In order to shorten the detection time and improve the average precision on embedded devices, A lightweight and high accuracy model is proposed for passion fruit in complex environments (backlight, occlusion, overlap, sunny, cloudy, rainy). Firstly, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computation while improving detection speed. Secondly, a new feature branch is added to the GhostNet network, and the feature fusion layer in the neck network is reconstructed to effectively combine the lower-level and higher-level features, which not only improves the accuracy of the model but also maintains its lightweight. Finally, the knowledge distillation methods are used to transfer the knowledge from the more capable teacher model to the less capable student model, which significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than the original YOLOv5s model. Furthermore, the improved model size is 7.14MB, reduced to half of the original model, and the real-time detection frame rate is 11.25 FPS on the Jetson Nano. Compared to the state-of-the-art model, the proposed model outperforms them in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruits in complex orchard scenes, which can provide valuable technical support for the development of orchard picking robots and greatly improve the intelligence level of orchards.

As marine traffic is contributing to pollution and mostly have predictable route with repetitive load profiles, to reduce their impact on environment, hybrid system with proton exchange membrane fuel cells (PEMFC-s) and battery pack, is promising replacement. For this purpose, the numerical model of repowered existing vessel that have two diesel engines with 300 kWe is developed. The goal of this paper is to develop numerical model which analyzes and determine equivalent hybrid ship propulsion system for known traveling route. The developed numerical model consists of an interconnected system with PEMFC stack and battery pack as power sources. Numerical model is developed and optimized to meet minimal required power demand for successful route demand, which has variable loads and daily sails six-time same voyage- in total 54 nautical miles. The results have shown that equivalent hybrid power system consists of 300 kWe PEMFC stack and battery pack with 424 kWh battery and state of charge varying between 20 and 87%. To power this new hybrid power system, hydrogen tank of 7200 l holding 284.7 kg at pressure of 700 bar is needed, compared to previous system that spend 1524 kg of diesel and generate 4886 kg of CO2.

The effective Supervisory Control and Data Acquisition (SCADA) system can improve the reliability, safety and economic benefits of microgrid operation. In this research, the lower central controller and upper WEB monitoring system are connected by the SCADA system which is as the hub of microgrid intelligent monitoring platform. This system contains a set of specific functions programmed by Java as a middleware which can provide control and communication between the central controller and the upper monitoring system. The system realizes the real-time data acquisition and storage, the control instructions parsing and transmitting, the microgrid security and stability, the load balancing and resource recovery of the microgrid. All that functions have been tested and verified in the actual operation.

Meat serves as a vital component of the human diet, offering a rich source of protein and essential trace elements. China stands as both a significant producer and consumer of meat on a global scale, leading the world in terms of total meat production and consumption. As the standard of living within the country continues to rise, there is a growing emphasis on the nutritional value and safety of meat consumption. The tenderness of meat is a critical factor influencing its overall quality. Traditionally, tenderness has been assessed through shear force testing, a method that is inherently destructive, inefficient, and results in considerable sample wastage. In light of these drawbacks, non-destructive testing techniques have emerged as a preferred alternative, promising greater accuracy, efficiency, and convenience without compromising the integrity of the samples. This paper delves into the application of five advanced non-destructive testing technologies in the realm of meat tenderness assessment. These include near-infrared spectroscopy, hyperspectral imaging, Raman spectroscopy, airflow optical fusion detection, and nuclear magnetic resonance detection. Each technology is scrutinized for its respective strengths and limitations, providing a comprehensive overview of their current utility and potential for future development. Moreover, the integration of these techniques with the latest advancements in artificial intelligence (AI) technology is explored. The fusion of AI with non-destructive testing offers a promising avenue for the development of more sophisticated, rapid, and intelligent systems for meat tenderness evaluation. This integration is anticipated to significantly enhance the efficiency and accuracy of quality assessment in the meat industry, ensuring a higher standard of safety and nutritional value for consumers. The paper concludes with a set of technical recommendations aimed at guiding the future direction of non-destructive, AI-enhanced meat tenderness detection, thereby contributing to the ongoing improvement of the meat industry in China and beyond.

Graph Neural Networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale and complex nature of graph data demands substantial computational resources and high performance during both training and inference stages, presenting significant challenges, particularly in the context of embedded systems. Recent studies on GNNs have investigated both software and hardware solutions to enhance computational efficiency. Earlier studies on Deep Neural Networks (DNNs) have indicated that methods like reconfigurable hardware and quantization are beneficial in addressing these issues. Unlike DNN research, studies on efficient computational methods for GNNs are less developed and require more exploration. This survey reviews the latest developments in quantization and FPGA-based acceleration for GNNs, showcasing the capabilities of reconfigurable systems (often FPGAs) to offer customized solutions in environments marked by significant sparsity and the necessity for dynamic load management. It also emphasizes the role of quantization in reducing both computational and memory demands through the use of fixed-point arithmetic and streamlined vector formats. This paper concentrates on low-power, resource-limited devices over general hardware accelerators and reviews research applicable to embedded systems. Additionally, it provides a detailed discussion of potential research gaps, foundational knowledge, obstacles, and prospective future directions.

Applied talent is not only a builder of human civilization but also a promoter of economic development. They not only need systematic and solid engineering theoretical knowledge but also rich engineering practical experience. Applied undergraduate colleges are the cradle for cultivating applied talent and shoulder the important mission of cultivating various types of applied talent for society. With the rapid development of higher education, the number of applied undergraduate institutions has sharply increased, but the quality of applied talent cultivated by them has shown a significant decline, which greatly restricts the pace of industrial development in the world. This article proposes a new concept of promoting the "three certificates" (graduation certificate, degree certificate, and skill certificate) education model in applied undergraduate colleges, which is of great significance for the country to cultivate composite talents with the ability of "product design, production management, and product processing" at the same time.

This study investigates the influence of adding hydrogen as an additive to gasoline in a four-stroke engine, utilizing a comprehensive thermodynamic comparative analysis conducted with self-developed engine model. The research aims to assess the performance, emissions, and efficiency of the engine when using gasoline-hydrogen blends, and to provide insights into the potential benefits of this approach. First the engine performance and emissions under different hydrogen blending levels were examined. A range of different air-to-fuel ratios (rich to lean) and varying percentages of hydrogen were considered. This systematic variation allowed for a detailed evaluation of the influence of hydrogen content on combustion efficiency, power out-put, and emissions characteristics. The analysis results included key parameters such as indicated specific fuel consumption and mean effective pressure. Additionally, the study focused on range prediction of nitrogen oxides (NOx) emissions, which are a critical environmental concern asso-ciated with internal combustion engines. The analysis of pressure and temperature profiles throughout the engine cycle shed light on the combustion characteristics and efficiency im-provements associated with hydrogen addition. In terms of emissions, the study projected that all emissions were reduced except NOx, which is highly dependent on hydrogen percentage, and it might be reduced in some cases, but with higher temperatures and pressures associated with hydrogen addition in most cases there is actually NOx increase, especially at higher engine loads.

This study presents an advanced Simulated Shearer Machine Cutting Experiment System enhanced with digital twin technology. Central to this system is a simulated shearer drum, designed based on similarity theory to mirror the operational dynamics of actual mining cutters accurately. The setup incorporates a modified machining center equipped with sophisticated sensors that monitor various parameters such as cutting states, forces, torque, vibration, temperature and sound. These sensors are crucial for precisely simulating the shearer cutting actions. The integration of digital twin technology is pivotal, featuring a real-time data management layer, a dynamic simulation mechanism model layer, and an application service layer that facilitates virtual experiments and algorithm refinement. This multifaceted approach allows for in-depth analysis of simulated coal cutting, utilizing sensor data to comprehensively evaluate the shearer's performance. The study also includes tests on simulated coal samples. The system effectively conducts experiments and captures cutting condition signals via the sensors. Through time-domain analysis of these signals, gathered while cutting materials of varying strengths, it is determined that the cutting force signal characteristics are particularly distinct. By isolating the cutting force signal as a key feature, the system can effectively distinguish between different cutting modes. This capability provides a robust experimental basis for coal-rock identification research, offering significant insights into the nuances of shearer operation.

This study explored the effects of cryogenic treatment on the microstructure, hardness, and wear-resistance of diamond-like carbon (DLC) by cryogenically treating NAK 80 mold steel coated with DLC. Raman spectroscopy analyzed the structure of the DLC film. Nanoindenter analyzed the hardness and Young’s modulus of the film, and their relationship determined the wear resistance. Wear test assessed the wear rate and friction coefficient of the DLC film. The results showed that cryogenic treatment increased the rate of carbide precipitation and refined the grain structure. Raman spectroscopy indicated that the Raman intensity rate (I_D/I_G) of treated DLC films was smaller than those without cryogenic treatment. When the sp3 bond increased, the hardness and wear-resistance of the DLC film also increased.

In the field of railroad safety, effective detection of surface cracks is critical, necessitating reliable, high-speed non-destructive testing (NDT) methods. This study introduces a hybrid Eddy Current Testing (ECT) probe, specifically engineered for railroad inspection, to address the common issue of ’lift-off noise’ due to varying distances between the probe and test material. Unlike traditional ECT methods, this probe integrates transmit and differential receiver coils, aiming to enhance detection sensitivity and minimize lift-off impact. The study optimizes ECT probes employing different driver coils, emphasizing three main objectives: a) quantitatively evaluating each probe using signal- to-noise ratio (SNR) and outlining a real-time data processing algorithm based on SNR methodology; b) exploring the frequency range proximal to the electrical resonance of the receiver coil; c) examining sensitivity variations across varying lift-off distances. The experimental outcomes indicate that the newly designed probe with figure 8-shape driver coil significantly improves sensitivity in detecting surface cracks on railroads. It achieves an impressive SNR exceeding 100 for defects with minimal dimensions of 1 mm in width and depth. Simulation results closely align with experimental findings, validating the investigation of optimal operational frequency and lift-off distance for selected probe performance, determined to be 0.3 MHz and 0.5 mm, respectively. The realization of this project would lead to notable advancements in enhancing railroad safety by improving crack detection efficiency.

Electrical contacts are important circuit components with diverse industrial applications, and their failure can lead to multiple unwanted effects. Hence, the behavior of electrical contacts is a widely studied topic in scientific literature based on various approaches, tools, and techniques. The present study proposes a numerical modeling and simulation approach based on the Holm contact theory to study the dependence between the electric potential and the temperature within an electrical contact. Structured in 5 sections, the research was conducted using COMSOL Multiphysics software and its solid-state mechanics, electric current, and heat transfer modules in order to highlight contact behavior from mechanical, electrical and thermal points of view: the von Mises stress, contact force, the electric field amplitude, the variation of the electrical potential along the current path, the temperature gradient, and dependence of temperature along the contact elements edges were obtained by simulation and graphically represented. The results are in line with the expectations and with past research that was studied in the literature review.

Addressing the significant challenge in high-speed cotton dibbling operations in Xinjiang—specifically, the duck bill’s ("Duck bill" is a type of duck-billed bunch planting mechanism or component). shortened opening duration leading to seed throwing and floating—a new crawler-type delayed hole-forming mechanism has been designed. This mechanism extends the duck bill horizontally, thereby prolonging its opening time, enabling cotton sowing speeds of up to 6 km/h. Following agronomic principles for cotton planting, the overall layout of the crawler-type hole-forming mechanism, the structural parameters of the key components and the trajectory of the hole-forming are determined. We use the Discrete Element Method (DEM) and multi-body dynamics coupling method to simulate and analyze the motion process of the device. The fixed the tilt angle of the duck bill α(A), the depth of the duck bill hole-forming into the soil h(B), and the angle of rotation of the moving duck bill β(C) were taken as the experimental factors, with the longitudinal length of cotton seed hole (Y1) and the hole-forming depth of cotton seed hole (Y2) as the response values. The parameter range of each factor and the preliminary influence on the response value were determined through pre-experiments and single-factor simulation test. Based on RecurDyn-EDEM coupling, a quadratic regression orthogonal rotation combination simulation test was carried out. The results show that the order of the primary and secondary factors affecting the Y1 of the time-lapse hole-forming device was: A > C > B. The order of primary and secondary factors affecting the Y2 of the delayed hole forming device was: B > C > A. When the A was 2.4 °, the B was 42.4 mm, and the C was 30.5 °, the performance of the hole-forming was the best, and the Y1 was 26.4 mm, and the Y2 was 25.0 mm. The bench verification test results show that under the optimized combination of operating parameters, the average Y1 was 29.1 mm, and the average Y2 was 23.2 mm. Compared with the results of the previous coupled simulation model, the average relative errors of the two are 7.23 % and 4.36 %, respectively, indicating the accuracy and effectiveness of the established DEM simulation model and virtual test analysis. The hole-forming area and the opening time of the duck bill after the stable operation of the machine were recorded and measured. The calculated hole dislocation rate Hc was 4.33 %, which did not exceed the national standard requirement of 6 %. The qualified rate of hole distance Hx was 94.33 %, which was much higher than the national standard requirement of 80 %. The average opening time of the duck bill at a speed of 6 km/h is 0.45 s, which is much longer than the time required for cotton seeds to fall from the duck bill 0.11 s. It meets the requirements of high-speed cotton planting in China and facilitating advancements in future high-speed planter technology.

