The lithium-ion batteries are widely used as a power source for portable devices, including cell phones. The useful life is about 2 years or 500 cycles, contributing to the generation of waste from electrical and electronic equipment (WEEE). Mining of lithium and cobalt damages the environment and is onerous; therefore, sustainable alternatives, such as obtaining these elements from secondary sources as recycling of lithium-ion batteries, are essential to provide the inputs used in the sector. However, the metallurgical route which will used to recovering them must be considered, due to this work aims for a more environmentally favorable process using DL-malic acid 1.5 M and instead of compared with sulfuric acid 2 M, heat pretreatment of 1 h and 3 h, and for all conditions, experiments were carried out with and without adding the oxidizing agent hydrogen peroxide. The best yields occurred in presence of H2O2 10 % v/v, and heat pretreatment of 1 h: 33.49 % Co and 4.63 % Li, and 29.78 % Co e 3.44 % Li were recovered by sulfuric acid and DL-malic acid, respectively.

Day-ahead forecasting of electricity prices is important in deregulated electricity markets for all the stakeholders: energy wholesalers, traders, retailers, and consumers. Electricity price forecasting is an inherently difficult problem due to its special characteristic of dynamicity and non-stationarity. In this paper, we present a robust price forecasting mechanism that shows resilience towards aggregate demand response effect and provides highly accurate forecasted electricity prices to the stakeholders in a dynamic environment. We employ an ensemble prediction model in which a group of different algorithms participate in predicting the price for each hour of a day. We propose two different strategies, namely, Fixed Weight Method (FWM) and Varying Weight Method (VWM), for selecting each hour's expert algorithm from the set of participating algorithms. In addition, we utilize a carefully engineered set of features selected from a pool of features derived from information such as past electricity price data, weather data, and calendar data. The proposed ensemble model offers better results than both the Pattern Sequence-based Forecasting (PSF) method and our own previous work using Artificial Neural Networks (ANN) alone do on the datasets for New York, Australian, and Spanish electricity markets.

Epithelial–mesenchymal transition (EMT) is defined as a cellular process during which epithelial cells acquire mesenchymal phenotypes and behavior following the downregulation of epithelial features. EMT and its reversed process, the mesenchymal-epithelial transition (MET), and the special form of EMT, the endothelial-mesenchymal transition (EndMT), have been thought as a universal dogma controlling developmental and pathological processes. More than half a century of EMT study has made it a large research field and a mainstream concept. However, discrepancies and disputes over EMT and EMT research have also grown over time. Particularly, neither the epithelial and mesenchymal states/properties nor their regulatory networks nor specific markers have been defined, rendering the EMT, MET and EndMT concepts groundless. Moreover, EMT and MET effects should not be a cause, but rather a consequence of or an accompanying effect during developmental and pathological processes. EMT and MET represented by the change in cell shapes or adhesiveness or symbolized by EMT factors are biased interpretation of the overall change in cellular property and regulatory networks during development and cancer progression. The true meaning of EMT effects in some developmental and pathological processes, such as fibrosis, needs re-evaluation. But the core EMT factors are actually a few components of the regulatory networks of neural stemness, which determines tumorigenicity and pluripotency. The EMT effects in cancer progression and neural crest formation are wrong attribution of the role of neural stemness during cancer progression and the cell-intrinsic property of neural crest cells to the unknown mesenchymal state. It is time to reassess the significance of EMT and its related concepts in scientific research.

Flavonoids are secondary plant metabolites involved in biological activity that are present in plentiful proportions in many plant origin foods and beverages. Owing to their chemical difference and qualities that make them beneficial for human health, they have received a lot of focus in research. This review therefore presents an account on the chemical structure of flavonoids, food sources and their metabolism with emphasis on bioavailability. And they also examine their antioxidant, anti-inflammatory, anticancer, cardiovascular protective, neuroprotective, and antimicrobial properties and reveal related molecular processes. In addition, it overviews the clinical data concerning their possible use in the prevention and treatment of chronic diseases. Some of the problems that attend current flavonoid research are also dealt with; such issues as variation in the bioactivity of flavonoids and scarcity of clinical studies. This review is designed to present current state of knowledge and to provoke further research concerning the further potential of flavonoids in enhancing human health.

Solanum indicum Linn, is commonly known as Indian Nightshade or Poison Berry belongs to the family Solanaceae. This review studied the botanical description, traditional uses of its seeds, its chemical composition, pharmacological properties and modern applications in medicinal system. The plant is rich in alkaloids, steroidal saponins, flavonoids and phenolic acids having diverse pharmacological activities and phytochemical profile. It is used in treatment of various respiratory disorders, inflammation, skin problems and gastrointestinal disease since ancient times. Scientific research in modern times also tested many of the traditional uses revealing anti-inflammatory, antioxidant, antimicrobial activities as well as some cytotoxic and even antidiabetic effects. These pharmacological activities show potential future as uses for organic drugs, natural health products, skincare formulations and agricultural advancements.

Model selection and model averaging have been the popular approaches in handling modelling uncertainties. Fan and Li(2006) laid out a unified frame work for variable selection via penalized likelihood. The tuning parameter selection is vital in the optimization problem for the penalized estimators in achieving consistent selection and optimal estimation. Since the OLSpost-LASSO estimator by Belloni and Chernozhukov (2013), few studies have focused on the finite sample performances of the class of OLS post-penalty estimators with the tuning parameter choice determined by different tuning parameter selection approaches. We aim to supplement the existing model selection literature by studying such a class of OLS post-selection estimators. Inspired by the Shrinkage Averaging Estimator (SAE) by Schomaker(2012) and the Mallows Model Averaging (MMA) criterion by Hansen (2007), we further propose a Shrinkage Mallows Model Averaging (SMMA) estimator for averaging high dimensional sparse models. Based on the Monte Carlo design by Wang et al. (2009) which features an expanding sparse parameter space as the sample size increases, our Monte Carlo design further considers the effect of the effective sample size and the degree of model sparsity on the finite sample performances of model selection and model averaging estimators. From our data examples, we find that the OLS post-SCAD(BIC) estimator in finite sample outperforms most of the current penalized least squares estimators as long as the number of parameters does not exceed the sample size. In addition, the SMMA performs better given sparser models. This supports the use of the SMMA estimator when averaging high dimensional sparse models.

Background: Bayesian Network (BN) modeling is a prominent methodology in computational systems biology. However, the incommensurability of datasets fre- quently encountered in life science domains gives rise to contextual dependence and numerical irregularities in the behavior of model selection criteria (such as MDL, Minimum Description Length) used in BN reconstruction. This renders model features, first and foremost dependency strengths, incomparable and diffi- cult to interpret. In this study, we derive and evaluate a model selection principle that addresses these problems. Results: The objective of the study is attained by (i) approaching model eval- uation as a classification problem, (ii) estimating the effect that sampling error has on the satisfiability of conditional independence criterion, as reflected by Mutual Information, and (iii) utilizing this error estimate to penalize uncertainty with the novel Minimum Uncertainty (MU) model selection principle. We vali- date our findings numerically and demonstrate the performance advantages of the MU criterion. Finally, we illustrate the advantages of the new model evaluation framework on real data examples. Conclusions: The new BN model selection principle successfully overcomes per- formance irregularities observed with MDL, offers a superior average convergence rate in BN reconstruction, and improves the interpretability and universality of resulting BNs, thus enabling direct inter-BN comparisons and evaluations.

Background: The genetic variants identified by three large genome-wide association studies (GWAS) of educational attainment were used to test a polygenic selection model. Methods: Average frequencies of alleles with positive effect (polygenic scores or PS) were compared across populations (N=26) using data from 1000 Genomes. A null model was created using frequencies of random SNPs. Results: Polygenic selection signal of educational attainment GWAS hits is high among a handful of SNPs within genomic regions replicated across GWAS publications. A polygenic score comprising 9 SNPs predicts population IQ (r=0.88), outperforming 99% of the polygenic scores obtained from sets of random SNPs (Monte Carlo p= 0.011). Its predictive power remains unaffected after controlling for spatial autocorrelation (Beta= 0.83). The largest polygenic score (161 SNPs) exhibits similar predictive power (Beta=0.8). Random polygenic scores are moderate predictors of population IQ (thanks to spatial autocorrelation), and their predictive power increases logarithmically with the number of SNPs, indicating an exponential reduction in noise. Conclusion: This study provides guidance for using GWAS hits together with random SNPs for testing polygenic selection using Monte Carlo simulations.

Waste management is an unavoidable technological operation in the process of raw material extraction. The main characteristic of this technological operation is the handling of large quantities of waste material, which can amount to several hundred million cubic metres. Working with this amount of material usually requires high-capacity systems for excavation and loading, a large fleet of trucks for haulage, construction, and maintenance of a complex roads network, use of a significant area of land in order to achieve the required capacities, etc. At the same time, this operation must comply with all administrative and environmental standards. Therefore, optimising waste rock management (particularly haulage and dumping) has the potential to significantly improve the overall value of the project. This paper presents a hybrid model for the optimisation of waste dump design and site selection. The model is based on different mathematical methods (genetic algorithm, analytic hierarchy process and heuristic methods) adapted to different aspects of the problem. The main objective of the model is to provide a solution (in analytical and graphical form) for the draft waste dump design, on the basis of which the final waste dump design can be defined.

