this domain is the high frequency of sequence mislabelling encountered when searching for suitable sequences for phylogenetic analysis. These issues include the incorrect identification of sequenced species, non-standardised and ambiguous sequence annotation, and the inadvertent addition of paralogous sequences by users, among others. Taken together, these issues likely add considerable noise, error or bias to phylogenetic inference, a risk that is likely to increase with the size of phylogenies or the molecular datasets used to generate them. Here we present a software package, phylotaR, that bypasses the above issues by using instead an alignment search tool to identify orthologous sequences. Our package builds on the framework of its predecessor, PhyLoTa, by providing a modular pipeline for identifying overlapping sequence clusters using up-to-date GenBank data and providing new features, improvements and tools. We demonstrate our pipeline’s effectiveness by presenting trees generated from phylotaR clusters for two large taxonomic clades: palms and primates. Given the versatility of this package, we hope that it will become a standard tool for any research aiming to use GenBank data for phylogenetic analysis.

When implementing a control system for a ground-based unmanned vehicle (UV) used in agri-culture, an important factor is the low cost of the equipment used, so the use of cameras without lidars for navigation, avoiding obstacles, and ensuring movement safety seems promising. En-suring the safety of movement of UV consists of developing methods and means that make it possible to bypass static and dynamic obstacles and make an emergency stop if it is impossible to bypass. The article describes methods and software that provide detection of objects surrounding the UV through the use of the YOLOv8 neural network, space free for movement through the use of se-mantic segmentation with the MobileNetV3 network architecture, tools for combining several data sources to build a local perception map, as well as linear and angular speed of the UV based on calculating the optimal direction of movement for avoiding obstacles. Testing of the developed methods and software was realized in the Webots simulation environment. Software is developed with ROS2.

Text annotation is an essential element of the natural language processing approaches. The manual annotation process performed by humans has several drawbacks, such as subjectivity, slowness, fatigue, and possibly carelessness. In addition, annotators may annotate ambiguous data. So, we developed the concept of automated annotation to get the best annotations using several machine-learning approaches. The proposed approach is based on an ensemble algorithm of meta-learners and meta-vectorizer techniques. The approach employs a semi-supervised learning technique for automated annotation, aimed at detecting hate speech. This involves leveraging various machine learning algorithms, including Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbors (KNN), and Naive Bayes (NB), in conjunction with Word2Vec and TF-IDF text extraction methods. The annotation process is performed using 13,169 Indonesian YouTube comments data. The proposed model used a Stemming approach using data from Sastrawi and also new data of 2,245 words. Semi-supervised learning uses 5%, 10%, and 20% of labeled data as compared to performing labeling based on 80% of the datasets. In semi-supervised learning, the model learns from the labeled data, which provides explicit information, and the unlabeled data, which offers implicit insights. This hybrid approach enables the model to generalize and make informed predictions even when limited labeled data is available, ultimately enhancing its ability to handle real-world scenarios with scarce annotated information. In addition, the proposed method uses a variety of thresholds for matching words labeled with hate speech ranging from 0.6, 0.7, 0.8, and 0.9. The experiment showed that the KNN-Word2ec model has the best accuracy value of 96.9% with a scenario of 5%:80%:0.9. However, several other methods have also accuracy above 90%, such as SVM and DT based on both text extraction methods in several test scenarios.

This study presents an innovative analytical method for the detection and quantification of 14 β-agonists in pork using liquid chromatography-tandem mass spectrometry (LC-MS/MS). The method involves the use of a solid phase microextraction (SPME) probe, consisting of a wooden tip coated with polyacrylonitrile (PAN) and molecularly imprinted polymer (MIP). This probe has been integrated into an automated extraction device, designed in our laboratory to extract the target analytes prior to LC-MS/MS analysis. Compared to the traditional solid-phase extraction (SPE) procedure, the proposed approach significantly reduces the costs related to adsorbent ma-terial and solvent consumption, and shortens purification time, thereby reducing both the tech-nical workload and associated expenses. The methodology has been carefully validated in ac-cordance with the National Standard of the People's Republic of China (GB/T 22286-2008), evalu-ating key parameters including the limit of detection (LOD), limit of quantification (LOQ), matrix effects, linearity, and both intra-day and inter-day precision. The average recovery rates for all β-agonists were observed to lie between 71.6% and 82.2%, with relative standard deviations (RSDs) consistently below 15% for both types of precision. The LOD and LOQ values were found to range from 0.09 to 0.39 μg/kg and 0.27 to 0.99 μg/kg, respectively. In terms of accurate detection of positive samples, the developed method demonstrated a closer approximation to the true value of the sample compared to the National Standard method GB/T 31658.22-2022. Overall, the proposed method exhibits substantial promise for the routine assessment of β-agonists in pork and presents a practical alternative for compliance monitoring in regulatory settings.

Cryopreservation has been used extensively for cattle in Bangladesh, albeit no study was conducted on the cryopreservation techniques of buffalo. This study compares two freezing methods and the effects of diluters on the semen quality of buffalo. In the first freezing protocol, semen was frozen in two-step: from 37 °C to 5 °C for 30 minutes in a BLRI-developed equilibration chamber and from 5 oC to -120 oC in a Styrofoam box using liquid nitrogen vapor from different distances (0.5, 1.5, 1.6, 2 and 3 inches). At the same time semen was frozen in a programmable freezer in three steps. The semen samples were then evaluated for motility and morphological quality by CASA. In another experiment, the efficacy of one locally developed diluter-Tris-fructose-egg yolk-based (TFE) and three commercial diluters (Andromed, Triladyl and Steridyl) were evaluated. The highest number of motile sperms (62.67±1.12; P< 0.01) and progressive motility (38.97±1.10; P < 0.001) was observed at 1.6 inches above liquid nitrogen. There was no significant difference in overall motility, progressive and slow motility between semen cryopreserved in the cheap nitrogen vapor technique (57.49±5.67, 38.70± 4.04 and 3.83± 0.63, respectively) and expensive automated technique (65.94±4.65, 45.54 ± 3.64 and 2.43± 0.36, respectively). The highest recovery rate and conception rate were observed in semen diluted with TFE (82.4% and 80%, respectively). Hence, the cryopreservation technique using nitrogen vapor and TFE diluent is cost-effective and suitable for freezing buffalo semen that would produce superior semen for artificial insemination.

In areas where conventional fundus cameras are logistically unaffordable, the smartphone-based approach is considered as a promising future of glaucoma screening due to their affordability and ease-of-use. Optic disc localization is a critical stage during glaucoma screenings. For fundus images captured with standard fundus cameras, the majority of the models available out there can locate the optic disc with satisfactory performance. However, for images that are captured with smartphone-based fundus cameras, the inherent noise and lower quality of the fundus image makes it difficult for models to detect the optic disc region. In this study, we have proposed to utilize YOLOv8n for optic disc localization due to the model’s cutting-edge performance in diverse tasks and its lightweight nature. We have used a public dataset which has 2000 low quality fundus images that are captured using a smartphone-based fundoscopy device. From these, 60% of the data was used for fine-tuning the model, and 25% for testing. By using a confidence of 50% set as threshold, the model was able to detect the optic disc successfully on over 97% of test images with intersection over union of above 0.85. These results highlight the potential of the lightweight YOLOv8n model for deployment on resource-constrained environments, offering a promising performance on accurately localizing the OD and enhancing the feasibility of affordable glaucoma screening on smartphones.