In this study, nanostructured cerium-doped TiO2 (Ce-TiO2) films with the addition of different amounts of cerium (0.00, 0.08, 0.40, 0.80, 2.40, and 4.10 wt. %) were deposited on a borosilicate glass substrate, by flow coating sol-gel process. After flow coating, deposited films were dried at the temperature of 100 °C for 1 h, followed by calcination at the temperature of 450 °C for 2 h. For the characterization of sol-gel TiO2 films, the following analytic techniques were used: X-ray diffraction (XRD), thermal gravimetry (TG), differential thermal analysis (DTA), and differential scanning calorimetry (DSC). Sol-gel derived Ce-TiO2 films were used for photocatalytic degrada-tion of the ciprofloxacin (CIP). The influence of the amount of Ce in TiO2 films, the duration of the photocatalytic decomposition, and the irradiation type (UV-A and simulated solar light) on the CIP degradation were monitored. Kinetics parameters (reaction kinetics constants and the half-life) of the CIP degradation, as well as photocatalytic degradation efficiency, were determined. The best photocatalytic activity was achieved by the TiO2 film doped with 0.08 wt.% Ce, under both UV-A, and solar irradiation.

This paper presents a piezoresistive pressure sensor with a shield layer for improved stability. Compared with the conventional piezoresistive pressure sensors, p-type piezoresistors are covered by an n-type shield layer, which is formed by ion implantation. The proposed pressure sensors have been successfully fabricated by bulk micromachining techniques. The impact of electrical field on piezoresistors is studied by simulation. The temperature drift of the pressure sensor has been investigated by both simulation and experimental measurement. Characteristics of developed pressure sensors are tested from -40 C to 125 C. A sensitivity of 0.022 mV/V/KPa and a maximum non-linearity of 0.085% FS are measured for the fabricated sensor in a pressure range of 1 MPa. The temperature coefficients of resistance of shielded piezoresistors are found to be smaller than those of un-shielded ones. It is demonstrated that the shield layer is able to reduce the drift caused by electrical field and ambient temperature variation.

Longitudinal cutting is a most common process in steel structure manufacturing, and the man-hours of the process provide an important basis for enterprises to generate production schedules.However, currently the man-hours in factories are mainly estimated by experts, and the accuracy of this method is relatively low.In this study,we propose a system that predicts man-hours with history data in the manufacturing process and that can be applied in practical structural steel fabrication.The system addresses the data inconsistency problem by one-hot encoding and data normalization techniques,Pearson correlation coefficient for feature selection,and the Random Forest Regression(RFR) for prediction.Compared with the other three Machine Learning(ML) algorithms, the Random Forest algorithm has the best performance.The results demonstrate that the proposed system outperforms the conventional approach and has better forecast accuracy, so that it is suitable for man-hours prediction.

Aiming at the problems of high labor intensity and high cost of manual picking, high loss rate of mechanical picking seeds, low mechanization level and difficult to guarantee the quality of picking plates in the process of picking plates of edible sunflower. Based on the principle of manual plate taking, a plate taking control system for sunflower harvesting table was designed. Through the research and analysis of the principle of taking the plate of the edible sunflower harvesting table. According to the actual operation requirements, the overall scheme of the sunflower plate control system is determined, and the control strategy of imitating artificial low loss harvesting is designed. To reduce the grain loss in the process of taking the plate and improve the control accuracy of the system on the movement speed and displacement of the key components in the process of taking the plate, a trapezoidal acceleration and deceleration control algorithm is designed as the control algorithm of taking the plate. To verify the working performance of the plate control system, with the absolute error, relative error and total loss rate of the harvest as objectives. The bench and field verification experiments were both carried out. The bench experiment showed that the speed error of the plate parts was not more than 0.028 m/s. In the bench experiments of the device, the maximum positioning error was 1.25 mm, the average relative error is only 0.94 %, and the grain loss rate was not more than 2.26 %. It result showed that the system algorithm was reliable, the positioning accuracy was high, and the taking plate operation can be completed well. The field verification experiment showed that the forward speed of the unit was in the range of 0.4~0.8 m/s, and the total loss rate of harvest was less than 5 %. When the forward speed is 0.6 m/s, the minimum harvest loss rate is 2.32 %, and which indicated the control system meets the requirements of sunflower harvesting operation.

Currently there are fewer depth models applied to pepper picking detection, while the existing generalized neural networks have problems such as large model parameters, long training time, and low model accuracy.In order to solve the above problems, this paper proposes a Yolo-chili target detection algorithm for chili pepper detection. First, the classical target detection algorithm yolov5 is used as a benchmark model, and an adaptive spatial feature pyramid structure combining the attention mechanism and the idea of multi-scale prediction is introduced to improve the model's detection effect on occluded peppers and small target peppers. Secondly, a three-channel attention mechanism module is introduced to improve the algorithm's long-distance recognition ability and reduce the interference of redundant testers. Finally, the quantized pruning method is used to reduce the model parameters and realize the lightweight processing of the model. Applying the method to the homemade chili pepper dataset, the AP value of chili pepper reaches 93.11%; the accuracy rate is 93.51% and the recall rate is 92.55%.The experimental results show that yolo-chili is able to achieve accurate and real-time pepper detection under complex orchards.

Ever since Varela and Maturana proposed the concept of autopoiesis as the minimal requirement for life, there has been a focus on cellular systems that erect topological boundaries to separate themselves from their surrounding environment. Here we reconsider whether the existence of such a spatial boundary is strictly necessary for self-producing entities. This work presents a novel computational model of a minimal autopoietic system inspired by dendrites and molecular dynamics simulations in three-dimensional space. A series of simulation experiments where the metabolic pathways of a particular autocatalytic set are successively inhibited until autocatalytic entities that could be considered autopoietic are produced. These entities maintain their distinctness in an environment containing multiple identical instances of the entities without the existence of a topological boundary. This gives rise to the concept of a metabolic boundary which manifests as emergent self-selection criteria for the processes of self-production without any need for unique identifiers. However, the adoption of such a boundary comes at a cost, as these autopoietic entities are less suited to their simulated environment than their autocatalytic counterparts. Finally, this work showcases a generalized metabolism-centered approach to the study of autopoiesis that can be applied to both physical and abstract systems alike.

Recently, attention mechanisms have developed into an important tool for performance improvement of deep neural networks. In computer vision, attention mechanisms are generally divided into two main branches: spatial and channel attention. Both attention categories have their own advantages. The fusion of both attentions achieves higher performance, on the cost of the computational load. This paper introduces an innovative and lighter n-shifted sigmoid channel and spatial attention (CSA) module to reduce the computational cost and to improve the 3D scene relevant features selection. To validate the proposed attention module, 3D scene object detection in the deep Hough voting point sets is considered as the testing application. The proposed attention module with its piecewise n-shifted sigmoid activation function improves the network’s learning and generalization capacity which effectively predict bounding box parameters directly from 3D scenes and detect objects more accurately. This advantage is achieved by selectively attending to more relevant features of the input data. When used in the deep Hough voting point sets, the proposed attention module outperforms state-of-the-art 3D detection methods on the sizable SUNRGBD dataset. Experiments conducted showed an increase of 12.02 mean accuracy precision (mAP) when compared to the celebrated VoteNet (without attention). It also got 9.92 mAP higher compared to the MLVCNet, and 10.32 mAP higher than the Point Transformer. The proposed model not only decreases the sigmoid vanishing gradient problem but also brings out valuable features by fusing channel-wise and spatial information while improving accuracy results in 3D object detection.

The influence of short term water absorption on the mechanical properties of halloysite nanotubes-multi layer graphene reinforced polyester hybrid nanocomposites has been investigated. The addition of nano-fillers significantly increased the flexural strength; tensile strength and impact strength in dry and wet conditions. After short term water exposure; the maximum microhardness; tensile; flexural and impact toughness values were observed at 0.1 wt% MLG. The microhardness increased up to 50.3%; tensile strength increased up to 40% and flexural strength increased up to 44%. Compared to dry samples; the fracture toughness and surface roughness of all types of produced nanocomposites were increased that may be attributed to plasticization effect. Scanning electron microscopy revealed that the main failure mechanism is caused by the weakening of nano-filler-matrix interface induced by water absorption. It was further observed that synergistic effects were not effective at concentration of 0.1 wt% to produce considerable improvement in mechanical properties of produced hybrid nanocomposites.

In this paper, the boiling flow inside a nanochannel with 700000 argon particle has been simulated by molecular dynamics (MD) simulation. This approach has been employed to analysis the superheated flow and its heat transfer pattern as well. For all simulations an external thrust force varying from 1 PN to 12 PN is exerted on inlet nanoparticles along the channel to have the forced annular boiling flow. Computations reveal that saturation condition and superheat degree have significant impacts on the liquid-vapor interface. Furthermore, because of the major influence of surface tension throughout a nanochannel, the x-velocity of liquid film and vapor core has not considerable fluctuations and stay smooth. All provided results show the behaviors completely similar to the available outcomes in the literature.

To address the requirements of sonar imaging, such as high receiving sensitivity, wide bandwidth, wide receiving angle, an AlN PMUT with an optimized ratio of 0.6 for the piezoelectric layer diameter to backside cavity diameter is proposed in this paper. A sample AlN PMUT is designed and fabricated with SOI substrate-based bulk MEMS process. The characterization test result of the sample demonstrates a -6 dB bandwidth of approximately 500 kHz and a measured receiving sensitivity per unit area of at 1.37 V/μPa/mm2, which significantly surpasses the performance of previously reported PMUTs. The -6 dB horizontal angles of the AlN PMUT at 300 kHz and 500 kHz are measured 68.30° and 54.24°, respectively. To achieve an accurate prediction of its characteristics when being packaged and assembled in a receive array, numerical simulations with the consideration of film stress are conducted. The numerical result shows a maximum deviation of ±7% in the underwater receiving sensitivity across the frequency range of 200 kHz to 1000 kHz and a deviation of about 0.33% in the peak of underwater receiving sensitivity comparing to the experimental data. By such good agreement, the simulation method reveals its capability of providing theoretical foundation for enhancing the uniformity of the AlN PMUTs in future studies.

In the recent years, tubular nanostructures have been related with immense advances in various fields of science and technology. Considerable research efforts have been centered on the theoretical prediction and manufacturing of non-carbon nanotubes (NTs), which meet modern requirements for the developing of novel devices and systems. In this context, diatomic inorganic nanotubes formed by atoms of elements from the 13th group of the periodic table (B, Al, Ga, In, Tl) and nitrogen (N), have received much research attention. In the present work, the elastic properties of single-walled boron nitride, aluminium nitride, gallium nitride, indium nitride and thallium nitride nanotubes were numerically evaluated using the nanoscale continuum modelling approach (also called molecular structural mechanics). The elastic properties (rigidities, surface Young´s and shear moduli, and Poisson´s ratio) of nitride nanotubes are discussed with respect to the bond length of the corresponding diatomic hexagonal lattice. The results obtained contribute to a better understanding of the mechanical response of nitride compound-based nanotubes, covering a broad range from the well-studied boron nitride NTs to the hypothetical thallium nitride NTs.

To stabilize the Earth’s climate a large-scale transition is needed to non-carbon emitting renewable energy technologies like wind and solar energy. Although these renewable energy sources are now lower-cost than fossil fuels, their inherent intermittency make them unable to supply a constant load without storage. To address these challenges rechargeable electric batteries are currently the most promising option; however, their high capital costs limit current deployment velocities. To both reduce the cost as well as improve performance 3D printing technology has emerged as a promising solution. This literature review provides the state-of-the-art enhancements of battery properties with 3D printing including efficiency, mechanical stability, energy and power density, customizability and sizing, production process efficiency, material conservation and environmental sustainability as well as the progress in solid-state batteries. The principles, advantages, limitations, and recent advancements associated with the most common types of 3D printing are reviewed focusing on their contributions to the battery field. 3D printing batteries offer design flexibility, material flexibility, reduces pack weight, minimizes material waste, increases the range of applications and has the potential to reduce costs. As 3D printing technologies become more accessible, the prospect of cost-effective production for customized batteries is extremely promising.

Background/Objectives: The aim of this study was to investigate feasibility and safety of neuromuscular electrical stimulation (NMES) in patients on extracorporeal membrane oxygenation (ECMO) and assess thoroughly any potential adverse events. Methods: We conducted a safety and feasibility study including 16 ICU patients on ECMO support who were admitted to the cardiac surgery ICU from January 2022 to December 2023. Patients underwent a 45-minute NMES session, still on ECMO support, that included a warm up phase of 5 minutes, a main phase of 35 minutes and a recovery phase of 5 minutes. NMES was implemented on vastus lateralis, vastus medialis, gastrocnemius and peroneus longus muscle of both lower extremities. Two stimulators delivered biphasic, symmetric impulses of 75 Hz, with 400 μsec pulse duration, 5 sec on (1,6 sec ramp up and 0,8 sec ramp down) and 21 sec off. The intensity levels aimed to cause visible contractions and be well tolerated. Primary outcomes of the study were feasibility and safety, evaluated by whether the NMES sessions were successfully achieved, and by any adverse events and complications. Secondary outcomes included indices of rhabdomyolysis from biochemical blood test, 24 hours after the application of NMES. Results: All patients successfully completed their 45-minute NMES session, without presenting hemodynamic deterioration, adverse events or signs of rhabdomyolysis. The majority of patients achieved type 4 and 5 quality of muscle contraction. Conclusions: NMES is a safe and feasible exercise methodology in patients supported with ECMO.