Shark unprovoked attacks consist of fatal and non-fatal cases. Numerous cases have been reported involving shark species from Carcharhinus melanopterus with length of 145.5 cm to half-ton Carcharodon carcharias. Currently there are more (P < 0.05) unprovoked non-fatal cases with the average is 28.46 cases/shark species (95%CI: 3.86-53.1) than unprovoked fatal cases, which the average is 5.12 cases /shark species (95%CI: -0.075-10.3). Hence this paper seeks to select the best shark size model that correlates with the unprovoked fatal and non-fatal cases. The studied sharks consist of 24 shark species with the average length is 268.18 cm (95%CI: 230-306 cm) and the average weight is 225.42 kg (95%CI: 128-323 kg). Based on the model and as described by low values of AIC and the highest values of R² and adjusted R² , shark weight followed by combinations of shark weight and length produced unprovoked fatal and non-fatal cases best models. The model for explaining unprovoked fatal cases is the shark weight with high numbers of cases observed in large size shark (weight⁓fatal cases, AIC = 165.359, R² = 0.72, Adj. R = 0.71). While for non-fatal cases, the best model is also the shark weight (weight⁓non fatal cases, AIC = 246.93, R² = 0.63, Adj. R = 0.59).

In recent times, voice assistants have become a part of our day-to-day lives, allowing information retrieval by voice synthesis, voice recognition, and natural language processing. These voice assistants can be found in many modern-day devices such as Apple, Amazon, Google, and Samsung. This project is primarily focused on Virtual Assistance in Natural Language Processing. Natural Language Processing is a form of AI that helps machines understand people and create feedback loops. This project will use deep learning to create a Voice Recognizer and use Commonvoice and data collected from the local community for model training using Google Colaboratory. After recognizing a command, the AI assistant will be able to perform the most suitable actions and then give a response. The motivation for this project comes from the race and gender bias that exists in many virtual assistants. The computer industry is primarily dominated by the male gender, and because of this, many of the products produced do not regard women. This bias has an impact on natural language processing. This project will be utilizing various open-source projects to implement machine learning algorithms and train the assistant algorithm to recognize different types of voices, accents, and dialects. Through this project, the goal to use voice data from underrepresented groups to build a voice assistant that can recognize voices regardless of gender, race, or accent. Increasing the representation of women in the computer industry is important for the future of the industry. By representing women in the initial study of voice assistants, it can be shown that females play a vital role in the development of this technology. In line with related work, this project will use first-hand data from the college population and middle-aged adults to train voice assistants to combat gender bias.

In this work we looked for a stable and accurate procedure to perform feature selection in datasets with a much higher number of predictors than individuals, as in Genome-Wide Association Studies. Due to the instability in feature selection when many potential predictors are measured, a variable selection procedure is proposed that combines several replications of shrinkage regression models. A weighted formulation is used to define the final predictors. The procedure is applied to investigate Single Nucleotide Polymorphisms (SNPs) predictors associated to Alzheimer’s disease in the Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset. Two data scenarios are investigated: one considering only the set of SNPs and another with the covariates age, sex, educational level and APOE4 genotype. The SNP rs2075650 and the APOE4 genotype are given as risk factors for AD, which is in line with the literature, and other four new SNPs are pointed, opening new hypotheses for in vivo analyses. These experiments demonstrate the potential of the new method for stable feature selection.

In recent times, using image-based deep learning techniques has been very useful for classifying fruits. However, mango is a particular challenge because its shelf life is directly related to the degree of maturity at the time of harvest, which is determined mainly through the visual assessment of the operators when sorting them, doing it incorrectly, coupled with the blows and compressions exposed during storage and transport, trigger the deterioration in their quality, hence the importance of this operation. In this sense, the purpose of this study focuses on designing a computational model based on Deep Learning that uses a convolutional neural network (CNN) parameterized to select mangoes according to their color tone based on their maturity stage. A dataset was established from 201 labeled images, then a CNN architecture was built, obtaining a model on which 3 criteria were evaluated: the number of convolution and grouping layers, the resolution of the input images and the number of training epochs required. As a result, an input image resolution of 32 x 32 pixels was achieved, the process included a convolution layer followed by pooling that fed another layer that processed the results and ended in an output layer with 2 neurons under the One Hot Encoding representation. The model required 20 epochs to perfect its training, achieving 96.04 % accuracy in mango image selection. This study supports the potential of CNNs in quality analysis through mango color selection, even in uncertainty scenarios.

This paper proposes a model to evaluate business projects to get into an incubator, allowing to rank them in order of selection priority. The model combines the Momentum method to build prospective scenarios and the Multiple Criteria Decision Making (MCDM) method TOPSIS-2N to rank the alternatives. Six business projects were evaluated to be incubated. The Momentum method made it possible for us to create an initial core of criteria for the evaluation of incubation projects. The TOPSIS-2N method supported the decision to choose the company to be incubated by ranking the alternatives in order of relevance. Our evaluation model has improved the existing models used by incubators. This model can be used and / or adapted by any incubator to evaluate the business projects to be incubated. The set of criteria for the evaluation of incubation projects is original and the use of prospective scenarios with a MCDM method to evaluate companies to be incubated does not exist in the literature.

Traditional classroom teaching model can no longer meet the needs of students' ability development. As a new model actively advocated in the modern education concept, personalized teaching focuses on the development needs of students and emphasizes respect for students' individualized growth. In this work, we utilize deep learning method to recommend teaching strategies for different features of students. Specifically, the proposed method includes the construction of a multi-layer neural network model, which can analyze students' multi-dimensional learning data and behavior patterns, so as to recommend the most suitable teaching strategies for individual students. Through data collection and preprocessing, model architecture design, model training and optimization, the model gradually improves the accuracy of prediction and recommendation. Experimental analysis verifies the effectiveness of the model through field teaching experiments, and the results show that the personalized teaching strategy based on deep learning can significantly improve the learning effect and participation of students.

Background: Alfalfa, the most economically important forage legume worldwide, features modest genetic progress due to long selection cycles and large extent of non-additive genetic variance associated with its autotetraploid genome. Methods: To improve the efficiency of genomic selection in alfalfa, we explored the effects of genome parametrization (as autotetraploid and diploid dosage, plus allele ratios) and SNP marker subsetting (all available SNPs; only genic regions; only non-genic regions) on genomic regressions, together with various levels of filtering on reading depth and missing rates. We used Genotyping by Sequencing-generated data and focused on traits of different genetic complexity, i.e., dry biomass yield in moisture-favorable (FE) and drought stress (SE) environments, leaf size, and onset of flowering, assessed on 143 genotyped plants from a genetically-broad European reference population and their phenotyped half-sib progenies. Results: On average, allele ratio improved the predictive ability compared with other genome parametrizations (+7.9% vs. tetraploid dosage, +12.6% vs. diploid dosage), SNP subsetting offered an advantage compared with any tested subsettings (+3.7% vs. genic regions, +7.6% vs. non-genic regions). However, when focusing on specific traits, different combinations of genome parametrization and subsetting reached better performances. We also released Legpipe2, a SNP calling pipeline tailored for reduced representation (GBS, RAD) medium-sized genotyping experiments.

Despite Low Power Wide Area Networks’ ability to offer an extended range, it might still encounter challenges with coverage blind spots in the network. This article proposes an innovative energy-efficient nature-inspired relay selection algorithm for LoRa-based LPWAN networks, serving as a solution for challenges related to poor signal range in areas with limited coverage. A behavior swarm-inspired approach has been utilized to select the relays’ localization in the network, providing network energy efficiency and radio signal extension. These relays help bridge communication gaps, significantly reducing the impact of coverage blind spots by forwarding signals from devices with poor direct connectivity with the gateway. The proposed algorithm considers critical factors for the LoRa standard, such as the Spreading Factor or device energy budget analysis. The simulation experiments validate the proposed scheme’s effectiveness in terms of energy efficiency under diverse multi-gateway topology scenarios involving thousands of devices. Specifically, it has been verified that the proposed approach outperforms the reference method in preventing the battery depletion of relays, which is vital for battery-powered IoT devices. Furthermore, for some large-scale problems, the proposed heuristic method achieves over twice the speed of the exact method with a negligible accuracy loss of less than 2%.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research towards the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we introduce a set of metrics considering both quantitative and qualitative aspects of the road network. Compared to traditional neural networks, our HAN model demonstrates superior accuracy and F1-score, particularly for road types with comparable samples. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.

Determining accurate PM2.5 pollution concentrations and understanding their dynamic patterns is crucial for scientifically informed air pollution control strategies. Traditional reliance on linear correlation coefficients for ascertaining PM2.5 related factors only uncovers superficial relationships. Moreover, the invariance of conventional prediction models restricts their accuracy. To enhance the precision of PM2.5 concentration prediction, this study introduces a novel integrated model that leverages feature selection and a clustering algorithm. Comprising three components - feature selection, clustering, and integrated prediction, the model first employs the non-dominated sorting Genetic Algorithm (NSGA-III) to identify the most impactful features affecting PM2.5 concentration within air pollutants and meteorological factors. This step offers more valuable feature data for subsequent modules. The model then adopts a two-layer clustering method (SOM+K-means) to analyze the multifaceted irregularity within the dataset. Finally, the model establishes the Extreme Learning Machine (ELM) weak learner for each classification, integrating multiple weak learners using the Adaboost algorithm to obtain a comprehensive prediction model. Through feature correlation enhancement, data irregularity exploration, and model adaptability improvement, the proposed model significantly enhances the overall prediction performance. Data sourced from 12 Beijing-based monitoring sites in 2016 were utilized for an empirical study, and the model's results compared with five other predictive models. The outcomes demonstrate that the proposed model significantly heightens prediction accuracy, offering useful insights and potential for broadened application to multifactor correlation concentration prediction methodologies for other pollutants.

Malaria remains an important cause of death, especially in sub-Saharan Africa with about 228 million malaria cases worldwide and an estimated 405,000 deaths in 2019. Currently, malaria is diagnosed in the health facility using a microscope (BS) or rapid malaria diagnostic test (MRDT) and with area where these tools are inadequate the presumptive treatment is performed. Apart from that self-diagnosis and treatment is also practiced in some of the households. With the high-rate self-medication on malaria drugs, this study aimed at computing the most significant features using feature selection methods for best prediction of malaria in Tanzania that can be used in developing a machine learning model for malaria diagnosis. A malaria symptoms and clinical diagnosis dataset were extracted from patients’ files from four (4) identified health facilities in the regions of Kilimanjaro and Morogoro. These regions were selected to represent the high endemic areas (Morogoro) and low endemic areas (Kilimanjaro) in the country. The dataset contained 2556 instances and 36 variables. The random forest classifier a tree based was used to select the most important features for malaria prediction. Regional based features were obtained to facilitate accurate prediction. The feature ranking as indicated that fever is universally the most influential feature for predicting malaria followed by general body malaise, vomiting and headache. However, these features are ranked differently across the regional datasets. Subsequently, six predictive models, using important features selected by feature selection method, were used to evaluate the features performance. The features identified complies with malaria diagnosis and treatment guideline provided with WHO and Tanzania Mainland. The compliance is observed so as to produce a prediction model that will fit in the current health care provision system in Tanzania.

In the software development process, the decision-maker (DM) has a range of problems inherent to its function. Wrong choices during software planning can bring great risk to the project. Therefore, the planning of software releases to be delivered to the customer should be well done. This is not an easy task because releases are made up of many requirements that contain complex variables that must be considered, such as precedence, cost, requirement stability, among other features that make the requirements-selection process challenging. To make this process less exhaustive, DM can use tools that facilitate this work. In software engineering, we can find fields of research specialists in this context, such as Search-Based Software Engineering (SBSE). The SBSE makes use of advanced metaheuristics to search for optimal solutions or the closest to it. In this work, we try to use another field of research to solve this same problem type, the Verbal Decision Analysis (VDA). To do this, we elaborate a workflow that will use the same source data, execute two solutions using the two search fields (SBSE and VDA) and compare the results. In the end, we evaluated and commented on the results.

Feature selection is predominantly used in machine learning tasks, such as classification and regression. It selects a subset of features (relevant attributes of data points) from a larger set that contributes as optimally as possible to the informativeness of the model. There are exponentially many subsets of a given set, and thus, the exhaustive search is only practical for problems with at most a few dozen features. In the past, there have been attempts to reduce the search space using dynamic programming. However, models that consider similarity in pairs of features besides the quality of individual features do not provide the required optimal substructure. As a result, algorithms, which we will call suboptimal dynamic programming algorithms, find a solution that may deviate significantly from the optimal one. In this paper, we propose a dynamic programming algorithm with an iterative upgrade where the order of feature processing is inverted in each iteration. Such an alternating approach allows for improving the optimization function by using the score from the previous iteration to estimate the contribution of unprocessed features. The iterative process is proven to converge and terminate when the solution does not change in three successive iterations or when the number of iterations reaches the threshold. Results in more than 90 % of tests align with those of the exhaustive search, being competitive and often superior to the reference greedy approach. The validation was done by comparing the scores of output feature subsets and examining the accuracy of different classifiers learned on these features. In the context of feature selection, the proposed algorithm can be characterized as a filter method. However, we expect that the idea of alternating suboptimal optimization will soon be generalized to tasks beyond feature selection.

This study explores the complexities of sport manager selection, investigating the impact of affirmative action, recruitment strategies, organizational culture, diversity initiatives in board selection, and career advancement insights from coaches' perspectives. To conduct this investigation, a purposive sampling technique was employed, selecting 65 prominent sports managers and coaches from Romania. Participants, aged between 35 to 58 years old, boasted an average of 10 to 20 years of sports experience and were chosen based on specific criteria, including academic qualifications. Data collection occurred over an extended period, spanning from fall 2022 to spring 2024, through semi-structured interviews with sport managers and coaches. The findings unveiled persistent challenges in effectively implementing affirmative action measures, as sport managers grapple with balancing the promotion of deserving candidates while maintaining continuity in board culture. Achieving meaningful diversity necessitates nuanced approaches that consider both candidate quality and cultural compatibility. Moreover, the study sheds light on coaches' perspectives when considering executive council positions, highlighting various pathways to career advancement. Recruitment practices prioritized informal methods, emphasizing board cohesion. Despite the recognized importance of diversity, challenges persist in selecting candidates solely based on demographic representation. The study provides valuable insights into promoting diversity and inclusivity within sports organizations' executive councils. Future research directions may include exploring longitudinal trends and delving into the qualitative experiences of underrepresented groups, with the aim of advancing understanding and promoting equity within sports organizations.

High dimensional datasets are highly likely to have redundant, irrelevant, and noisy features that negatively affect the performance of the classification algorithms. Selecting the most relevant features and reducing the dimensions of datasets by removing the undesired features is a dimensional reduction technique called Feature Selection (FS). In this paper, we propose an FS approach based on the Black Hole Algorithms (BHO) with a mutation technique called MBHO. Generally, BHO contains two major phases. At the exploitation phase, a set of stars are modified based on some rule and according to some objective function, the best star is selected as the black hole which attracts other stars. Furthermore, when a star gets closer to the event horizon, it will be swallowed and a new one will be randomly generated in the search space which thus is the exploration phase. However, randomness may cause the algorithm to fall into the trap of local optima, and to overcome such complications, inversion mutation is used. Furthermore, we modify a widely utilized objective function in most of the proposed works for wrapper feature selection by combining two new terms that are based on the correlation among the selected subset of features and the features and the classification label. We also utilize a transfer function, known as the V2 transfer function, to convert continuous values into discrete ones to enhance search. We assess our approach via extensive evaluation experiments using fourteen benchmark datasets. We benchmark the performance of a wrapper FS approach called Binary Cuckoo Search (BCS), and three filter-based FS approaches (namely Mutual Information Maximisation (MIM), Joint Mutual Information (JMI), and minimum Redundancy Maximum Relevance (mRMR)). Our evaluation has shown that the proposed model is an effective approach for FS, in selecting better features that enhance the performance metrics on the classifiers. Thus, MBHO can be utilized as one alternative to the existing state-of-art-approaches. We release the source codes of our implementation for the community to build on with new methods and datasets.

Higher traffic density in Russian cities and less uniform traffic due to congestions are reasons for increased emissions of pollutants contained in exhaust gases of vehicles. The paper presents the modeling results of pollutant dispersion in Magnitogorsk. The analysis of these results shows that now many blocks of flats and social infrastructure of the city are in a zone with an excess of maximum allowable concentration of pollutants. Having summarized the methodological framework formulated by Russian and foreign researchers, the authors systemized the existing methods used to decrease pollutants produced by vehicles. It is proposed to choose an optimal combination of such methods applying a developed mathematical model. By adopting an optimal combination of the methods, it is possible to ensure minimum air pollutant emissions from vehicles, allocating limited financial resources. The mathematical modeling of the solutions on changing traffic density and structure and implementing methods used to decrease pollutants on one of the Magnitogorsk crossroads with the heaviest traffic is used to draw a conclusion about efficiency of the designed model used as a tool for strategic planning of development and transformation of street networks.

In recent years, research has focused on generating mechanisms to assess the levels of subjects' cognitive workload when performing various activities that demand high concentration levels, such as driving a vehicle. These mechanisms have implemented several tools to analyze cognitive workload where the electroencephalographic (EEG) signals are the most used due to its high precision. However, one of the main challenges in the EEG signals implementing is finding the appropriate information to identify cognitive states. Here we show a new feature selection model for pattern recognition using information from EEG signals based on machine learning techniques called GALoRIS. GALoRIS combines Genetic Algorithms and Logistic Regression to create a new fitness function that identifies and selects the critical EEG features that contribute to recognizing high and low cognitive workload and structures a new dataset capable of optimizing the model's predictive process. We found that GALoRIS identifies data related to high and low cognitive workload of subjects while driving a vehicle using information extracted from multiple EEG signals, reducing the original dataset by more than 50%, maximizing the model's predictive capacity-achieving a precision rate greater than 90%.

Due to the rapid development of unmanned aerial vehicles (UAVs) communication technology, UAVs are gradually competing with primary users (PUs) for spectrum resources. Cognitive radio (CR) is a promising solution to meet the needs. Cooperative spectrum sensing (CSS) is considered as an effective method to detect the PU signal and identify available spectrum resources for UAVs in a cognitive UAV network (CUAVN). However, the cooperative mode among multiple UAVs may incur a high overhead, resulting in performance degradation. Therefore, we introduce a differential sequential 1 (DS1), which incorporates a differential mechanism and leverages the sequential idea based on the classical voting rule to enhance cooperative performance and efficiency. In view of this, we formulate three scenarios to characterize the PU activity and introduce a multi-slot cooperative mode within a single UAV to realize cooperative gain. Further, only the information change about the PU status is sequentially calculated in DS1, and combined with a sequential idea, the efficiency of the voting rule is greatly improved. Moreover, the application of support vector machines (SVM) in dynamic selection enables the selection of the most suitable voting rule based on diverse sensing parameters. This dynamic selection process ensures optimal performance and efficiency by adapting the voting rule to the specific characteristics of the given scenario. Finally, simulation results demonstrate that the superiority of our proposal with respect to the detection performance, sample size and the energy efficiency is evident, which proves the high performance of the proposed policy.

This paper presents a comparative study of fundamental similarity functions for Siamese networks in semantic textual similarity (STS) tasks. We evaluate various similarity functions using the STS Benchmark dataset, analyzing their performance and stability. Additionally, we introduce a multi-objective approach for optimal threshold selection. Our findings provide insights into the effectiveness of different similarity functions and offer a straightforward method for threshold selection optimization, contributing to the advancement of Siamese network architectures in STS applications.