Lung cancer remains a pervasive global health challenge, necessitating precise and efficient classification methods to inform optimal treatment strategies. In this study, we investigate the potential of machine learning algorithms in developing a computer-aided diagnostic tool for early and accurate lung cancer classification, leveraging essential protein biomarkers as predictive features. Our investigation reveals the superiority of Deep Neural Networks (DNNs) in lung cancer classification, achieving an impressive accuracy of 96.91%. This highlights the transformative potential of DNNs in facilitating real-world clinical applications, offering clinicians a powerful tool for accurate diagnosis and prognosis. Additionally, we analyze the performance of Ensemble Methods, including Voting (91.75%) and Bagging (93.81%), as viable alternatives to DNNs. These ensemble techniques demonstrate robust performance, further underlining their utility in lung cancer classification tasks. Furthermore, our study underscores the critical role of hyperparameter tuning, particularly in adjusting parameters such as min child weights and learning rates, in mitigating overfitting and enhancing the generalizability of diverse machine learning models. For instance, Support Vector Machines (SVM) exhibit varying accuracies ranging from 74.23% to 95.88% across different hyperparameter configurations, emphasizing the importance of hyperparameter optimization in maximizing model performance. In summary, our comprehensive comparative analysis sheds light on the efficacy of different machine learning approaches in lung cancer classification. By leveraging advanced algorithms and optimizing model parameters, researchers and clinicians can harness the power of machine learning to advance early detection and personalized treatment strategies for lung cancer patients.

Driven by the importance of early detection for improving patient outcomes, this study investigates the effectiveness of various machine learning algorithms in predicting lung cancer based on clinical data. Lung cancer remains a significant global health concern, and this research seeks to contribute to advancements in early diagnosis through the application of machine learning techniques. The dataset consists of 385 training and 97 test samples, with a k-fold cross-validation approach (k=5) utilized to mitigate overfitting. Additionally, the ADASYN oversampling technique is employed to address class imbalance. Our analysis includes traditional algorithms such as Logistic Regression and Decision Trees, as well as ensemble methods like XGBoost, LGBM, and AdaBoost. Furthermore, we explore the effectiveness of deep learning models, particularly Deep Neural Networks (DNN). Results demonstrate promising accuracy rates across all models, with some outperforming others in terms of precision, recall, and F1-score. Our findings reveal that LGBM achieves the highest accuracy among all models, with an accuracy rate of 96.91%. It also exhibits superior performance in terms of precision, recall, and F1-score, particularly in classifying both positive and negative instances of lung cancer.

In recent decades, the requirements for implantable medical devices increased, but the risks of implant rejection still exist. These issues are primarily associated with poor osseointegration, leading to biofilm formation on the implant surface. This study focuses on addressing these issues by developing a biomaterial for implant coatings. 45S5 Bioglass has been widely used in tissue engineering due to its ability to form a hydroxyapatite layer, ensuring a strong bond between the hard tissue and the bioglass. In this context, 45S5 bioglasses, modified by the incorporation of different amounts of copper oxide, from 0 to 8 mol%, were synthesized by the melt-quenching technique. The incorporation of Cu ions does not show a significant change in the glass structure. Since the bioglass exhibited the capacity of being polarized, and therefore promoting the osseointegration effectiveness, the electrical properties of the prepared samples were studied using the impedance spectroscopy method, in the frequency range of 102-106 Hz and temperature range of 200-400 K. The effects of CuO on charge transport mobility were investigated. Additionally, the bioactivity of the modified bioglasses was evaluated through immersion tests in simulated body fluid. The results revealed the initiation of a Ca-P-rich layer formation on the surface within 24 h, indicating the potential of the bioglasses to enhance the bone regeneration process.

A novel five-surface phosphor-in-ceramic (FS-PiC) for high illumination and excellent color uniformity in larger-scale LEDs for sensor light source application is demonstrated. YAG phosphor (Y3Al5O12:Ce3+) was uniformly mixed with ceramic and sintered at 680°C to form a phosphor wafer. A sophisticated laser engraving was employed on the phosphor wafer to form a saddle-shaped large-scale FS-PiC LEDs. The performance of the FS-PiC LEDs exhibited the illumination of 401lm, average color temperature (CCT) of 5488K±110K, and color coordinates (CIE) of (0.3179±0.003, 0.3352±0.003). In contrast to convention single-surface phosphor-in-ceramic (SS-PiC) LEDs, the performance exhibited the illumination of 380lm, average CCT of 5830K±758K, and CIE of (0.3083±0.07, 0.3172±0.07). These indicated that the performance of the FS-PiC LEDs was higher than the SS-PiC LEDs for illumination, CCT, and CIE of 1.1, 7, and 23 times, respectively. Furthermore, the FS-PiC LEDs demonstrate lower lumen loss of 2% and less chromaticity shift of 5.4x10-3 under accelerated aging at 350°C for 1008 hours, owing to the high ceramic melting temperature of up to 510°C. In this study, the proposed FS-PiC larger-scale LEDs having excellent optical performance and high reliability may be the promising candidates to replace the convention phosphor-in-organic silicone material used in high-power LEDs for the next generation of sensor light sources, display, and headlight applications.

To secure logic circuits against the illegal copying the insertion of the so-called key bit inputs using XOR/XNOR gates has been proposed in . The inserted gates modify (lock) the behavior of the original circuit and only the correct choice of the secret key bits guarantees the equivalent behaviour of the locked circuit to the original circuit. To break this kind of security, i.e. to find the secret key bits, there was a SAT solver based attack proposed in . The aim of this work is to experimentally verify this attack on several locked circuits with various number of primary inputs and outputs and with various number of gates. Except for the random placement of the key gates we evaluate also the positioning with chaining elimination. The obtained and presented results show that we were able to unlock 10 of 11 circuits within few minutes on a common PC.

This study investigates the effects of Zinc (4wt.%) and severe plastic deformation on the mechanical properties of AZ61 magnesium alloy through the stir-casting process. The severe plastic deformation (equal channel angular pressing (ECAP)) has been done followed by T4 heat treatment. The microstructural examinations revealed that the addition of 4wt.%Zn enhances the uniform distribution of β-phase, contributing to a more uniformly corroded surface in corrosive environments. Additionally, dynamic recrystallization (DRX) significantly reduces the grain size of as-cast alloys after undergoing ECAP. The attained mechanical properties demonstrate that after a single ECAP pass, AZ61 + 4wt.%Zn alloy exhibits optimal yield strength (YS), ultimate compression strength (UCS), and hardness. This research highlights the promising potential of AZ61 + 4wt.%Zn alloy for enhanced mechanical and corrosion-resistant properties, offering valuable insights for applications in diverse engineering fields.

Three types of the composites were tested for electromagnetic interference (EMI) absorption shielding effectiveness, curing process and physical-mechanical properties. In the first type of composites, manganese-zinc ferrite, nickel-zinc ferrite, and both fillers in their mutual combinations were incorporated into acrylonitrile-butadiene rubber. The overall content of the filler, or fillers combinations was kept on 200 phr. Then, carbon black, or carbon fibres, respectively were incorporated into each rubber formulation in constant loading - 25 phr, while the content of magnetic fillers was unchanged - 200 phr. The work was focused on the understanding of correlation among electromagnetic shielding parameters and electrical conductivity of composites in relation to their EMI absorption shielding effectiveness. The absorption shielding ability of materials was evaluated within the frequency range from 1 MHz to 6 GHz. The study revealed good correlation among permittivity, conductivity, and EMI absorption effectiveness. Although, the absorption shielding efficiency of composites filled only with ferrites seems to be the highest, the absorption maxima of those composites were reached over 6 GHz. The application of carbon based fillers resulted in higher electrical conductivity and higher permittivity of composites, which was reflected in their lower absorption shielding performance. Though, the composites with filled with ferrites and carbon based fillers absorbed electromagnetic radiation within the desired frequency range. The presence of carbon based fillers caused the improvement in tensile behavior of composites. The study also demonstrated that the higher was the ratio of nickel-zinc ferrite in magnetic fillers combinations, the higher was the absorption shielding performance.

The study findings revealed significant variability in various wood properties among different genetic families, although the static modulus of elasticity did not exhibit significant differences between the chosen genetic families. All measured wood properties decreased from the bottom to the top of the model trees. Wood hardness displayed a moderately negative correlation with wood density and weak correlations with MOE and MOR. Given the weak correlations between wood hardness and other wood mechanical properties, it is suggested that the MOEdyn would be a more suitable trait for genetic studies.

This paper presents an on-device semi-supervised human activity detection system that can learn and predict human activity patterns in real time. The proposed semi-supervised learning (SSL) framework uses sparsely labelled user activity events acquired from Inertial Measurement Unit (IMU) sensors installed as wearable device. The objective is to learn classification of multiple classes of human activities in real-time. The proposed cluster-based learning model in this approach is trained with data from the same target user, thus preserving data privacy while providing personalized activity detection services. Two different cluster labelling strategies, namely, population-based, and distance-based, are employed to achieve the desired classification performance. A comparative study of these strategies has been presented in terms of classifiability and classification accuracies. The proposed system is shown to be computationally efficient, which is relevant in the context of limited computing resources on typical wearable devices. The trade-off between classification accuracy and computation complexity is analyzed for different algorithmic hyper-parameters and other system parameters. Extensive experimentation and simulation study have been conducted on a multi-user human activity data from the public do-main in order to validate the proposed learning paradigm.

Due to the manufacturing process of Additive Manufacturing (AM) Parts the mechanical properties cannot be predicted. The scope of the present work is to propose a predictive tool for the mechanical properties of AM parts through the use of Adaptive Neuro-Fuzzy Inference System (ANFIS). The Adaptive Neuro-Fuzzy Inference System (ANFIS) combines neural networks with fuzzy logic to generate a mapping between the inputs and the output. Real data experiments from different AM technologies and materials compose the initial dataset so a detailed investigation is conducted to gain knowledge of how different parameters affect the UTS, the elongation and the Young modulus of each experiment. Experimental data were also use to train, check and verify the methodology. The method is tested for FFF technology, PLA material and 3 point bending stress, with interesting results.

Plant cells' ability to withstand abiotic stress is strongly linked to modifications in their mechanical characteristics. Nevertheless, the lack of a workable method for consistently tracking plant cell mechanical properties severely restricts our comprehension of the mechanical alterations in plant cells under stress. With Polyethylene Glycol (PEG6000), we created a drought-like environment, and we used the Double Resonator Piezoelectric Cytometry (DRPC) method to dynamically and non-invasively track changes in the stress (ΔS) created and viscoelasticity (storage modulus G' and loss modulus G") of protoplasts and suspension cells of rice during drought stress. The findings demonstrate that, rice suspension cells and protoplasts react mechanically differently to 5%–15% PEG6000 stress, implying distinct resistance mechanisms. However, neither of them can withstand 25% PEG6000 stress, they respond mechanically similarly to 25% PEG6000 stress. The results of DRPC are further corroborated by the morphological alterations of rice cells and protoplasts observed under an optical microscope. To sum up, the DRPC technique functions as a precise cellular mechanical sensor and offers novel research tools for the evaluation of plant cell adversity and differentiating between the mechanical reactions of cells and protoplasts under abiotic stress.

Transportation contributes significantly to greenhouse gas emissions, with electrification offering a promising solution. This study evaluates the degradation of State of Health (SOH) over 2.5 years for electrified buses under different charging protocols: DC Fast charging and Flash charging. The vehicles’ models, charging protocols, and financial implications are discussed. High-level simulations reveal that after 2.5 years, the Flash charging vehicle’s SOH reaches 88.93%, while the DC fast charging vehicle reaches 89.46%, showing a 0.47% difference. This slight variance is attributed to Flash charging vehicles avoiding full charge/discharge cycles, reducing battery aging impact. Considering this minimal SOH degradation difference, the choice between DC Fast charging and Flash charging primarily hinges on capital expenditure disparities. Flash charging, with its lower initial battery capacity and reduced capital costs, presents a compelling alternative for city busoperators seeking to electrify their fleets.

In this paper, a novel permanent magnet-assisted synchronous reluctance machine (PMASynRM) with rare-earth PMs and ferrite magnets is proposed. The performance of PMASynRM is discussed with respected to the different magnet ratio of rare-earth PMs and ferrite magnets. Some characteristics including the flux density, output torque, cogging torque, output power, power factor, torque ripple, loss, efficiency, and demagnetization are calculated by 2-D finite element analysis (FEA). The analysis results show that the excellent performance can be obtained by using hybrid magnet of rare-earth PMs and ferrite magnets with the suitable magnet ratio, and provide some desirable cost-performance trade-off.