The Giant Babax, an endemic bird in China and a nationally protected wildlife species of Class Ⅱ, is primarily distributed in southern and southeastern Tibet. To investigate the factors influencing nesting site selection, this study conducted research on nest characteristics and nesting site preferences at four sample sites around Lhasa from March to October 2023y, using systematic search methods, tracking methods, and sampling methods. The research findings are as follows: (1) The average nest depth was (7.70±1.47)cm, nest height was (19.58±2.97)cm, inner diameter was (10.64±1.73)cm, outer diameter was (24.65±4.8)cm, average weight was (162.3±13.5)g, and average nest spacing within the plot was 396.93m. (2) The nests of Giant Babax were predominantly found on vegetation such as Salix longistamina (38%), Hippophae gyantsensis (20%), Rosa sericea Lindl. (14%), and Populus szechuanica Schneid(11%). They showed a preference for artificial secondary forests as nesting sites. (3) Giant Babax exhibited a preference for habitats with robust trees that had high canopies while being distant from houses and roads, but close to water sources; moreover, the canopy of the nesting tree played a crucial role in their choice of nesting sites. (4) The reproductive success rate reached 76%, with key factors affecting it being the canopy coverage of the nesting tree and the number of helpers. These research results provide fundamental data support for population conservation efforts and ecological resource management strategies concerning the Giant Babax.

Caries is a prevalent oral disease that primarily affects children and teenagers. Advances in ma-chine learning have caught the attention of scientists working with decision support systems to predict early tooth decay. Current research has developed machine learning algorithm for caries classification and reached high accuracy especially in ML for image data. Unfortunately, most studies on dental caries only focus on classification and prediction tasks, meanwhile dental carries prevention is more important. Therefore, this study aims to design an efficient feature for decision support system machine learning based that can identify various risk factors that cause dental caries and its prevention. The data used in the research work was obtained from the 2018 Korean Children's Oral Health Survey, which totaled nine datasets. The experimental results show that combining the mRMR and GINI Feature Importance methods when training with the GBDT model achieved the optimum performance of 95%, 93%, 99%, and 88% for accuracy, F1 score, precision, and recall, respectively. So, the proposed method has provided effective predictive model for dental caries prediction.

Today’s purchasing companies demand an advanced buyer equal of enactment from their supplier while the two parties maintain a respectful connection. Although the supplier selection (SC) product life cycle cost (SCPLCC) is an important consideration among corporations, SCPLCC problem has become associated with deciding how one supplier should be selected from possible alternatives. In this study, we applied two types of goal programming, multiobjective linear programming and revised multichoice goal programming to develop a PLCC-based concept to solve the SCPLCC problem and construct a decision-making tool for application to a case of supply chain management in a Taiwanese light-emitting diode company in the high-tech industry. Our study main contribution Company managers can easily use the two approaches of the SCPLCC model with different parameters to solve SCPLCC model problems. Finally, we comparing five models found RMCGP with weighted linear goal programming had an adequate effect for application to the PLCC concept for high-technology comapny; this cloud make company decision–makers focus on low PLCC and select better supplier.

This paper surveys estimates of the transmission features of the novel coronavirus, and then proposes a model to address sample-selection bias in estimated determinants of infection. Containment assumptions of the infection forecasting models depend on assumed effects of policies and self-regulating behavior. In the commons dilemma of the pandemic, the perceived ‘low risks’ of unregulated marginal choices do not reflect the full social cost, implying non-pharmaceutical interventions (NPI) to reduce mortality can enhance social welfare. As more economic activity renews with liftings of restrictive NPI (RNPI), a critical question concerns the ability of milder NPI (MNPI) and voluntary precautions to mitigate the risk of greater infections and deaths while also limiting the pandemic’s economic damage and its social costs. Ineffective NPI could lead to continued COVID-19 waves and new types of crises, worsened expectations and delayed economic recoveries. From the central range of surveyed estimates of transmission and alternative herd-immunity-threshold estimates, a ‘worst-case’ virus guidepost suggests eventual deaths of around 25 to 41 million worldwide and 1.1 to 1.7 million in the U.S. needed to reach herd immunity with no vaccine or treatment. The most optimistic study surveyed (theoretical model from a non-reviewed preprint study) combined with the low end of the range of the estimated mortality rate suggests 6 to 9 million deaths worldwide and 250 to 370 thousand in the U.S. to reach herd immunity. Successes in the mix of NPI, treatments, and vaccine can limit the eventual global death toll of the virus. Improved estimation models for forecasting and decision making may assist in better targeting the local timings and mix of NPI. Diagnostic tests for the virus have been largely limited to symptomatic cases, causing possible sample selection bias. A recursive bivariate probit model of infection and testing is proposed along with several possible applications from cross-section or panel-data estimation. Multiple potential explanatory variables, data sources, and estimation needs are specified and discussed.

The COVID-19 pandemic over the past years has shown a great need for rapid, low-cost and on-site detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In this paper, an aptamer-based colloidal gold nanoparticle lateral flow test strip was well developed to realize the visual detection of wild type SARS-CoV-2 spike protein (SP) and multiple variants. Under the optimal reaction conditions, a low detection limit of SARS-CoV-2 S protein of 0.68 nM was acquired, and the actual detection recovery was 83.3% to 108.8% for real world samples. This suggests a potential tool for the prompt detection of SARS-CoV-2 with good sensitivity and accuracy, and a new method for the development of alternative antibody test strips for the detection of other viral targets.

A pivotal strategy in decarbonizing the transport sector is by transitioning from internal combustion engine vehicles (ICEVs) to electric vehicles (EVs), especially if they are charged with renewable energy. To provide an incentive to the common populace to switch to EVs, cities should set up - or enable or even encourage the private sector to do so - electric vehicle charging stations (EVCS) at multiple and suitably accessible locations. This paper aims to present a digitaltwin-enabled methodology study for selecting the most suitable possible locations to establish EVCS with consideration of the low voltage (LV) network operation in terms of power losses, active and reactive power in EV charging demand and the effect of the EVCS on the transformers, based on examples in Newcastle upon Tyne (England, UK). It also evaluates the most suitable type of charger that could be installed at these locations by studying the estimated traffic, cost and impact of the EVCS on the power grid, both at peak and off hours. This paper demonstrates how digitaltwin technologies, such as the web-based tool AutoDesign by Northern Powergrid and EA Technology and open source Pandapower can be used for identifying the most viable and cost-effective locations to connect EVCSs to a Distribution Network Operators (DNO)’s LV network. The results of the analysis indicate that with the installation of the most suitable type of EVCS in a particular location, the local power grid would not be significantly affected at any hour of the day.

Supplier selection (SC) continues to be a crucial component in manufacturing procurement. Using the PLCC advantages generates revenue and lowers costs more than might be anticipated. Supplier selection (SC) product life cycle cost (SCPLCC) is an important consideration among corporations, SCPLCC problem has become associated with deciding how one supplier should be selected from possible alternatives. Past literature on this topic is limited. We try to close this gap in knowledge. In this study, we attempt to apply two types of goal programming, multiobjective linear programming and revised multichoice goal programming to develop a PLCC-based concept to solve the SCPLCC problem and construct a decision-making tool for application to a case of supply chain management in a Taiwanese light-emitting diode company in the high-tech industry. Our study main contribution Company managers can easily use the two approaches of the SCPLCC model with different parameters to solve SCPLCC model problems. Finally, we are comparing five models found RMCGP with weighted linear goal programming had an adequate effect for application to the PLCC concept for high-technology Company; this cloud makes company decision–makers focus on low PLCC and select a better supplier in sustainable supply chains development.

Supplier selection (SC) product life cycle cost (SCPLCC) is an important consideration among corporations, SCPLCC problem has become associated with deciding how one supplier should be selected from possible alternatives. In this study, we applied two types of goal programming, multiobjective linear programming and revised multichoice goal programming to develop a PLCC-based concept to solve the SCPLCC problem and construct a decision-making tool for application to a case of supply chain management in a Taiwanese light-emitting diode company in the high-tech industry. Our study main contribution Company managers can easily use the two approaches of the SCPLCC model with different parameters to solve SCPLCC model problems. Finally, we comparing five models found RMCGP with weighted linear goal programming had an adequate effect for application to the PLCC concept for high-technology company; this cloud makes company decision–makers focus on low PLCC and select a better supplier in sustainable supply chains goal.

Flooding, exacerbated by climate change, poses a significant threat to certain areas, increasing in frequency and severity. In response, the construction of supplementary dams has emerged as a reliable solution for flood management. This study employs a Remote Sensing (RS) approach integrated with GIS to assess the feasibility of constructing a supplementary dam near Linville, Brisbane, Australia, with the aim of mit-igating floods and preventing overtopping failure at the Wivenhoe Dam. Using QGIS software and a 25-meter resolution DEM from the Queensland Spatial Catalogue ‘QSpatial’ website, four potential dam sites were analysed, considering cross-sections, watershed characteristics, and water volume calculations. Systematic selection criteria were applied to identify the most optimal option based on dam wall di-mensions, volume-to-area, and volume-to-cost ratios. The selected option was further assessed against predefined criteria, yielding one optimal choice. The study provides insights into the feasibility and ef-fectiveness of supplementary dam construction for flood mitigation in the region, with recommendations for future research and implementation.

Surface water distribution extracted from remote sensing data has been used in water resource assessment, coastal management, and environmental change studies. Traditional manual methods for extracting water bodies cannot satisfy the requirements for mass processing of remote sensing data; therefore, accurate automated extraction of such water bodies has remained a challenge. The histogram bimodal method (HBM) is a frequently used objective tool for threshold selection in image segmentation. The threshold is determined by seeking twin peaks, and the valley values between them; however, automatically calculating the threshold is difficult because complex surfaces and image noise which lead to not perfect twin peaks (single or multiple peaks). We developed an operational automated water extraction method, the modified histogram bimodal method (MHBM). The MHBM defines the threshold range of water extraction through mass static data; therefore, it does not require the identification of twin histogram peaks. It then seeks the minimum values in the threshold range to achieve automated threshold. We calibrated the MHBM for many lakes in China using Landsat 8 Operational Land Imager (OLI) images, for which the relative error (RE) and squared correlation coefficient (R2) for threshold accuracy were found to be 2.1% and 0.96, respectively. The RE and root-mean-square error (RMSE) for the area accuracy of MHBM were 0.59% and 7.4 km2. The results show that the MHBM could easily be applied to mass time-series remote sensing data to calculate water thresholds within water index images and successfully extract the spatial distribution of large water bodies automatically.

A multimodal detection system with complementary capabilities for efficient detection was developed for impurity detection. The system consisted of a visible light camera, a multispectral camera, image correction and registration algorithms. It can obtain spectral feature and color feature at the same time, and has higher spatial resolution than a single spectral camera. This system was applied to detect impurities in Pu ’er tea to verify its high efficiency. The spectral and color features of each pixel in the images of Pu ’er tea were obtained by this system and used for pixel classification. The experimental results show that the accuracy of Support Vector Machine (SVM) model based on combined features is 93%, which is 7% higher than that based on only spectral features. By applying median filtering algorithm and contour detection algorithm to the label matrix extracted from pixel-classified images, 8 impurities except hair were detected successfully. Moreover, taking advantage of the high resolution of visible light camera, small impurities can be clearly imaged. By comparing the segmented color image with the pixel-classified image, small impurities such as hair could be detected successfully. Finally, it is proved that the system can obtain multiple images to allow a more detailed and comprehensive understanding of the detected items, and has excellent ability to detect small impurities.

Using the PLCC advantages generates revenue and lowers costs more than might be anticipated. It ensures better decisions by using a more perfect and practical assessment of revenues and costs. Although the supplier selection (SC) product life cycle cost (SCPLCC) is an important consideration among corporations, SCPLCC problem has become associated with deciding how one supplier should be selected from possible alternatives. In this study, we applied two types of goal programming, multiobjective linear programming and revised multichoice goal programming to develop a PLCC-based concept to solve the SCPLCC problem and construct a decision-making tool for application to a case of supply chain management in a Taiwanese light-emitting diode company in the high-tech industry. Our study main contribution Company managers can easily use the two approaches of the SCPLCC model with different parameters to solve SCPLCC model problems. Finally, we comparing five models found RMCGP with weighted linear goal programming had an adequate effect for application to the PLCC concept for high-technology company; this cloud make company decision–makers focus on low PLCC and select better supplier.

The last-mile logistics in cities have become an indispensable part of the urban logistics system. This study aims to explore the effective selection of last-mile logistics nodes to enhance the efficiency of logistics distribution, strengthen the corporate distribution image, and further reduce corporate operating costs and alleviate urban traffic congestion. This paper proposes a clustering-based approach to identify urban logistics nodes from the perspective of geographic information fusion. This method comprehensively considers several key indicators, including the coverage, balance, and urban traffic conditions of logistics distribution. Additionally, we employed a greedy algorithm to identify secondary nodes around primary nodes, thus constructing an effective nodal network. To verify the practicality of this model, we conducted an empirical simulation study using the logistics demand and traffic conditions in the Xianlin District of Nanjing. This research not only identified the locations of primary and secondary logistics nodes but also provided a new perspective for constructing the urban last-mile logistics system, enriching the academic research related to logistics node construction. The results of this study are of significant theoretical and practical importance for optimizing urban logistics networks, enhancing logistics efficiency, and promoting the improvement of urban traffic conditions.

The negative binomial regression model (NBRM) is a generalized linear model which relaxes the restrictive assumption by the Poisson regression model when the variance is equal to the mean. The estimation of the parameters of the NBRM is obtained using the maximum likelihood (ML) method. Maximum likelihood estimator becomes unstable when the explanatory variables are linearly dependent, a situation known as multicollinearity. Based on this, we developed a new estimator called modified jackknifed Negative Binomial Kibria-Lukman (MJNBKL) estimator for the radiation of multicollinearity in NBRM using four different biasing (shrinkage) parameters. We establish superiority condition for MJNBKL estimator over the ones. The performance MJNBKL estimator was ascertained by comparing it with the existing ones through a Monte Carlo simulation study and two real life application datasets. The results of the simulation and real life application show that MJNBKL estimator outperformed the other estimators compared with by having the smallest MSE across all sample sizes and for different levels of correlation for the four biasing parameters used and the third biasing parameter is the optimal shrinkage parameter with the lowest MSE.

Marker-assisted selection (MAS) and genomic selection (GS) have been used to select individuals with desirable traits. MAS used a few markers associated with a specific trait to select individuals with desirable traits, which are determined after a Genome-wide association studies (GWAS). On the contrary, GS uses a large number of markers distributed across the genome to predict the genomic breeding values for a further selection of the individuals. In general, MAS has shown a high prediction accuracy but is not suitable for traits that are controlled for multiple genes, and has another constraint, it is required the phenotypic data; on the contrary, GS has not shown the highest prediction accuracy as MAS but it takes into account the effect of multiple genes controlling a target trait and it can be used without phenotypic data. Including GWAS-selected markers in GS can enhance the reduced prediction accuracy that GS shows in comparison with MAS. Thus, the objective of this study was to compare the prediction accuracy of MAS, and some models of genomic prediction (gBLUP, gBLUP including GWAs-selected markers, and some Bayesian models such as Bayes A, Bayes B, Bayes LASSO and Bayesian Ridge Regression) with GWAS-selected markers incorporated in gBLUP in order to confirm if the incorporation of GWAS in GS increases the prediction accuracy of GS. As a model for this study, it was used data from Sorghum which has shown population structure, to evaluate if the incorporation of GWAs-selected markers into GS improves prediciton accuracy. It was used a sample of 6000 SNPs out of the 265.487 reported in the study conducted by Morris et al (2013), and also it was considered some parameters that affect the efficiency of the selection such as the size of the training population, the heritability, and the number of QTNs. The GWAS-selected SNPs were identified after using the model BLINK. The results showed that the incorporation of GWAS-selected markers enhanced the performance of the genomic selection with similar prediction accuracy as MAS, the number of QTNs and size of the training population affected the accuracy, with higher accuracy with a bigger size of the training population and with a lower number of QTNs, but it seems that the heritability does not have any impact in the model where GWAS-selected SNPs were included in gBLUP.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

Accurate forecasting of icing thickness has a great significance for ensuring the security and stability of power grid. In order to improve the forecasting accuracy, this paper proposes an icing forecasting system based on fireworks algorithm and weighted least square support vector machine (W-LSSVM). The method of fireworks algorithm is employed to select the proper input features with the purpose of eliminating the redundant influence. In addition, the aim of W-LSSVM model is to train and test the historical data-set with the selected features. The capability of this proposed icing forecasting model and framework is tested through the simulation experiments using real-world icing data from monitoring center of key laboratory of anti-ice disaster, Hunan, South China. The results show that the proposed W-LSSVM-FA method has a higher prediction accuracy and it may be a promising alternative for icing thickness forecasting.

The paper presents attribute based characterization of nanomaterials method for computer storage and retrieval as knowledgebase. The knowledgebase permits indepth understanding and comparison between nanomaterials available with the scientists and product developers to satisfy their research and development (R & D) needs. Techniques for order preference by similarity to ideal solution (TOPSIS) is proposed to evaluate nanomaterials in the presence of multiple attributes. The method normalizes attributes to nullify the effect of different units and their values in the range of 0 to 1. The relative importance of different attributes for different applications is considered. The weight vector is derived using Eigen value formulation. The positive and negative benchmark solutions are derived. Euclidean distance of alternatives from these best and worst solution leads to the development of proximity /goodness/suitability index for ranking. Final decision is taken by decision makers by SWOT analysis and short and long term strategies of the organisation. The methodology is illustrated with the help of an example and step-by-step procedure. Results, discussion and conclusion highlights the importance and practical application.

There is scientific consensus that organismal aging did not evolve by natural selection (NS) because it lacks individual benefit. Nonetheless it exists, leading to much speculation about its origins, and when the diminishing force of selection begins. Both concepts are based upon two misconceptions; that aging occurs in and of itself and is caused by the declining strength of NS during the reproductive lifespan. Although lacking individual benefit, aging evolved by NS as a tradeoff of survival for reproduction. Based upon regulatory dynamics that participate in this tradeoff, aging begins once reproductive success has been achieved through offspring nurturing. Thereafter, the strength of NS wanes to exponentially accelerate aging, leading to death. Assumptions of the theory are that: (1) a life-long, “holistic” regulatory mechanism whose genic expression is modified epigenetically, originates in ontogenesis; (2) the regulatory mechanism of the last developmental stage becomes redundantly expressed during “morphostasis”, a non-aging, life interval of peak vitality to ensure completion of reproduction through nurturing, and (3) thereafter, loss of regulatory redundancy causes aging which reduces the strength of natural selection and allows accumulation of randomly occurring somatic damage.

Selection is a fundamental interaction element in Virtual Reality (VR) and 3D user interfaces (UIs). Raycasting, one of the most common object selection techniques, has been known to have difficulties in selecting small or distant objects. Meanwhile, recent advancements in computer vision technology have enabled seamless vision-based hand tracking in consumer VR headsets, enhancing accessibility to freehand mid-air interaction and highlighting the need for further research in this area. This study proposed a new technique called TouchView which utilizes a virtual panel with a modern adaptation of the Through-the-lens metaphor to improve freehand selection for VR UI. TouchView enables faster and less demanding target selection by allowing direct touch interaction with the magnified object proxies reflected on the panel view. Repeated-measures ANOVA on the results of a follow-up user experiment on multitarget selection with 23 participants showed that TouchView outperformed the current market-dominating freehand raycasting technique, Hybrid Ray in terms of task performance, perceived workload, and preference. The user behavior was also analyzed to understand the underlying reasons for these improvements. The proposed technique can be used in VR UI applications to enhance the selection of distant objects, especially for cases with frequent view shifts.