By using the particle swarm optimization algorithm for crystal structure prediction, we reveal a newly orthorhombic Cmcm structure of HfB4, which is more energetically superior to the previously proposed YB4-, ReP4-, FeB4-, CrB4-, and MnB4-type structures in the considered pressure range. The phonon dispersion and elastic constants calculations confirm that the new phase is dynamically and mechanically stable. The calculated large shear modulus (240 GPa) and high hardness (45.7 GPa) imply that the predicted Cmcm-HfB4 is a potential superhard material. Meanwhile, the directional dependences of the Young's modulus, bulk modulus, and shear modulus for HfB4 are systematically investigated. Further analyses of the density of states and electronic localization function indicate that the strong B-B and B-Hf covalent bonds greatly contribute to its high hardness and stability.

Despite the availability of COVID-19 vaccines, the global pandemic remains a significant health challenge. Timely detection of the virus is crucial for effective containment efforts, prompting the exploration of machine learning (ML) models for COVID-19 detection. highlights the ongoing significance of COVID-19 as a global health crisis despite the availability of vaccines. To address the need for timely virus detection, the study explores the efficacy of machine learning (ML) models, including DNN, Voting, Bagging, SVC_rbf, SVC_linear, SVC_polynomial, and SVC_sigmoid, in predicting COVID-19 infection probability. With a dataset comprising 4000 samples split into 3200 for training and 800 for testing, the analysis reveals that DNN and Voting models demonstrate the highest performance, achieving an impressive accuracy of 89%. These results underscore the potential of ML techniques, particularly DNN and ensemble methods like Voting, in facilitating early COVID-19 detection and contributing to effective pandemic management. The study emphasizes the importance of continued research to further refine and optimize ML-based COVID-19 detection systems.

Hybrid electric vehicles (HEVs) are perceived as a first step towards the future of sustainable transport. Of course, battery electric vehicles (EVs) are currently ideal for what is wanted to stand for transport in the future. The lack of infrastructure for these vehicles makes many potential users choose hybrid vehicles in these conditions. This paper analyzes the influence of the engine and electric motor of hybrid vehicles on their performances. Three engines with slightly different power and close characteristics were considered for configured models. Also, two electric motors with very different power but having a very close maximum continuous torque have been used in models. One is an induction motor, and the other is a permanent magnet synchronous motor. ADVISOR software has been used for vehicles configuration and simulation. Series and parallel hybrid vehicles have been considered. The main dynamic performances and the fuel consumption in two driving cycles were compared for the configured models. Three conventional models with the same engines used in HEVs have also been simulated for reference. The results highlight that in the case of HEVs, the choice of combination engine/electric motor is crucial in obtaining the best report between dynamic performances and low fuel consumption, and implicitly a low negative impact on the environment.

Numerous image processing techniques (IPTs) have been employed to detect crack defects, offering an alternative to human-conducted onsite inspections. These IPTs manipulate images to extract defect features, particularly cracks in surfaces produced through Additive Manufacturing (AM). This article presents a vision-based approach that utilizes deep convolutional neural networks (CNNs) for crack detection in AM surfaces. Traditional image processing techniques face challenges with diverse real-world scenarios and varying crack types. To overcome these challenges, our proposed method leverages CNNs, eliminating the need for extensive feature extraction. Annotation for CNN training is facilitated by LabelImg without the requirement for additional IPTs. The trained CNN, enhanced by OpenCV preprocessing techniques, achieves an outstanding 99.54% accuracy on a dataset of 14,982 annotated images with resolutions of 1536 × 1103 pixels. Evaluation metrics exceeding 96% precision, 98% recall, and a 97% F1-score highlight the precision and effectiveness of the entire process.

As modern systems are becoming more complex their control strategy cannot longer relay only on measurement information that usually comes from probes but also from mathematical models. Those systems models can lead to unbearable computation times due to their own complexity, turning the control process non-viable, which leads to the implementation of surrogate models that enable to achieve estimates within acceptable time to take decisions. A control trained with Deep Reinforcement Learning algorithm, using a Physics-Informed Neural Network to obtain the temperature map on the following time step, replaces the need of running Direct Numerical Simulations. On this work we considered an 1D heat conduction problem, which temperature distribution feeds a control system to activate a heat source aiming to obtain a constant, previously defined, temperature value. With this approach, control training becomes much faster without the need of performing numerical simulations or laboratory measurements, as well the control is taken based on Neural Network enabling its implementation on simple processors to edge computing.

In order to solve the problem of fault diagnosis for CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and ensemble learning model is proposed. First, various monitoring signals including vibration signal, noise signal and current signal are collected. Then, the monitoring signals are preprocessed and the time-domain, frequency-domain and time-frequency domain feature indexes are extracted to construct a multi-dimensional mixed domain feature set. Finally, the feature set is putting into the constructed DoubleEnsemble-LightGBM model to realize the fault diagnosis of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the public data set and the feed system test bench data set, and the average overall accuracy is 91.07% and 98.06% respectively. Compared with XGBoost and other advanced ensemble learning models, the method has better accuracy. It provides technical support for the stable operation and intelligent of CNC machine tools..

This paper presents geometric analyses of welded frames after free relaxing and vibratory stress relief (VSR). Respected frames were tested components of a prototype packaging machine. Two types of relaxation were carried out to remove stresses introduced as a result of welding process. One of the frame was subjected to free relaxing, while the other one to accelerated vibration relaxing. Detection of the frame geometry changes was performed using a photogrammetric system. In addition, an evaluation of the geometry change was conducted for fifteen variants of steel frame support. A comparative analysis of the geometric deviations of the frames after free and vibratory stress relief confirmed the assumption that the frame after vibration stress relief better reproduces the nominal dimensions. Nevertheless, it should be emphasized that after vibratory stress relief the frame is not subject to further deformation, which is a desirable effect. In the case of free relaxing, the frame undergoes dimensional changes in a random manner. In summary, carrying out accelerated vibratory stress relief allows control of spontaneous dimensional changes in the designed frame of a packaging machine resulting from spontaneous relaxation of stresses arising from the welding process. The shortening of the relaxation process of the welded frame is also an unquestionable advantage.

The undoped and tungsten (W)-doped vanadium dioxide (VO₂) thin films were prepared by electron beam evaporation associated with ion-beam assisted deposition (IAD). The influence of different W-doped contents (3%-5%) on the optical, electrical, structural, and thermos-mechanical properties of VO₂ thin films was investigated experimentally. Spectral transmittance results showed that with the increase of W-doped contents, the transmittance in the visible light range (400-750 nm) decreases from 60.2% to 53.9%, and the transmittance in the infrared wavelength range (2.5 μm to 5.5 μm) drops from 55.8% to 15.4%. As the W-doped content increases, the residual stress in the VO₂ thin film decreases from -0.276 GPa to -0.238 GPa, but the surface roughness increases. For temperature-dependent spectroscopic measurements, heating the VO2 thin films from 30°C to 100°C showed the most significant change in transmittance for the 5% W-doped VO₂ thin film. When the heating temperature exceeds 55°C, the optical transmittance drops significantly, and the visible light transmittance drops by about 11%. Finally, X-ray Diffraction (XRD) and scanning electron microscope (SEM) were used to evaluate the microstructure characteristics of VO₂ thin films.

Ambulatory heart rate (HR) monitors that acquire electrocardiogram (ECG) or/and photoplethysmographm (PPG) signals from the torso, wrists, or ears are notably less accurate in tasks associated with high levels of movement compared to clinical measurements. However, reliable estimation of HR can be obtained through data fusion from different sensors. These methods are especially suitable for multimodal hearable devices, where heart rate can be tracked from different modalities, including electrical ECG, optical PPG, and sounds (heart tones). Combined information from different modalities can compensate for single source limitations. In this paper, we evaluate the possible application of data fusion methods in hearables. We assess data fusion for heart rate estimation from simultaneous in-ear ECG and in-ear PPG, recorded on eight subjects while performing 5-minute sitting and walking tasks. Our findings show that data fusion methods provide a similar level of mean absolute error as the best single-source heart rate estimation but with much lower intra-subject variability, especially during walking activities. We conclude that data fusion methods provide more robust HR estimation than a single cardiovascular signal. These methods can enhance the performance of wearable devices, especially multimodal hearables, in heart rate tracking during physical activity.

Statistical denoising techniques have been well studied, however many challenges still remain. This 9 article focuses on determining the least necessary number of significant samples in a statistical pop-10 ulation sampling, while minimizing the impact on the statistical detection of the fiber Bragg grating 11 (FBG) power spectra. This is achieved by using Bayesian decision making, small population statis-12 tics while excluding false detection. First, we investigate the impact of two-sided sliding window 13 technique applied near the cell under the test. The window size varies from 8 to 60 samples. The 14 considered maximum size of population sampling is connected with the number of wavelength 15 samples within the bandwidth of the symmetrical FBG power spectra peaks. Regarding the sym-16 metry of FBG power spectra peaks and the possible reduction of computational demands, we inves-17 tigate the impact of a one-sided sliding window. This enables to achieve less processing latency for 18 real time applications thus brings benefits to FBG-based fiber optical sensing. Both, two- and one-19 sided small population sampling techniques are then experimentally verified. Detection results are 20 analyzed in depth via calculating detection thresholds by using the small size window sliding along-21 side the waveband. From results achieved, it was found that the normality three-sigma rule does 22 not need to be followed while using the small population sampling. Experimental demonstrations 23 and analyses showed that the proposed concept of denoising and statistical threshold detection 24 based on the sliding window does not depend on the prior knowledge of probability distribution 25 functions of the FBG power spectra peaks level and background noise. We have also found that the 26 thresholds’ adaptability mainly depends on the statistical numerical characteristics of the above ad-27 ditive mixture of the FBG power spectra peaks signals and background noise.

The electroencephalogram (EEG) is a record of brain activity. Brain Computer Interface (BCI) technology formed by the EEG signal has become one of the hotspots at present. How to extract the feature signal of EEG is the most basic research of BCI technology. In this paper, A new method of recognizing fatigue, conscious, concentrated state of human brain is proposed by the combination of discrete wavelet transform and the neural network based on EEG signal. First of all, the law signal is preprocessed by the wavelet denoising method because the law EEG signal contains a large number of high frequency noise, which is decomposed into multi-layer high frequency signal and low frequency signal. thus, δ wave, θ wave, α wave, β wave are obtained by the wavelet transform. And then, frequency band energy of the different wave is regards as the feature signal of EEG. In the experiment, the feature signal is classified by radial basic function (RBF) and annealed chaotic competitive learning network (ACCLN). RBF and ACCLN networks are trained with 500 sets of sample data and are tested by 100 sets of samples in different mental states. The experimental results show that the average accuracy of RBF network under three conditions are 88.75%, 88.25%, 88.5%, respectively, and the correct rate of ACCLN network is 97%, 98%, 98%, respectively.

A portable laser photoacoustic sensor based on a Field-Programmable Gate Array (FPGA) is reported for methane detection. A tunable DFB diode laser in the 1654 nm wavelength range is used as an excitation source. The photoacoustic signal processing was implemented by a FPGA device. A small resonant photoacoustic cell is designed. The minimum detection limit (1σ) of 10 ppm for methane (CH₄) is demonstrated.

Based on the need for real-time sag monitoring of Overhead Power Lines (OPL) for electricity transmission, this article presents the implementation of a hardware and software system for online monitoring of OPL cables and cable sag determination. The mathematical model based on differential equations and the methods of algorithmic calculation of OPL cable sag are presented. Considering that, based on the mathematical model presented, the calculation of OPL cable sag can be done in different ways depending on the sensors used, and the presented application uses a variety of sensors. Therefore, a direct calculation is made using one of the different methods. Subsequently, the verification relations are highlighted directly and, respectively, the calculation by the alternative method, which uses another group of sensors, to generate both a verification of the calculation and the functionality of the sensors, thus obtaining a defect observer of the sensors. The hardware architecture of the OPL cable online monitoring application is presented, together with the main characteristics of the sensors and communication equipment used. The configurations required to transmit data using the ModBUS and ZigBee protocols are also presented. The main software modules of the OPL cable condition monitoring application are described, which ensure the monitoring of the main parameters of the power line and the visualisation of the results both on the electricity provider's intranet using a web server and MySQL database, and on the Internet using an Internet of Things (IoT) server. This categorisation of the data visualisation mode is done in such a way as to ensure a high level of cyber security. Starting from the mathematical model of the OPL cable sag calculation, it goes through the stages of creating such a monitoring system, from the numerical simulations carried out using Matlab to the real-time implementation of this monitoring application. The main modules of the application software are: the software module for reading quantities from the sensor network through a ModBUS Input/Output (I/O) server, the software module for real-time calculation of the OPL cable sag, the software module for read/write operations based on MySQL type data, the software module for transferring data to the user's intranet through a web server, and the software module for viewing data by authorised users based on user and password through an IoT server. The development software environments used are Matlab and Laboratory Virtual Instrument Engineering Workbench (LabVIEW).