Traffic Inspection (TI) work in this article is positioned as a specific module of road traffic with its primary function oriented towards monitoring and controlling safe traffic and the execution of significant events within a particular geographic area. Exploratory research on the significance of event execution in simple, complicated and complex traffic flow and process situations is related to the activities of monitoring and controlling functional states and performance of categorical variables, which include objects and locations of road infrastructure, communication infrastructure and networks of traffic inspection resources. It is emphasized that the words “work” and “traffic” have the semantic status as synonyms (in one world language), which is explained in the design of the Agent-based model of the complexity of content and contextual structure of TI work at the singular and plural level with 12 points of interest (POI) in the thematic research. An Event Execution Log (EEL) was created for on-site data collection with eight variables, seven of which are independent (event type, activities, objects, locations, host, duration-period and periodicity of the event) and one dependent (significance of the event) variable. The structured data set includes 10,994 input-output vectors in 970 categories collected in the EEL created by 32 human agents (traffic inspectors) over a 30-day period. An algorithmic presentation of the methodological research procedure for preprocessing and final data processing in the ensemble of machine learning models for classification and selection of TI tasks is given. Data cleaning was performed on the available dataset to increase data consistency for further processing. Vector elimination was carried out based on the Location variable, such that the total number of vectors equals the number of unique categories of this variable, which is 636. The main result of this research is the Classification modeling of the significance of events in TI work based on machine learning techniques and the Stacking ensemble. The created machine learning models for event significance classification modeling have high accuracy values. To evaluate the performance metrics of the Stacking ensemble of models, the confusion matrix, Precision, Recall, ND F1-score are used.

The intelligent elderly care model places new demands on the skills of aging caregivers. The identification and development of forward-thinking, high-potential nursing talent is essential for advancing the intelligent elderly care sector. Multi-benchmarking selection and competitive analysis is used to evaluate and identify nursing personnel in the rehabilitation treatment center of a hospital in Hefei City. Using proxy evaluation and democratic evaluation model, three types of benchmarks such as single item benchmark, individual benchmark and group benchmark were identified and selected, and the professional nursing team was constructed based on the evaluation results. Different from the traditional other-directed evaluation, multi-benchmarking selection and competitive analysis is self-directed evaluation, this method is more conducive to the identification of high-potential and digital nursing talents by intelligent elderly service organizations, and facilitates the formation of professional nursing teams with complementary strengths and cross-fertilization, so as to satisfy the diversified and multi-level needs of the elderly for intelligent elderly services.

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.

Mitral regurgitation (MR) is a broadly diffuse valvular heart disease (VHD) with a significant impact on healthcare system and patient’s prognosis. Transcatheter mitral valve interventions (TMVI) are now well-established techniques included in the therapeutic armamentarium for managing patients with mitral regurgitation, either primary or functional MR. Even if guidelines give indications regarding the correct management of this VHD, the wide heterogeneity of patient’s clinical background, valvular and heart’s anatomy make each patient a unique case, in which the appropriate device’s selection requires a multimodality imaging evaluation and a multidisciplinary discussion. Proper pre-procedural evaluation plays a pivotal role to judge the feasibility of TMVI, as well as a cooperative works between imagers and interventionalist is crucial for procedural success. This manuscript aims to provide an exhaustive overview of the main parameters that need to be evaluated for appropriate device selection, pre-procedural planning, intraprocedural guidance and post-operative assessment in the setting of TMVI. In addition, it tries to give some insights about next perspective of structural cardiovascular imaging.

In a hyperconnected society, computer networks play a pivotal role in all activities that permeate our daily lives. In the context of smart cities, theses networks play a pivotal role in enhancing urban efficiency and sustainability. The continuous flow of packets in these networks poses security challenges, from personal data leakage to service unavailability. Anomaly-based methods are commonly used to detect network attacks. In this context, Software-Defined Networking (SDN) emerges as a solution for anomaly detection in network traffic, facilitating comprehensive, real-time analyses and dynamic adaptation to changes. This study aims to present a systematic review of feature selection techniques and evaluate the effectiveness of attribute selection with a multi-class classifier in network anomaly detection. The objective of this paper is to inspire future research and identify trade-offs among these techniques for detecting Denial of Service (DoS) attacks. Based on the findings, the analysis of the entire dataset yields superior results in terms of precision (99%), but using the output of OneR, although resulting in a slight loss of precision compared to the complete dataset, presents the highest precision among other studied techniques, indicating a trade-off between precision and processing time efficiency.

High temperature stress affects tomato production both in tropical and sub-tropical environments worldwide. To explore genetic variation for heat tolerance in tomato, 329 transcontinental tomato varieties were evaluated at The Ministry of Municipality and Environment (MME) greenhouses near Doha, Qatar. Preliminary phenotypic analysis identified a diverse set of 71 hybrid and pure line tomato varieties for more detailed studies. The selected subset was examined in the greenhouse in a randomized complete block design under heat stress. The materials were phenotyped for fruit size, fruit weight, fruit hardness, fruit locules, fruit set (%), total soluble solids (TSS), and fruit yield. Significant phenotypic differences among genotypes were observed for all the traits assessed. To explore the genetic basis of variation among varieties the subset was genotyped using 104 SNP markers identified in previous heat tolerance genome wide association studies (GWAS). Nineteen QTL associated SNP markers could reliably select heat tolerant varieties in terms of better fruit yield, fruit set, and TSS. These markers are located on Chromosome 1, 5, 6, 8, 9, and 12. Interestingly, two clusters of markers on chromosome 6 were linked to significant effects on yield, fruit set, and TSS under high temperature. Some markers located within these QTL regions were also reported as associated with heat tolerance in other studies. Eighteen out of nineteen SNP markers were mapped within a gene body. Based on the phenotypic and the genotypic analysis, an elite set of five varieties was selected for approval for heat stress environments in Qatar. These findings have significance not only for Qatar, but they are also valuable for wider application at other locations worldwide. The 19 markers presented here could be adopted by breeders for marker-assisted selection (MAS) for heat tolerance.

The study investigated farmers’ perception on pests and diseases management strategies, agricultural practices, production constraints and selection criteria of elite varieties using a survey research design. A total of 700 questionnaires were administered to smallholder farmers who were farming for household consumption, those producing for sale and household consumption and those who were mainly producing for sale because their primary goal was to produce for the market. Findings revealed that the most prevalent pests identified were whiteflies (Bemisia tabaci), grasshoppers (Zonocerus variegatus), aphids (Aphis gossypii), mealybugs (Phenacoccus manihoti), termites (Isoptera), and grasscutters (Thryonomys swinderianus). The three most common diseases of cassava limiting growth and yield with mixed infection include viral, bacterial, and fungal. The study also revealed that only 12.5% of farmers cultivated improved cassava varieties. The management practices implemented encompassed field sanitation and the application of pesticides. Lack of capital and no availability of market were the most important production and marketing constraints faced by farmers in the study area, whereas poundability and high storage root yield are the most preferred traits farmers consider in selecting a new variety. Results suggest that smallholder farmers should endeavor to undergo various developmental programs to develop themselves to increase their competitive advantage in their locality and in the local and global agricultural sectors. In addition, governments and other policy makers should strategize plans and programs that would contribute to smallholder farmers’ agriculture, community and national development.

The Cobb angle is critical in assessing adolescent idiopathic scoliosis (AIS) patients. This study aimed to evaluate the error in selecting the cranial and caudal limit vertebrae on AIS digital X-rays of experienced and novice observers and its correlation with the error in measuring the Cobb angle and determining the length of the scoliotic curves. Using the TraumaMeter v.873 software, eight raters (four experienced and four novices) independently evaluated 68 scoliotic curves on 42 AIS X-rays across three sessions one month apart according to Hopkins’ criteria of absolute reliability. Two spine specialist experts using the Cobb method established the gold standard measurements. The percentage of error in the selection of the cranial vertebrae (the most-tilted vertebra above the apex) is higher than in the caudal vertebrae (the most-tilted vertebrae below the apex) (44.7%, CI95% 41.05-48.3 compared to 35%, CI95% 29.7-40.4). The error in the choice of the most tilted vertebrae, in number of vertebrae per scoliotic curve, was MBE (mean bias error) =0.45, CI95% 0.38-0.52 in the cranial and MBE=0.35, CI% 0.69-0.91 in the caudal. The percentage of errors in the choice of boundary vertebrae is lower for the experienced than for the novices, both in cranial and caudal. The experienced chose at least one boundary vertebrae incorrectly in 52% of the meas-urements and the novices in 65.1%. The error in the Cobb angle did not depend on the number of boundary vertebrae chosen incorrectly (r=0.198, p=0.111). Of the 50% of Cobb angle measurements closest to the actual value, 55.4% (454) were obtained by incorrectly selecting at least one boundary vertebra. There was a positive correlation (r=0.673, p=0.000) between the error in selecting the boundary vertebrae and the error in determining the length of the scoliotic curves. The error in quantifying the length of scoliotic curves was MBE=0.43, CI95% 0.35-0.51 vertebrae per curve. We can conclude that errors in selecting boundary vertebrae are common among experienced and novice observers, with a greater frequency of error in the cranial vertebrae. There is no correlation between the error in selecting the boundary vertebrae and the error in measuring the Cobb angle. Contrary to the consensus, the accuracy of determining the length of the scoliotic curve is limited by the Cobb method’s reliance on the correct selection of boundary vertebrae. Inappropriate choice of boundary vertebrae leads to an estimated error in determining the length of the scoliotic curves of 0.805 vertebrae for each boundary vertebra chosen incorrectly.