Quantum computing (QC) has opened the door to advancements in machine learning (ML) tasks that are currently implemented in the classical domain. Convolutional neural networks (CNNs) are classical ML architectures that exploit data locality and possess a simpler structure than fully-connected multi-layer perceptrons (MLPs) without compromising the accuracy of classification. However, the concept of preserving data locality is usually overlooked in the existing quantum counterparts of CNNs, particularly for extracting multi-features in multidimensional data. In this paper, we present a multidimensional quantum convolutional classifier (MQCC) that performs multidimensional and multi-feature quantum convolution with average and Euclidean pooling and thus adapting the CNN structure to a variational quantum algorithm (VQA). Average pooling is based on the quantum Haar transform (QHT) and Euclidean pooling is based on partial quantum measurement. The experimental work was conducted using multidimensional data to validate the correctness and demonstrate the scalability of the proposed method utilizing both noisy and noise-free quantum simulations. We evaluated the MQCC model with reference to reported work on state-of-the-art quantum simulators from IBM Quantum and Xanadu using a variety of standard ML datasets. The experimental results showed favorable characteristics of our proposed techniques compared to existing work with respect to a number of quantitative metrics such as the number of training parameters, cross-entropy loss, classification accuracy, circuit depth, and quantum gate count.

This study utilises NaOH to treat composite cementitious materials containing aeolian sand and zeolite powders, which were used to replace 50% of the cement in aeolian-sand concrete (ASC). The mechanical properties of treated ASC considerably improved, especially when the NaOH dosage was 4% by mass. After curing this sample (denoted as AAZC-4) for 28 d, its compressive strength improved by 17.2% and its split tensile was increased by 16.3%. Potassium feldspar and montmorillonite in zeolite powder and SiO2 in the sand were decomposed by OH− and combined with other elements to generate various silicate gels and A-type potassium zeolite crystals inside the concrete. Microscopic examination showed that the gels and crystals intertwined to fill the pores, decreasing (increasing) the percentage of large (small) pores, thus optimising the pore structure. This substantially improved the mechanical properties of ASC. Freeze–thaw salt-intrusion tests showed that the extent of mass loss, degree of damage and loss of compressive strength of AAZC-4 were similar to those of ordinary concrete but were reduced by 36.8%, 19% and 52.1%, respectively, compared with those of ASC. Therefore, AAZC-4 has sustainable working performance in the chloride ion permeable environment in cold and arid areas.

This literature review provides an in-depth exploration of the research conducted on the investigation and measurement of residual stress (RS) in Wire Arc Additive Manufacturing (WAAM) products, particularly focusing on how process parameters influence the phenomenon. RS plays a crucial role in determining the mechanical behavior and structural integrity of WAAM components. This review article gives an understanding of the relationship between process parameters and RS to optimize the WAAM processes and ensure the durability of the final products. It also summarizes key findings, measurement techniques, challenges, and future directions in this evolving field. The review also analyzes a measurement of RS in the products of WAAM as a function of process parameters depending on examining various research studies, techniques, and methodologies employed in their studies. Experimental measuring techniques and numerical analysis of RS to determine the impacts of RS in mechanical response in products of WAAM were discussed. By offering a comprehensive overview of current research trends and insights, this review serves as a valuable resource to guide future investigations, fostering the advancement of WAAM as a robust and efficient manufacturing technology.

To enhance the applicability of dual-phase high-entropy alloys (HEAs) like Fe32Cr33Ni29Al3Ti3, fabricated via selective laser melting (SLM), a focus on improving their mechanical properties is essential. As part of this effort, heat treatment was explored. This study compares the microstructure and mechanical properties of the as-printed sample with those cooled in water after undergoing heat treatment at temperatures ranging from 1000 to 1200 ℃ for 1 hour. Both pre- and post-treatment samples reveal a dual-phase microstructure comprising FCC and BCC phases. Although heat treatment led to a reduction in tensile and yield strength, it significantly increased ductility compared to the as-printed sample. This strength-ductility trade-off is related to changes in grain sizes with ultrafine grains enhancing strength and micron grains optimizing ductility, also the influence of the content of FCC/BCC phases and dislocation density. In particular, the sample heat-treated at 1000 °C for 1 hour and then water-cooled exhibited a better combination of strength and ductility, a yield strength of 790 MPa, and an elongation of 13%. This research offers innovative perspectives on crafting dual-phase HEA of Fe32Cr33Ni29Al3Ti3, allowing for tailorable microstructure and mechanical properties through a synergistic approach involving SLM and heat treatment.

This paper aims to address the exponential stability and stabilization problems for a class of delayed nonlinear Markov jump systems under randomly occurring Denial-of-Service (DoS) attack and packet loss. Firstly, the stochastic characteristics of DoS attack and packet loss are depicted by the attack success rate and packet loss rate. Secondly, a Period Observation Window (POW) method and a hybrid-input strategy are proposed to compensate for the impact of DoS attack and packet loss on the system. Thirdly, A Dynamic Event-triggered Mechanism (DETM) is introduced to save more network resources and ensure the security and reliability of systems. Then, by constructing a general common Lyapunov functional and combining with the DETM and other inequality analysis techniques, the less conservative stability and stabilization criteria for the underlying systems are derived. In the end, the effectiveness of our result is verified through a numerical example.

The research reported on this paper was aimed at improving the overall efficiency of a PDO certified artisanal cheese production process. Being a PDO certified foodstuff by the EU, it is considered to have properties and qualities determined by the geographical environment in which is made, with its production taking place in a specific and determined geographical location, in this case the Serra da Estrela region. In that sense, the authors conducted a mapping according to a systemic perspective of the processes involved in the context of manufacturing and distribution of certified Serra da Estrela cheese. Numerous methods were used throughout the process, such as a systemic design analysis, and techniques derived from ethnographic methods, which led to the collection of data in the field and consequently provided the immersion of the researcher in genuine work situations. Critical points were identified and emphasized in the systemic map with the purpose of encouraging initiatives to address and overcome the gaps and inefficiencies detected. The systemic design analysis triggered the development of design work. Observations following an ethnographic approach identified ergonomic risks in cheese making during the process of cutting excess chips, fostering the emergence of musculoskeletal disorders at the wrist. A tool that fits best to the task at hand was developed. A prototype of the new tool enabled collecting feedback from use in the work context, in order to inform product development. The domains of agricultural production and microbiology, considering the specific microorganisms developed trough the ripening process of the cheese, turned out to be aspects of high importance for the issue under focus, contributing to a broader understanding of the ripening process and its risks, simultaneously improving the efficiency and success of cheese production. If it were not for the systemic analysis, which served as a link between the boundaries of distinct domains such as the risk of microorganism contamination, ergonomics, energy efficiency, legislation and regulation policies, transportation challenges and economic viability, approached throughout the research. Simultaneously creating bridges between them, the various problems might not have been detected in the first place, as they are usually addressed in specialized disciplines, predetermined by the restrictions of each specific area of knowledge. As a consequence of the development of this research, which was based on an analysis that sought to establish possible connections between various disciplines and tried to constantly maintain a holistic perspective, making new connections and observing the issues from a new angle, apart from the already established methodologies. All this allowed to lay out the seeds for the development of a plan to tackle the critical points identified by the systemic analysis reported in this paper.

The goal of this research is to determine the optimal microwave-assisted sol-gel synthesis pa-rameters of TiO2 nanoparticles with the achievement of the crystalline TiO2 nanoparticles with the highest specific surface area and the lowest energy band gap. Titanium isopropoxide was used as a precursor to prepare the sol (colloidal solution) of TiO2, isopropanol as a solvent, acetylacetone for complexation, and nitric acid as a catalyst. Four samples of titanium dioxide were synthesized from the prepared colloidal solution in a microwave reactor at a temperature of 150 °C for 30 minutes and at a temperature of 200 °C for 10, 20, and 30 minutes. The phase composition of the prepared samples was determined by X-ray diffraction analysis (XRD) and Fourier-transform infrared spectroscopy (FTIR). Nitrogen adsorption/desorption isotherms were used to determine the spe-cific surface area and pore size distributions by Brunauer-Emmett-Teller (BET) method. The band gap energy values of the TiO2 samples were determined by diffuse reflectance spectroscopy (DRS). CrystallineTiO2 nanoparticles with the highest specific surface area and the lowest energy band gap were obtained for the TiO2 sample synthesized at 200 °C for 10 minutes.

This article presents an innovative approach to the design of a safe adaptive backstepping control system. Tailored specifically for underactuated marine robots, the system utilizes simple sensors for enhanced practicality and efficiency. Given their operation in diverse oceanic environments fraught with various sources of uncertainties, ensuring the system's safe and robust behavior holds paramount importance in the control literature. To address this concern, this paper introduces a control strategy designed to ensure robustness at both the kinematic and dynamic levels. By emphasizing the compensation for the system uncertainties, the design integrates a straightforward fuzzy system structure. To further ensure the system's safety, a funnel surface is defined, followed by the design of a suitable nonlinear sliding surface as a function of the funnel and tracking error. Specifically leveraging the Lyapunov function, the study formally establishes the Semi-globally Practically Finite-time Stability of the closed-loop system, validated through simulations conducted on underactuated marine robots.

The effects of CO₂-water-rock interactions on the mechanical properties of shale are essential for estimating the possibility of sequestrating CO₂ in shale reservoirs. In this study, uniaxial compressive strength (UCS) tests together with an acoustic emission (AE) system and SEM & EDS analysis were performed to investigate the mechanical properties and microstructural changes of black shales with different saturation times (10 days, 20 days and 30 days) in water dissoluted with sub-/super-critical CO₂. According to the experimental results, the values of UCS, Young’s modulus and brittleness index decrease gradually with increasing saturation time in water with sub-/super-critical CO₂. Compared to intact samples, 30-days’ saturation causes reductions of 56.43% in UCS and 54.21% in Young’s modulus for sub-critical saturated samples, and 66.05% in UCS and 56.32% in Young’s modulus for super-critical saturated samples, respectively. The brittleness index also decreases drastically from 84.3% for intact samples to 50.9% for samples saturated in water with sub-critical CO₂, to 47.9% for samples saturated in water with super-critical carbon dioxide (SC-CO₂). SC-CO₂ causes a greater reduction of shale’s mechanical properties. The crack propagation results obtained from the AE system show that longer saturation time produces higher peak cumulative AE energy. SEM images show that many pores occur when shale samples are saturated in water with sub-/super-critical CO₂. The EDS results show that CO₂-water-rock interactions increase the percentages of C and Fe and decrease the percentages of Al and K on the surface of saturated samples when compared to intact samples.

Despite being stored at 113 K and atmospheric pressure, LNG cold potential is not exploited to reduce green ships’ energy needs. An innovative system based on three Organic Ranking Cycles integrated into the regasification equipment is proposed to produce additional power and recover cooling energy from condensers. A first-law analysis identified ethylene and ethane as suitable working fluids for the first and the second ORC making available freshwater and ice. Propane, ammonia and propylene could be arbitrarily employed in the third ORC for air-conditioning. An environmental analysis that combines exergy efficiency, ecological indices and hazard aspects for marine environment and ship’s passengers, indicated propylene as safer and more environmentally friendly. The exergy analysis confirms more than 20% of the LNG potential can be recovered from every cycle to produce a net clean power of 76 kW, whereas 270 kW can be saved by recovering condensers' cooling power to satisfy some ship needs. Assuming the sailing mode, a limitation of 162 kg in LNG consumptions was determined, avoiding the emission of 1584 kg of CO2 per day. Marine thermal pollution is reduced by 3.5 times by recovering the working fluids' condensation heat for the LNG pre-heating.

The focus of this work lies in the construction of monitoring system designed in the form of a patch using a long-lasting potentiometric electrolyte concentration sensor from metal electrodes, in a galvanic cell configuration Mg(s)|NaCl(aq)|Cu(s). Initially, a mathematical analysis was conducted on the expected sensor output through the Nernst equation. The experimental phase involved conducting controlled tests in the laboratory using various molar concentrations of sodium chloride (NaCl) in aqueous solution. Results showed that the electrolyte sensor allows for monitoring electrolyte levels in NaCl in the range of 0.02 to 1 M/L, with electrode lifespan exceeding 10 days. On the other hand, when patch is using human sweat during controlled exercise routines, it showed the sensor's capability for monitoring changes in the subjects' hydration levels in real time. The sensor output potential is greater than 1.7 volts when the sensor electrodes are in contact with human sweat, which is equivalent to measuring molar concentrations at normal hydration and moderately high hydration levels. Sensor results indicate that the system can function in a self-powered manner without external batteries. Additionally, the extended lifespan of its electrodes allows for continuous monitoring of imbalances in the human body, showcasing the system capability for long-term health assessment.

Pulmonary Embolism (PE) is the obstruction of blood arteries in the lungs by a blood clot. The mortality risk for PE is approximately 30%. Detecting pulmonary embolism in the segmental arteries of the lung is more challenging than in the main arteries and is very prone to being missed. A computer-based approach was created in this work to automatically identify pulmonary embolism in the segmental arteries using computed tomography images. The system's infrastructure includes an enhanced Mask R-CNN deep neural network that has been trained with images containing PE. The network accurately identifies the location of the pulmonary embolism on the computed tomography picture and successfully extracts its borders. The investigation was conducted by generating a local dataset. The study's performance was evaluated using pulmonary embolisms identified manually by the expert radiologist. The sensitivity, specificity, accuracy, dice coefficient, and Jaccard index values for 2130 pictures were 96.4%, 93.5%, 96.1%, 0.96, and 0.90, respectively. The improved Mask R-CNN model has demonstrated superior performance when compared to the traditional Mask R-CNN and U-Net models. This high-performance technology is designed to identify pulmonary embolism and will aid professionals in assessing the size of the embolism.

In this work, an analog front-end (AFE) circuit for Electrocardiogram (ECG) detection system has been designed, implemented, and investigated in an industry-standard Cadence simulation framework using advanced technology node of 45 nm. The AFE consists of an instrumentation amplifier, a Butterworth band-pass filter (with fifth-order low-pass and second-order high-pass sections), and a second-order notch filter- all are based on two-stage, Miller-compensated operational transconductance amplifiers (OTA). The OTAs have been designed employing the $g_m/I_D$ methodology. Both the pre-layout and post-layout simulation were carried out. The layout consumes an area of 0.0058 mm$^2$ without the resistors and capacitors. Analysis of various simulation results were carried out for the proposed AFE. The circuit demonstrates a post-layout bandwidth of 239 Hz with a variable gain between 44 to 58 dB, a notch depth of -56.4 dB at 50.1 Hz, a total harmonic distortion (THD) of -59.65 dB (less than 1\%), an input referred noise spectral density of $

The rock joint fissure slope in cold regions is prone to deformation and failure problems such as relaxation, tension and collapse under freeze-thaw (F-T) cycles. Based on the ideology of clean production and promoting the structural integrity of geotechnical projects in cold areas, this study designed and prepared aeolian-sand (AS) to replace part of river sand as a filling mortar material by taking advantage of the low cost and easy availability of AS. Investigations were carried out to determine the impact of varying proportions of AS in mortar on the microstructure and shear properties of the mortar-rock interface under F-T cycles. Therefore, F-T cycle testing, nuclear magnetic resonance (NMR) testing and shear testing were carried out on grout with different proportions of AS. The results show that the right proportion of AS replacement could enhance the shear deformation resistance and F-T resistance of the mortar-rock interface, and 30% proportion is the optimal proportion. By increasing of F-T cycles, the three types of specimens showed different degrees of particle spalling, shedding and cracking. The slurry-rock interface layer in the A (0%) group exhibited the most severe F-T deterioration, while the B (15%) group showed a lesser degree, and the C (30%) group performed the best. T2 spectrum curve and total spectrum area change law from the microscopic point of view to verify the 30% AS proportion mortar-rock interface F-T resistance is the strongest, followed by 15% AS proportion mortar, the weakest is ordinary mortar. The degradation of the mortar-rock bond is primarily due to the conversion of solid to liquid phases and the movement of internal water caused by fluctuating temperatures. The extent of F-T deterioration in the slurry-rock interface layer is greatly affected by the varying proportions of AS. The shear strength and shear stiffness of specific proportion of AS decreased with the increase of F-T cycles. For same F-T cycles, the shear strength and shear stiffness of group C (30%) were the highest, followed by group B (15%) and group A (0%). The grout material not only reinforces the F-T joint fissure slope, but also reduces the cost of grout reinforcement and promotes the clean production of geotechnical structures.

This paper explores the capability of various machine learning algorithms, including Random Forests and advanced gradient boosting techniques such as XGBoost, LightGBM, and CatBoost, to predict customer churn in the telecommunications sector. For this analysis, a dataset available to the public was employed. The performance of these algorithms was assessed using recognized metrics, including Accuracy, Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). These metrics were evaluated at different phases: subsequent to data preprocessing and feature selection; following the application of SMOTE and ADASYN sampling methods; and after conducting hyperparameter tuning on the data that had been adjusted by SMOTE and ADASYN. The outcomes underscore the notable efficiency of upsampling techniques such as SMOTE and ADASYN in addressing the imbalance inherent in customer churn prediction. Notably, the application of random grid search for hyperparameter optimization did not significantly alter the results, which remained comparatively unchanged. The algorithms' performance post- ADASYN application marginally surpassed that observed after SMOTE application. Remarkably, LightGBM achieved an exceptional F1-score of 89% and an ROC AUC of 95% subsequent to the ADASYN sampling technique. This underlines the effectiveness of advanced boosting algorithms and upsampling methods like SMOTE and ADASYN in navigating the complexities of imbalanced datasets and intricate feature interdependencies.

Sustainable manufacturing practices are becoming increasingly necessary due to the growing concerns regarding climate change and resource scarcity. Consequently, material recycling technologies have gradually become preferred over conventional processes. This study aimed to recycle waste polylactic acid (PLA) from household-disposed cups and lids to create 3D-printed parts and promote sustainable manufacturing practices. To achieve this, the current study utilised virgin and post-consumer PLA (sourced from household waste) blends. The PC-PLA wastes were shredded and sorted by size with the aid of a washing step, resulting in a filament with a 1.70 ± 0.5 mm diameter without fragmentation or dissolution. A 50:50 wt.% blend of virgin PLA (vPLA) and PC-PLA was selected as the standard recycling percentage based on previous research and resource conservation goals. The study investigated the impact of three 3D printing parameters (layer height (LH), infill density (I), and nozzle temperature (NT))on the quality of 3D-printed parts using a three-level L9 Taguchi orthogonal array. The findings revealed that blending PC-PLA with vPLA led to significant improvements in the tensile, flexural, and impact strengths by 18.40%, 8%, and 9.15%, respectively, compared to those of recycled PLA. This conclusion was supported by the investigation of the fracture surface area, which revealed fractographic features associated with printing parameters, such as plastic deformation and interfilament debonding. An ANOVA analysis revealed a positive influence of larger layer height and high nozzle temperature on the mechanical properties. Subsequently, the optimal printing parameters (LH: 0.3 mm, I: 100%, and NT: 215 °C) were determined using the S/N ratio, and a confirmation test using the optimum printing parameters exhibited a strong correlation with statistically predicted outcomes. Finally, the study used optimum printing parameters to fabricate 100% post-consumer recycled PLA 3D printed parts, demonstrating their potential for low-strength applications. Based on these findings, it can be concluded that virgin and post-consumer recycled PLA blended filament for fabricating 3D printed components is an effective way to support plastic recycling in the context of a circular economy.

The review aims to assess fifteen (15) academic literature sources, highlighting the application of machine learning algorithms in the maintenance operations of optical fiber networks. It exhibits the collection of data using PRISMA methodology—Preferred Reporting Item for Systems Review and Meta-Analyses. The application, results, and performance metrics are discussed based on the collected observations, computations, and statistics in the studies, which revealed records of high accuracy degrees ranging from 86% to 98% on average and quality ML models including Neural Networks (NNs), Support Vector Machines (SVMs), and LSTM, as well as deep learning models that disclosed effective results of determining challenges and problems within the optical fiber lines. The review mainly centralized on superior machine learning technologies that surpass traditional techniques in fault detection and localization for improved optical fiber networks’ operations while providing insights into the limitations and challenges encountered in real-world applications of these models, offering a comprehensive perspective on the optical fiber network’s domain.

This paper investigates an innovative photovoltaic cell configuration, denoted as “Au/CuSCN/RbGeI3/CdTe/ZnO/TiO2/FTO", using SCAPS-1D simulation. The research focuses on optimizing device performance by analyzing key components, including ZnO as the electron transport layer (ETL), RbGeI3 as the perovskite absorber layer, CuSCN as the hole transport layer (HTL), and CdTe as the active buffer layer. A comparison is made with the standard “Au/CuSCN/CH3NH3SnI3/CdTe/ZnO/TiO2/FTO" configuration under dark and illuminated conditions. Through an in-depth investigation involving temperature effects, generation rate analysis, RbGeI3 absorber layer thickness, Nd level, and interface defect levels, an optimized design for a unit area is achieved. The proposed solar cell demonstrates outstanding performance metrics, including an open circuit voltage (Voc) of 0.94V, a short circuit current density (Jsc) of 34.52mA/cm2, a fill factor (FF) of 77.77%, and an energy conversion efficiency (η) of 25.40%. These values significantly outperform the reference models with energy conversion efficiencies of 10.11% and 21.09%. Real-world applicability is validated by implementing these optimized characteristics in a photovoltaic system for Pakistan’s geographical location using PVSyst software. The suggested solar cell achieves a remarkable performance ratio (PR) of 85.6%, surpassing the PR of the reference basic solar cell model at 83%. The findings of this research offer a promising and superior solar cell design, incorporating innovative materials and optimization techniques to achieve exceptional energy conversion efficiency and overall performance. This study’s outcomes have the potential to advance photovoltaic technology and contribute to sustainable energy solutions worldwide.

The existence of low-cost and accurate tools that can equip the First Responders (FRs) to detect trapped victims and provide insights about their health condition in the aftermath of a disaster, is imperative. To address the problem of detecting trapped victims behind walls or debris, we have developed a tool that exploits an Ultra-Wide Band (UWB) radar sensor for data collection and Machine Learning (ML) algorithms for data analysis. To evaluate the efficacy of our approach, we collected data from nine humans, both in standing and lying down positions. Next, we applied various ML algorithms to the collected dataset for two discrete sub-tasks that are of interest from an FR’s perspective. The first task is the detection of the victim’s presence, where the algorithms attained more than 95% accuracy and F1-Score. The second task is the estimation of the distance between the radar sensor and the victim, where the tool showed an average error of less than 40 cm.

An active power dispatch method for a microgrid (MG) with multi-type loads, renewable energy sources (RESs) and distributed energy storage devices (DESDs) is the focus of this paper. The MG operates in a grid-connected model, and distributed power sources contribute to the service for load demands. The outputs of multiple DESDs are controlled to optimize the active power dispatch. Our goal with optimization is to reduce the economic cost under time-of-use (TOU) price, and to adjust the excessively high or low load rate of distributed transformers (DTs) caused by the peak-valley demand and load uncertainties. To simulate a practical environment, the stochastic characteristics of multi-type loads are formulated. The transition matrix of system state is provided. Then, a finite-horizon Markov decision process (FHMDP) model is established to describe the dispatch optimization problem. A learning-based technique is adopted to search the optimal joint control policy of multiple DESDs. Finally, simulation experiments are performed to validate the effectiveness of the proposed method, and the fuzzification analysis of the method is presented.

This study presents a groundbreaking approach in the field of gaming AI, focusing on the classic game” Pacman” through the lens of DRL integrated with advanced optimization techniques. The core of the research involves adapting DRL models for” Pacman”, utilizing the ESO for hyper- parameter tuning. These novel adaptations significantly enhance the AI agent’s performance, demonstrating a remarkable improvement in adaptability, responsiveness, and efficiency within the game environment. A pivotal aspect of this research is the innovative integration of metaheuristic optimization techniques into the DRL framework, a first in the domain of Atari gaming AI. This integration has proven essential in fine-tuning the DRL models, leading to a more effective and dynamic gaming experience. The study thoroughly evaluates and compares the performance of these algorithms, providing empirical support for their effectiveness and setting a new benchmark in AI-driven game development. The implications of this research extend beyond gaming AI, opening up possibilities for future exploration in several directions. Expanding DRL models to other complex gaming environments, continuous algorithmic enhancements, real-time learning adaptations, and applying these principles to robotics and autonomous vehicles are examples. The research also emphasizes ethical and responsible AI use in gaming to address fairness and addiction issues.

Responsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to improve forecasting accuracy, crucial for various application domains where real-world time series data often exhibit complex, non-linear patterns. Our approach advocates for utilizing Long Short Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models for precise time series forecasting. To ensure a fair evaluation, we compare the performance of our proposed approach with traditional neural networks, time-series forecasting methods, and conventional decline curves. Additionally, individual models based on LSTM, Bi-LSTM, and other machine learning methods are implemented for a comprehensive assessment. Experimental results consistently demonstrate that our proposed model outperforms all benchmarking methods in terms of mean absolute error (MAE) across most datasets. Addressing the imbalance between activations by consumer and prosumer groups, our predictions show superior performance compared to several traditional forecasting methods, such as the Autoregressive Integrated Moving Average model (ARIMA) and Seasonal Autoregressive Integrated Moving Average model (SARIMA). Specifically, the root mean square error (RMSE) of Bi-LSTM is 5.35%, 46.08%, and 50.6% lower than LSTM, ARIMA, and SARIMA, respectively, on the May test data.