Hybrid forecasting methods have emerged as a solution surpassing the limitations of both statistical and deep learning approaches. While the first emphasize the significance of variables, they often produce worse forecasting results when compared to newer techniques. In contrast, deep learning models remain enigmatic "black boxes" in terms of interpretability, although achieving better results in forecasting. This article introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, designed to harness the best of both approaches, enhancing forecasting accuracy while retaining model interpretability through a feature selection process. CCLR-DL blens cross-correlation analysis, lagged multiple linear regression and granger's causality procedures with deep learning architectures based on LSTM. In a practical demonstration, CCLR-DL was applied to a real database of clinical visits associated to diagnoses in Catalonia, Spain (tracking a population of 6.3 million patients during 10 years). Predicting visits enables the healthcare managers to be ready for future demand shifts. Results demonstrate a consistent and substantial improvement over standalone statistical and deep learning methods when predicting healthcare demand. This hybrid approach not only showcases its efficacy but also offers a promising solution to the challenge of balancing predictive accuracy with model explicability. In this context, this work aims to design and validate a method for feature selection and forecasting of multivariate high dimensional time series datasets not only to improve prediction accuracy but also to model transparency by identifying a subset of variables that improve predictions and G-cause the target variable.

Evolutionary ecology may be described as explaining ecology through evolution and vice versa, but one may also view it as an integration of the two fields, where one takes the view that ecology and evolution are inseparable, and one can only begin to understand the biology of organisms by synthesizing the two fields. An example of such a synthesis is the biology of high fecundity and the associated concept of sweepstakes reproduction, or skewed individual recruitment success. As an illustration we consider selection at linked sites under various dominance and epistasis mechanisms in a diploid population evolving according to random sweepstakes and experiencing recurrent bottlenecks. Using simulations we give a few examples of the impact of the stated elements on selection. We show that depending on the dominance mechanisms random sweepstakes can shorten the time to fixation (conditional on fixation) of the fit type at all sites. Bottlenecks tend to increase the fixation time, with random sweepstakes counteracting the effects of bottlenecks on the fixation time. Understanding the effect of random sweepstakes, recurrent bottlenecks, dominance mechanisms and epistasis on the fate of selectively advantageous mutations may help with explaining genetic diversity in natural highly fecund populations possibly evolving under sweepstakes reproduction.

Background: Metabolic flux analysis (MFA) is an indispensable tool in metabolic engineering. The simplest variant of MFA relies on an overdetermined stoichiometric model of the cell’s metabolism under the pseudo-steady state assumption, to evaluate the intracellular flux distribution. Despite its long history, the issue of model error in the overdetermined MFA, particularly misspecifications of the stoichiometric matrix, has not received much attention. Method: We evaluated the performance of statistical tests from linear least square regressions, namely Ramsey RESET test, F-test and Lagrange multiplier test, in detecting model misspecifications in the overdetermined MFA, particularly missing reactions. We further proposed an iterative procedure using the F-test to correct such an issue. Result: Using Chinese hamster ovary and random metabolic networks, we demonstrated that: (1) a statistically significant regression does not guarantee high accuracy of the flux estimates, (2) the removal of a reaction with a low flux magnitude can cause disproportionately large biases in the flux estimates, (3) the F-test could efficiently detect missing reactions, and (4) the proposed iterative procedure could robustly resolve the omission of reactions. Conclusion: Our work demonstrated that statistical analysis and tests could be used to systematically assess, detect and resolve model misspecifications in the overdetermined MFA.

This paper deals with the formulation of a Cobot kinematic model by developing both the direct and inverse kinematics and choosing the noa transformation matrix for defining the end-effector position and orientation with respect to the base frame. These algorithms have been validated via software in Matlab environment and by means of suitable experimental tests, which have been carried out by using a UR5e Cobot. Moreover, a specific industrial application regarding the robotized assembling of a multi-cylinder IC engine, has been designed in terms of layout and corresponding automatic cycle that is intended as a sequence of the robot elementary actions. In particular, the proposed robotized cell is composed by the UR5e Cobot along with its controller and a suitable electropneumatic circuit that includes a PLC with its user interface, which are both governed by means of a specific electronic board and a switch control box. The IC engine in scale of 1:5 and specific parts of the end-effector, which takes the role of vacuum gripper and torque limiting screwdriver, have been designed and manufactured by using a 3D printer.

Amidst the escalating demands for efficient Intelligent Transportation Systems (ITS) management, the significance of accurate Origin-Destination (OD) data prediction has emerged as a paramount concern, given its indispensable role in the ITS domain. This paper introduces a groundbreaking integrated model, creatively fusing the unique strengths of Graph Convolutional Network (GCN), Residual Neural Network (ResNet), and Long Short-Term Memory Network (LSTM) into a single architecture, which we name GraphResLSTM, to exploit road segment average speed data for OD prediction. Compared with conventional road segment traffic volume data, average speed data is more readily available, significantly reducing the data accessibility barrier for OD prediction. We underscore the critical role of selection of key road segments and employs a combination of Entropy Weight Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to identify 41 representative road segments from the experimental road network. In the experimental phase, we simulate 86400000 seconds of traffic conditions, generating a total of 1440000 data records. Utilizing these simulated data, we design and conduct comparative experiments between models as well as data types. The results demonstrate that both the GraphResLSTM model and road segment average speed data outperform other models and data types notably in OD prediction tasks.

More and more works are using machine learning techniques while adopting supervisory control and data acquisition (SCADA) system for wind turbine anomaly or failure detection. While parameter selection is important for modelling a wind turbine’s health condition, only a few papers have been published focusing on this issue and in those papers interconnections among sub-components in a wind turbine are used to address this problem. However, merely the interconnections for decision making sometimes is too general to provide a parameter list considering the differences of each SCADA dataset. In this paper, a method is proposed to provide more detailed suggestions on parameter selection based on mutual information. Moreover, after proving that Copula, a multivariate probability distribution for which the marginal probability distribution of each variable is uniform is capable of simplifying the estimation of mutual information, an empirical copula based mutual information estimation method (ECMI) is introduced for an application. After that, a real SCADA dataset is adopted to test the method, and the results show the effectiveness of the ECMI in providing parameter selection suggestions when physical knowledge is not accurate enough.

Stochastic mortality models seek to forecast future mortality rates; thus, apparently the objective variable should be the mortality rate expressed in the original scale. However, the performance of stochastic mortality models - in terms, that is, of their goodness-of-fit and prediction accuracy - is often based on the logarithmic scale of the mortality rate. In this article, we examine whether the same forecast outcomes are obtained when the performance of mortality models is assessed based on the original and log scales of the mortality rate. We compare four different stochastic mortality models: the original Lee-Carter model, the Lee-Carter model with (log-)normal distribution, the Lee-Carter model with Poisson distribution and the median Lee-Carter model. We show that the preferred model will depend on the scale of the objective variable, the selection criteria measure and the range of ages analysed.

The advancement of sequencing technology and molecular breeding methods have provided technical support and assurance for accurate breeding. Genomic Selection (GS) utilizes genomic information to improve livestock breeding and, it is more accurate and more efficient than traditional selection methods. GS has been widely applied in domestic animals breeding, especially in cattle. However, there is still limited study on the application and research of GS in sheep and goat. In this paper, we outlined the principle, analysis methods, the influential factors of GS, and elaborated on the research progress, challenges, and prospects of applying GS in sheep and goat breeding. Through the review of these aspects this paper is expected to provide valuable references for the implementation of GS in the field of sheep and goat breeding.

The studied solar pot is a recent invention, which gained a utility model protection in 2021 from the Hungarian Intellectual Property Office under patent number 5489. The device is made for environmentally friendly cooking or heating (by utilizing solar energy) of foods and liquids. Its structure is similar to a double pipe heat exchanger, it has an outer mantle and an inner cooking tank. The goals of the paper are proposing a new physically-based mathematical model describing the solar pot and carrying out computer experiments with it, assembling an experimental system of the pot connected with a solar collector and performing measurements on it. Based on the results, the solar pot can successfully be used for cooking or sterilizing foods or liquids during the studied time period, in Hungary.

This article investigates the effectiveness of feature extraction and selection techniques for enhancing the performance of classifiers accuracy in Type II Diabetes Mellitus (DM) detection using microarray gene data. To address the inherent high dimensionality of the data by employing three Feature Extraction (FE) methods are used namely, Short-Time Fourier Transform (STFT), Ridge Regression (RR), and Pearson Correlation Coefficient (PCC). To further refine the data, meta-heuristic algorithms like Bald Eagle Search Optimization (BESO) and Red Deer Optimization (RDO) are utilized for feature selection. The performance of seven classification techniques such as Non-Linear Regression - NLR, Linear Regression - LR, Gaussian Mixture Model - GMM, Expectation Maximization - EM, Logistic Regression - LoR, Softmax Discriminant Classifier - SDC, and Support Vector Machine with Radial Basis Function kernel - SVM-RBF are evaluated with and without feature selection. The analysis reveals that the combination of PCC with SVM-RBF achieved a promising accuracy of 92.85% even without feature selection. Notably, employing BESO with PCC and SVM-RBF maintained this high accuracy. However, the highest overall accuracy of 97.14% was achieved when RDO was used for feature selection alongside PCC and SVM-RBF. These findings highlight the potential of feature extraction and selection techniques, particularly RDO with PCC, in improving the accuracy of DM detection using microarray gene data.

This paper aims to demonstrate how the detection of communities for epidemiological networks can be used to reduce the dimensionality of optimal control problems. A range of planted partition stochastic blockmodels are generated, where the underlying communities in the model vary in detectability. A high-performance computing workflow is then used to simulate and estimate reduced model dynamics for the networks, which in turn is used to find optimal control solutions.

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.