The accurate forecasting of solar power output is essential for ensuring the stable and efficient operation of grid-connected photovoltaic (PV) systems, especially when faced with variable weather patterns. This research focuses on the integration of Machine Learning (ML) methodologies and climatic parameters to predict solar panel energy generation, with a specific emphasis on addressing consumption-production imbalances. Leveraging a dataset sourced from the Kaggle platform, the study is conducted in the context of Estonia, aiming to optimize solar energy utilization in this geographic region. The dataset, obtained from Kaggle, encompasses comprehensive information on climatic variables, including sunlight intensity, temperature, and humidity, alongside corresponding solar panel energy output. Leveraging machine learning algorithms, including XGBoost regression and neural networks, our model aims to identify complex patterns and relationships within the datasets. By tailoring the model to Estonia's climatic nuances, we seek to enhance the accuracy of energy production forecasts and, consequently, better manage the challenges associated with consumption-production imbalances. Furthermore, the research investigates the adaptability of the proposed model to diverse climatic conditions, ensuring its applicability for similar endeavors in other geographical locations. The performance of the forecasting model will be evaluated using error metrics like mean absolute error (MAE) and root mean squared error (RMSE). This study leverages a comprehensive dataset from Kaggle and utilizes advanced machine learning techniques to generate valuable insights. These insights can inform the development of sustainable energy policies and practices, ultimately leading to a more efficient and reliable renewable energy infrastructure.

Proteins have the ability to adsorb on the surface of materials, such as soft contact lenses (SCLs), and can affect the hydrophobicity, roughness and surface properties of the contact lenses (CLs), which, in turn, can influence the friction between the lenses and the ocular surface. Excessive friction between contact lenses and the ocular surface can lead to discomfort for the wearer and may cause irritation or inflammation of the cornea, better known as corneal ulcers (keratitis). Bovine serum albumin (BSA) is often used as a standard protein in biocompatibility testing of materials, including contact lenses. One standard commercial contact lenses was tested under lubricated conditions to access the coefficient of friction (CoF), being the contact lubricated with a tear like fluid (TLF) solution containing six different concentrations of BSA. In all cases, a good linearity of the results of the friction force was verified, so the first friction law can be applied to determine the value of the coefficient of friction. It was found that friction increases with increasing protein concentration.

The development of accurate dynamic battery pack models for electric vehicles (EVs) is critical for the ongoing electrification of the global automotive vehicle fleet, since these serve as a key element in the energy performance of an EV powertrain system. The Equivalent Circuit Model (ECM) technique at the cell level is commonly employed for this purpose, combining accuracy and efficiency in the representation of battery operation within the broader powertrain system. In this study, a second-order ECM model of a battery cell is being developed using Modelica, an equation-based modeling language. Parameter lookup tables at multiple levels of state of charge (SoC), extracted from Li-ion battery cells with 4 different commonly used cathode materials, have been utilized. This approach allows for a representation of the battery systems that are used in a wide range of commercial EV applications. To verify the model, an integrated EV model is developed and simulation results of the FTP75 driving cycle have been compared against an equivalent application in MATLAB Simulink. The findings demonstrate a close match between the results obtained from both software across different system points. Specifically, the maximum deviation of SoC is limited to 0.08% and the maximum value of relative voltage deviation is 1.4%. The verified model enables the exploration of multiple possible architecture configurations of EV powertrains with Modelica.

In this paper, the integrated performance of a modular biomass boiler with an existing industrial Rankine steam heat and power cycle and a supplementary supercritical-CO2 (sCO2) Brayton cycle is analyzed. The aim is to leverage the high efficiency supplementary sCO2 cycle to increase net generation and energy efficiency from the existing biomass boiler. Two sCO2 heater configurations situated within the flue gas flow path are investigated, namely a single convective-dominant heater, and a dual heater configuration with a radiative and a convective heater. A quasi-steady-state 1D model was developed to simulate the integrated cycle, including detailed component characteristics for the Rankine and Brayton cycles. The model solves the mass, energy, momentum, and species balance equations. The system is analyzed for three cases: (i) the existing Rankine cycle without the sCO2 integration, (ii) with the single convective-dominant sCO2 heater configuration, and (iii) the dual sCO2 heater configuration. The results show the required rate of overfiring for the sCO2 configurations, with a 15.3% increase in fuel flowrate resulting in an additional 21.2% in net power output. The model quantifies the impact of the sCO2 heaters, with reduced heat uptakes for downstream boiler heat exchangers. Furnace water wall heat uptake increased due to overfiring, offsetting the reduced heat uptakes at downstream evaporative heat exchangers. The dual configuration has more impact on Rankine cycle operation due to the radiative sCO2 heater placement in front of the second superheater, absorbing some of the direct radiation from the furnace.

Dynamic systems which underly controlled systems are expected to increase in complexity as robots, devices, and connected networks become more intelligent. While classical stable systems converge to a stable point (a sink), another type of stability is to consider a stable path rather than a single point. Such stable paths can be made of saddles which draw in trajectories from certain regions, and then push the trajectory toward the next saddle point. These are chains of saddles are called stable heteroclinic channels (SHCs), and can be used in robotic control to represent time sequences. While we have previously shown that each saddle is visualizable as a trajectory waypoint in phase space, how to increase the fidelity of the trajectory was unclear. In this paper, we hypothesized that the waypoints can be individually modified to locally vary fidelity. Specifically, we expected that increasing the saddle value (ratio of saddle eigenvalues) causes the trajectory to slow to more closely approach a particular saddle. Combined with other parameters that control speed and magnitude, a system expressed with an SHC can be modified locally, point by point, without disrupting the rest of the path, supporting their use in motion primitives. However, even more complex trajectory shape modifications are possible. While some combinations can enable a trajectory to better reach into corners, other combinations can rotate, distort and round the trajectory in the region of a corner. In our example, modifying select saddle values produced a 32% decrease in the trajectory error of a complex trajectory produced using this system. This is an effect not visible in previous 1D studies, that can lead to different learnable and tunable representations of dynamic systems.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

In multi-objective optimization problems, the optimization target is to obtain a set of non-dominated solutions. Comparing solution sets is crucial in evaluating the performances of different optimization algorithms. The use of performance indicators is common in comparing those sets and, subsequently, optimization algorithms. A good solution set must be close to the Pareto-optimal front, well-distributed, maximally extended and fully filled. Therefore, an effective performance indicator must encompass these features as a whole and must be Pareto dominance compliant. Unfortunately, some of the known indicators often fail to properly reflect the quality of a solution set or cost a lot to compute. This paper demonstrates that the Degree of Approximation (DOA) quality indicator, is a weakly Pareto compliant unary indicator that gives a good estimation of the match between the approximated front and the Pareto-optimal front. Moreover, DOA computation is easy and fast.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

The real systems are often complex, nonlinear, and noisy in various areas including mathematics, natural science, and social science. We present the symplectic entropy (SymEn) measure as well as an analysis method based on SymEn to estimate the nonlinearity of the complex system by analyzing the given time series. The SymEn estimation is a kind of entropy based on symplectic principal component analysis (SPCA) which represent organized but unpredictable behaviors of systems. The key to SPCA is to preserve the global submanifold geometrical properties of the systems through symplectic transform in the phase space, which is a kind of the measure-preserving transforms. The capability of preserving the global geometrical characteristics makes the SymEn a test statistic to detect the nonlinear characteristics in several typical chaotic time series and the stochastic characteristic in the Gaussian white noise. The results are in agreement with findings in the approximate entropy (ApEn), the sample entropy (SampEn) and the fuzzy entropy (FuzzyEn). Moreover, the SymEn method is also used to analyze the nonlinearities of the real signals (including the EEG signals for ASD and healthy subjects, and the sound and vibration signals for the mechanical systems). The results indicate that the SymEn estimation can be taken as a measure for describing the nonlinear characteristics in the data collected from the natural complex systems.

The article discusses issues related to the optimization of the operation of medium voltage networks, focusing on the optimization of network division points and the selection of the optimal network configuration aimed at reducing power and energy losses. The article provides a critical review of selected scientific works from recent years on the issue of network configuration optimization. The developed solution uses non-deterministic network models and statistical and probabilistic approaches. Optimization studies were carried out using heuristic optimization methods and proprietary algorithms for forecasting the load and power generated from renewable energy sources. The solution proposed in the article has many application possibilities. It can be used to optimize the location of network division points (reducing economic costs related to the modernization of network infrastructure) as well as to optimize the reconfiguration process in order to reduce power losses while maintaining voltage criteria.

Vibration signal analysis is regarded as a fundamental approach in diagnosing faults in rolling bearings, and recent advancements have shown notable progress in this domain. However, the presence of substantial background noise often results in the masking of these fault signals, posing a significant challenge for researchers. In response, an Adaptive Denoising Autoencoder (ADAE) approach is proposed in this paper. The data representations are learned by the encoder through convolutional layers, while the data reconstruction is performed by the decoder using deconvolutional layers. Both the encoder and decoder incorporate adaptive shrinkage units to simulate denoising functions, effectively removing interfering information while preserving sensitive fault features. Additionally, dropout regularization is applied to sparsify the network and prevent overfitting, thereby enhancing the overall expressive power of the model. To further enhance ADAE's noise resistance, shortcut connections are added. Evaluation using publicly available datasets under scenarios with known and unknown noise demonstrates that ADAE effectively enhances the signal-to-noise ratio in strongly noisy backgrounds, facilitating accurate diagnosis of faults in rolling bearings.

Nowadays, microfluidics has become an anarchist interdisciplinary topic with considerable attention in a wide range of biotechnology applications. In this research work, numerical investigation of microfluidic micro-mixer is carried out using hybrid actuation approach with different micropillar shapes and gaps. For this purpose, COMSOL Multiphysics is used with three different physics such as thermoviscous acoustic to solve acoustic governing equations, laminar physics is used to solve fluid flow governing equations and diluted transport species is used to solve mixing governing equations. The simulations were carried out with flow velocity of 200 µm/s at both inlets with an oscillation frequency of 15kHz. The outcomes were in the form of acoustic characteristics such as acoustic pressure, acoustic velocity, acoustic streaming and mixing index. The results revealed that the inclusion of micropillars enhanced the mixing performance and strength of acoustic field resulting in improvement of mixing performance compared to the case without micropillars. In addition, it was also investigated that blade shape micropillars with 0.150 mm gaps deliver best results compared to the other cases with maximum and minimum values of the mixing index 0.95 and 0.72 respectively. The obtained results can be extremely helpful for design and modifications of hybrid microfluidics micro-mixer.

Photovoltaic (PV) technologies are developing rapidly as a result of their ability to reduce energy consumption from conventional sources as well as the growth of global energy expenditures. Nevertheless, several impact categories during the PV panel life cycle occur and some principal sectors are affected. These impact categories are assessed by applying life cycle analysis (LCA) techniques through various software programs, databases and methods. Such analyses of energy technologies are crucial, as they can reveal the occurrence of hazardous emissions at distinct life cycle stages. In the present paper, a PV panel impact assessment through life cycle analysis is carried out. More precisely, a combination of PV technologies—monocrystalline, multicrystalline, copper indium gallium selenide (CIGS), amorphous, and ribbon—is studied. The impact categories of ozone depletion, human toxicity, particulate matter, ionising radiation, photochemical ozone formation, acidification, eutrophication, and ecotoxicity, as well as the sectors of human health, ecosystem quality, and environment, are assessed using the openLCA software, the ecoinvent database, the eco-indicator 99, IMPACT 2002+, ReCiPe, and TRACI methods.

Integrating nanomaterials like carbon nanotubes (CNTs) and iron oxide (Fe₃O₄) into epoxy composites has significant interest due to their potential to enhance mechanical properties. This study evaluates the impact of dispersion quality on the mechanical performance of CNT/Fe₃O₄/Epoxy composites, comparing stirring and sonication methods at three different loadings: 0.1, 0.3, and 0.5 wt.%. Tensile testing revealed that sonicated composites consistently outperformed stirred composites, with a significant increase in elastic modulus and ultimate tensile strength (UTS). However, fracture strain decreased in both composite types compared to pure epoxy, with sonicated composites experiencing a more significant reduction than stirred composites. These results underscore the importance of high-quality dispersion for optimizing mechanical properties.

Fused deposition modeling (FDM) is widely applied in various fields due to its affordability and ease of use. However, it faces challenges such as achieving high surface quality, precise dimensional tolerance and overcoming anisotropic mechanical properties. This paper analyzes and compare the machinability of 3D printed PLA, PETG and carbon fiber reinforced PETG focusing on surface roughness and burr formation. A design of experiments (DoE) with a full factorial design was used, considering three factors: rotation speed, feed rate and depth of cut. Each factor had different levels: rotational speed at 3000, 5500 and 8000 rpm; feed rate at 400, 600 and 800 mm/min; and depth of cut at 0.2, 0.4, 0.6, and 0.8 mm. Machinability was evaluated by roughness and burr height using a profilometer for all the materials under the same milling conditions. To evaluate the statistical significance of the influence of various processing parameters on surface roughness and burr formation in 3D printed components made of three different materials PLA, PETG and carbon fiber reinforced PETG, an analysis of variance (ANOVA) test was conducted. This analysis investigated whether variations in rotational speed, feed rate and depth of cut resulted in measurable and significant differences in machinability results. Results showed that milling parameters significantly affect roughness and burr formation, with optimal conditions for minimizing any misalignment highlighting the trade-offs in parameter selection. These results provide insights into the post-processing of FDM-printed materials with milling, indicating the need for a balanced approach to parameter selection based on application-specific requirements.

Day by day, the share of renewable energy-based power plants such as offshore wind farms and photovoltaic power plants, in the present-day power systems is escalating. Nevertheless, most of these power-producing facilities have been located quite far away from the load centers. At this stage, HVDC power systems provide satisfactory options due to qualities such as reduced line losses, substantial controllability, and environmental advantages. Nevertheless, unique converter designs are required to combine asynchronous HVDC networks with each other and with already existing high voltage alternating current (HVAC) networks. In this study, based on the above special cases, a unique DC-DC modular multilevel converter (MMC) architecture is presented that provides an excellent solution for both integrating modern asynchronous HVDC networks and integrating these modern HVDC power systems with existing asynchronous HVAC power systems. The mathematical analysis of the recommended DC-DC MMC design has been examined in detail and the power transfer between two asynchronous power grids has been realized in a simulation environment. Efficient bilateral power transmission has been made achievable by the control system. The recommended DC-DC MMC topology has shown to be a highly successful approach, in the interconnection of HVDC power systems, according to the simulation results.

Some optimal control problems need metaheuristics in searching for the optimal solution, especially when the process has certain characteristics like the Photobioreactor for Algae Growth (distributed parameter, nonlinearities, etc.). Particle Swarm Optimization (PSO) algorithms within control structures are a realistic approach; their task is often to predict the optimal control values working with a process model (PM). Owing to numerous numerical integrations, there is a big computational effort that is reflected in a large controller execution time. The authors propose to replace the PSO predictor with a machine learning model that has “learned” the quasi-optimal behavior of the couple (PSO, PM); the training data is obtained through closed-loop simulations over the control horizon. The new controller should preserve the process’s quasi-optimal control. In identical conditions, the process evolutions must also be quasi-optimal. The multiple Linear Regression and the Regression Neural Networks were considered as predicting models. The paper first proposes algorithms for collecting and aggregating data sets for the learning process. Algorithms for constructing the machine learning models, implementing the controllers, and closed-loop simulations are also proposed. The simulations prove that the two machine learning predictors have learned the PSO predictor’s behavior such that the process evolves almost identically. The resulting controllers’ execution time drastically decreased while keeping their optimality.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. In contemporary times, the transition from conventional electricity grids to Smart Grids constitutes an area where extensive research is conducted on a global scale. Among the research challenges, the investigation of Deep Transfer Learning (DTL) in the field of electricity load forecasting represents a fundamental effort that imparts generality to Artificial Intelligence applications, due to new capabilities, such as knowledge transfer and computational power reduction. In this paper a comprehensive study is conducted for day-ahead electricity load forecasting. For this purpose, three Sequence-to-Sequence (Seq2seq) Deep Learning (DL) models are used, namely the Multilayer Perceptron (MLP), the Convolutional Neural Network (CNN) and the Ensemble Learning Model (ELM), which is consisted of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL and emphasizing the way the datasets are trained and fine-tuning for higher forecasting accuracy. In order to implement the forecasting strategies using Deep Learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1-24 hours) for each month of the year for Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. After several trials, four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) contains the training of the DL models using Lesvos dataset, and the testing period performed directly on the Chios dataset without fine-tuning. The fourth strategy is a Multi-task Deep Learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. In this paper, we explore the performance of DTL and compare the results with those produced with MTDL. The results demonstrated that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, the two cases with fine-tuning (DTL Case 1 and 2) outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it has been concluded that the MLP model presents best monthly forecasts with a MAPE of 6.24% and 6.01% for the first two cases, the CNN model presents best monthly forecasts with a MAPE of 5.57% and 5.60% respectively and the ELM model achieves best monthly forecasts with a MAPE of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

This paper investigates the feasibility of a backend design for real-time, multiple-channel processing digital phased array system, particularly for high-performance embedded computing platforms constructed of using general purpose digital signal processors. Frist, we obtained the lab-scale backend performance benchmark from simulating beamforming, pulse compression, and Doppler filtering based on MicroTCA chassis using Serial RapidIO protocol in backplane communication. Next, a field-scale demonstrator of a multifunctional phased array radar is emulated by using the similar configuration. Interestingly, the performance of a barebone design is compared to that of emerging tools that systematically take advantage of parallelism and multicore capabilities, including Open Computing Language.

Abstract This study delved into the application of various machine learning (ML) models for the classification of lung cancer levels. Through meticulous monitoring of parameters such as minimum child weight and learning rate, efforts were made to mitigate overfitting while optimizing model performance. The Deep Neural Network (DNN) emerged as a standout performer, showcasing robust performance across training, validation, and testing stages. Ensemble methods like voting and bagging also demonstrated promising results. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges in achieving satisfactory performance. Overall, the investigation sheds light on the efficacy of different ML models in lung cancer level classification and underscores the importance of parameter tuning to address overfitting concerns.

In response to the burgeoning global demand for premium agricultural products, particularly within the competitive nut market, this paper introduces an innovative methodology aimed at enhancing the grading process for almonds and their shells. Leveraging state-of-the-art Deep Convolutional Neural Networks (CNNs), specifically the AlmondNet-20 architecture, our study achieves exceptional accuracy exceeding 99%, facilitated by the utilization of a 20-layer CNN model. To bolster robustness in differentiating between almonds and shells, data augmentation techniques are employed, ensuring the reliability and accuracy of our classification system. Our model, meticulously trained over 1000 epochs, demonstrates remarkable performance, boasting an accuracy rate of 99% alongside a minimal loss function of 0.0567. Rigorous evaluation through test datasets further validates the efficacy of our approach, revealing impeccable precision, recall, and F1-score metrics for almond detection. Beyond its technical prowess, this advanced classification system offers tangible benefits to both industry experts and non-specialists alike, ensuring globally reliable almond classification. The application of deep learning algorithms, as showcased in our study, not only enhances grading accuracy but also presents opportunities for product patents, thereby contributing to the economic value of our nation. Through the adoption of cutting-edge technologies such as the AlmondNet-20 model, we pave the way for future advancements in agricultural product classification, ultimately enriching global trade and economic prosperity.

Previous control methods developed by our research team cannot satisfy the high-accuracy requirements of unmanned surface vessel (USV) path-tracking during bathymetric mapping because of the excessive overshoot and slow convergence speed. For this reason, this study developed an adaptive fuzzy integral-derivative line-of-sight (AFIDLOS) guidance law for USV path-tracking control. Integral and derivative terms were added to counteract the effect of the sideslip angle, with which the USV could be quickly guided to converge to the planned path for bathymetric mapping. To obtain a high-accuracy of the look-ahead distance, a fuzzy control method was proposed. The proposed method was verified using simulations and outdoor experiments. The results demonstrate that the AFIDLOS guidance law can reduce the overshoot by 79.85%, shorten the settling time by 55.32% in simulation experiments, and reduce the average cross-track error by 10.91%, and can ensure a 30% overlap of neighboring strips of bathymetric LiDAR outdoor mapping when compared with the traditional method.

As technology advances, the field of electrical and computer engineering continuously demands the introduction of innovative new tools and methodologies to facilitate effective learning and comprehension of fundamental concepts. This research addresses an identified gap in technology-augmented education capabilities and researches the integration of Virtual Reality (VR) technology with real-time electronic circuit simulation to enable and enhance the visualization of non-observable concepts such as voltage distribution and current flow within these circuits. In this paper, we describe the development of our immersive educational platform, which makes understanding these abstract concepts intuitive and engaging. This research also involved the design and development of a VR-based circuit simulation environment. By leveraging VR’s immersive capabilities, our system enables users to physically interact with electronic components, observe the flow of electrical signals, and manipulate circuit parameters in real-time. Through this immersive experience, learners can gain a deeper understanding of fundamental electronic principles, transcending the limitations of traditional two-dimensional diagrams and equations. Furthermore, this research focuses on the implementation of advanced and novel visualization techniques within the VR environment for non-observable electrical and electromagnetic properties, providing users with a clearer and more intuitive understanding of electrical circuit concepts. Examples include color-coded pathways for current flow and dynamic voltage gradient visualization. Additionally, real-time data representation and graphical overlays are researched and integrated to offer users insights into the dynamic behavior of circuits, allowing for better analysis and troubleshooting.

In this paper, the feasibility and potential assessment (PA) of wind power in six different areas MehalMeda, Eneware, DebreBerhan, AlemKetema, GundoMekel, and Majet are investigated. The data is collected from the National Metrological Agency (NMA) in Addis Ababa and from the districts of the case study areas and analyzed using MATLAB and HOMER software. Using the data collected at 10 meter height, wind direction using a wind rose, the wind frequency distribution, and wind turbine characteristics have been analyzed. Moreover, to obtain a more realistic wind potential study, the wind speed at a 10 meter height is extrapolated to a height of 50 meter in order to determine wind speed, wind power density, and wind energy density. The average wind speed of the zone at 10m and 50m heights are 1.58 m/s and 1.99 m/s, 3.06 m/s and 3.85 m/s, 4.75 m/s and 5.98 m/s, 2.29 m/s and 2.88 m/s, 1.01 m/s and 1.27 m/s and 4.07 and 5.12m/s at Alemketema, Debreberhan, Eneware, Gundemeskel, Majete and Mehalmeda respectively. The extrapolated result shows that the maximum wind speed and power densities at a height of 50 meter for Eneware, MehalMeda and Debre Berhan are 10.4 m/s, 689 W/m2, 8.9m/s, 429 W/m2 and 6.3m/s, 152.2 W/m2 respectively. The energy densities at a height of 50 meter for AlemKetema, DebreBerhan, Eneware, GundoMekel, Majete, and MehalMeda are 181.06 kWh/m2*yr , 1332.83 kWh/ m2*yr, 6078.91 kWh/ m2*yr, 857.76 kWh/ m2*yr, 58.78 kWh/ m2*yr, and 3939.42 kWh/ m2*yr respectively. As per the international standard for wind power and wind speed classification, considering the extrapolated height, Eneware, MehalMeda, and DebreBerhan have feasible wind potential for both small-scale and large-scale wind farm implementation, whereas Majete, AlemKetema, and GundoMeskel of the North Shewa Zone in the Amhara region have poor wind potential.

Reasonable allocation of production plans and saving the overall electricity cost are crucial for large manufacturing conglomerates, which is an effective way for conglomerates to realize open-source and cost-saving. This paper develops an optimization model of off-site industrial production scheduling for enterprises in response to the problems of high electricity costs due to the irrational allocation of production schedules on the demand side of China's electric power and the difficulty of promoting industrial and commercial distributed photovoltaic (PV) projects in China. The model makes full use of the conditions of different PV resources and different electricity prices in different places to optimize the scheduling of industrial production in different places. The model is embedded with two sub-models of the electricity price prediction model and distributed photovoltaic kWh cost model to complete the model parameters, in which the electricity price prediction model utilizes the LSTM neural network. The integrated model is then solved by the particle swarm algorithm. To verify the effectiveness of the model in solving the problem of off-site production scheduling on the demand side of electricity, the research team researched two off-site pharmaceutical factories belonging to the same large pharmaceutical company. Finally, the research data were substituted into the model for solving, and it was concluded that the optimization model could significantly reduce the cost of electricity consumption of the enterprise by about 7.9 %.

In the dynamic landscape of modern education, characterized by an increasingly active involvement of IT technologies in learning, the imperative to transfer to students the skills necessary to integrate Artificial Intelligence (AI) into the process represents an important goal. This paper presents a novel framework for knowledge transfer, diverging from traditional programming language-centric approaches by integrating PSoC 6 microcontroller technology. This framework establishes a cyclical learning cycle encompassing theoretical fundamentals and practical experimentation, fostering AI literacy at the edge. Through a structured combination of theoretical instruction and hands-on experimentation, students develop proficiency in understanding and harnessing AI capabilities. Emphasizing critical thinking, problem-solving, and creativity, this approach equips students with the tools to navigate the complexities of real-world AI applications effectively. By leveraging PSoC 6 as an educational tool, a new generation of individuals is efficiently cultivated with essential AI skills. These individuals are adept at leveraging AI technologies to address societal challenges and drive innovation, thereby contributing to long-term sustainability initiatives. Specific strategies for experiential learning, curriculum recommendations, and results of knowledge application are presented, aimed at preparing students to excel in a future where AI will be omnipresent and indispensable.

As with many of the non-deterministic search algorithms, particularly those are analogous to complex biological systems, there are a number of inherent difficulties, and the Bees Algorithm (BA) is no exception. Basic versions and variations of the BA have their own drawbacks. Some of these drawbacks are a large number of parameters to be set, lack of methodology for parameter setting and computational complexity. This paper describes a Grouped version of the Bees Algorithm (GBA) addressing these issues. Unlike its conventional version, in this algorithm bees are grouped to search different sites with different neighbourhood sizes rather than just discovering two types of sites, namely elite and selected. Following a description of the GBA, the results gained for 12 benchmark functions are presented and compared with those of the basic BA, enhanced BA, standard BA and modified BA to demonstrate the efficacy of the proposed algorithm. Compared to the conventional implementations of the BA, the proposed version requires setting of fewer parameters, while producing the optimum solutions much faster.