The thermocontextual interpretation (TCI) establishes a system’s exergy, entropic energy, and thermal entropy as thermocontextual properties of state, defined with respect to its positive temperature surroundings. This work extends previous applications of the TCI to irreversible and statistical transitions. The TCI defines statistical entropy as a transactional process of derandomization and transition to a negative-entropy state. Statistical measurements of a confined quantum particle’s position are detailed in terms of reversible processes of instantiation and actualization. The TCI then formalizes the MaxEnt as a fundamental physical principle. We apply MaxEnt and statistical entropy measurements to the double-slit experiment. Particles passing through parallel slits record a wave interference pattern, but a “which-slit” detector eliminates wave interference. Richard Feynman called the double-slit experiment the only mystery, at the heart of quantum mechanics. The TCI offers a simple explanation. The which-slit detector breaks the system’s symmetry, enabling particles to pass through one slit or the other, and MaxEnt selects the asymmetrical transition, which has no wave interference and a higher statistical entropy.

Wheat (Triticum aestivum L.) breeding programs can take over a decade to release a new variety. However, new methods of selection such as genomic selection (GS) must be integrated to decrease the time it takes to release new varieties to meet the demand of a growing population. The implementation of GS into breeding programs is still being explored, with many studies showing its potential to change wheat breeding through achieving higher genetic gain. In this review, we explore the integration of GS for a wheat breeding program by redesigning the traditional breeding pipeline to implement GS. We propose implementing a two-part breeding strategy by differentiating between population improvement and product development. The implementation of GS in the product development pipeline can be integrated into most stages and can predict within and across breeding cycles. Additionally, we explore optimizing the population improvement strategy through GS recurrent selection schemes to reduce crossing cycle time and significantly increase genetic gain. The recurrent selection schemes can be optimized for parental selection, maintenance of genetic variation, and optimal cross-prediction. Overall, we outline the ability to increase the genetic gain of a breeding program by implementing GS and a two-part breeding strategy.

Estimating the ocean’s subsurface thermohaline information from satellite measurements is essential for understanding ocean dynamics and El Niño phenomenon. This paper proposes an improved double-output Residual Neural Network (DO-ResNet) model to concurrently estimate the ocean subsurface temperature (OST) and ocean subsurface salinity (OSS) in the tropical Western Pacific using multi-source remote sensing data, including sea surface temperature (SST), sea surface salinity (SSS), sea surface height anomaly(SSHA), sea surface wind (SSW), and geographical information (including longitude (LON) and latitude (LAT)). In the model experiment, Argo data were used to train and validate the model, and the root mean square error (RMSE), normalized root mean square error (NRMSE) and coefficient of determination (R²) were employed to evaluate the model's performance. The results showed that the sea surface parameters selected in this study have a positive effect on the estimation process, and the average RMSE and R² values for estimating OST (OSS) by the proposed model are 0.34 °C (0.05 psu) and 0.91 (0.95), respectively. Under the data conditions considered in this study, DO-ResNet demonstrates superior performance relative to the extreme gradient boosting model, random forest model, and artificial neural network model. Additionally, this study evaluates the model’s accuracy by comparing its estimations of OST and OSS across different depths with Argo-derived data, demonstrating the model's ability to effectively capture the most spatial features, and by comparing NRMSE across different depths and seasons, the model displays strong seasonal adaptability. In conclusion, this research introduces a novel artificial intelligence technique for estimating OST and OSS in the tropical Western Pacific Ocean.

This article systematically studied the A-optimal designs of a high-order mixture central polynomial model, which is an advancement of the research results for the A-optimal design of the most recent third-order mixture central polynomial model and a more accurate response surface model. This article is based on the simplex center design, obtaining measurement values at various design points, and verifying them through the A-optimal equivalence theorem. We also compare the A-efficiency of designs through examples, which can be applied to the A-optimal precise design of the fourth-order mixture model.

Refractoriness to antiseizure medications is still a major concern in the pharmacotherapy of epilepsy. For this reason, we decided to evaluate the combination of levetiracetam and cannabidiol, administered at a subthreshold dose, to limit the possible adverse effects of this phytocannabinoid. We administered levetiracetam (300 mg/kg/day, via osmotic minipumps), cannabidiol (120 mg/kg/day, injected once a day subcutaneously), or their combination for one week in epileptic rats. Saline-treated epileptic rats were the control group. Animals were monitored with video electroencephalography the week before and after the treatment. No changes were found in the controls. Levetiracetam did not significantly reduce the total seizure number or the overall seizure duration. Still, the overall number of seizures (p&lt;0.001, Duncan’s new multiple range test) and their total duration (p&lt;0.01) increased in the week following treatment withdrawal. Cannabidiol did not change seizures when administered as a single drug. Instead, levetiracetam combined with cannabidiol resulted in a significant reduction in the overall number and duration of seizures (p&lt;0.05), when comparing values measured during treatment with both pre- and post-treatment values. These findings depended on changes in convulsive seizures, while non-convulsive seizures were stable. These results suggest cannabidiol determined a remarkable potentiation of levetiracetam antiseizure effects at a subthreshold dose.

Public safety and intelligent surveillance systems critically depend on anomaly behavior detection for effective monitoring. In real-world pedestrian detection scenarios, prevalent challenges such as missed detections, complex background interference, and small target sizes hinder accurate anomaly identification. To address these issues, this study introduces YOLO-ABD, a lightweight method for anomaly behavior detection that integrates small target detection and channel shuffling. This method employs YOLOv8n as the baseline model, incorporating a small target detection mechanism in the Head part and utilizing GSConv convolution in the Backbone to enhance perceptual capability. Additionally, the SimAM attention mechanism is integrated to mitigate complex background interference, thereby improving target detection performance. Evaluation on the IITB-Corridor dataset demonstrated mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further highlighted the superiority of YOLO-ABD over advanced detection algorithms, underscoring its effectiveness and generalizability. With a relatively small parameter count, YOLO-ABD presents an excellent lightweight solution for pedestrian anomaly behavior detection.

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.

Session-based recommendations which aim to predict subsequent user-item interaction based on historical user behavior during anonymous sessions can be challenging tasks. Two main challenges need to be addressed and improved: (1) How to analyze these sessions to accurately and completely capture users’ preferences, and (2) how to identify and eliminate any interference caused by noisy behavior. Existing methods have not adequately addressed these issues since they either neglected the valuable insight that can be gained from analyzing consecutive groups of items or failed to take these noisy data in sessions seriously and handled them properly, which can jointly impede recommendation systems from capturing users’ real intentions. To address these two problems, we designed a multi-order semantic denoising (MSD) model for session-based recommendations. Specifically, we grouped items of different lengths as varying multi-order semantic units to mine the user’s primary intention from multiple dimensions. Meanwhile, a novel denoising network was designed to alleviate the interference of noisy behavior and provide a more precise session representation. The result of extensive experiments on three real-world datasets demonstrated that the proposed MSD model exhibited improved performance compared with existing state-of-the-art methods in session-based recommendation.

The SK model proposed by Sherrington and Kirkpatrick is an important mean field model for spin glasses. The dependence structure of Hamiltonians of the SK model is considered in this paper. We have investigated the covariance matrix of Hamiltonians of the SK model, and establish a relationship between the rank of the corresponding covariance matrix and the dimension of the space spanned by the Hamiltonians. Finally, we also give an upper bound for the rank of the covariance matrix, which might be the best.

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.

Geothermal energy, being a clean energy source, has immense potential, and accurate wellbore modeling is crucial for optimizing the drilling process and ensuring safety. This paper presents a novel geothermal wellbore model based on the drift-flux approach, tested under three different temperature and pressure well conditions. The proposed model integrates the conservation equations of mass, momentum, and energy, incorporating the gas-liquid two-phase flow drift-flux model and heat transfer model. Key features include handling heat transfer between the for-mation and the wellbore, addressing the slip relationship between gas and liquid phases, and accounting for wellbore friction. The nonlinear equations are discretized using the finite differ-ence method, and the highly nonlinear system is solved using the Newton-Raphson method. Numerical simulation, validation, and comparison with existing models demonstrate the en-hanced accuracy of this model. In our tests, the model achieved high accuracy in calculating bottom hole pressure and temperature, with Mean Relative Errors (MRE) significantly lower than those of other models. These results offer valuable insights for optimizing drilling parameters and ensuring drilling safety. Comparisons indicate that this approach significantly outperforms others in capturing the complex dynamics of geothermal wellbores, making it a superior tool for geo-thermal energy development.

Unevenly distributed rainfall leads to reduced potato water productivity (WP) under rainfed production. Understanding practices that can increase WP is vital. Objectives were to (i) understand seasonal variables that influence WP under rainfed conditions and (ii) the effect of the integration of cultivar, locality, mulch on potato WP. The study was under two agroecological zones Appelsbosch (Mbalenhle locality), and Swayimane (Stezi, and Mbhava locality), under smallholder. A split plot, in a randomized complete block design experiment, consists of mulching (mulch and not mulch), and selected cultivars. Soil water content (SWC), yield, and climatic conditions were collected, water use (ET) and WP were calculated. Rainfall, ET, and SWC had a significant influence on seasonal WP. Cultivar x mulch x locality had an insignificant effect on WP, however, locality x cultivars significantly altered potato WP. Localities that had lower vapor pressure deficit (VPD), low relative humidity, and sandy soil had higher potato WP of 14.53 kg m-3. The findings suggest that localities that have less atmospheric dryness and cultivars that show stability of yield across seasons can be an easy-to-apply practice for increasing potato WP under a resource-limited environment. Mulch is important when the distribution of intra-annual rainfall does not match crop water requirements.

With the development of deep learning, several Graph Neural Networks (GNN)-based approaches have been utilized for text classification. However, GNNs encounter challenges in capturing contextual text information within a document sequence. To address this, a novel text classification model RB-GAT is proposed by combining RoBERTa-BiGRU embedding and a multi-head Graph ATtention Network (GAT). First, the pre-trained RoBERTa model is exploited to learn word and text embeddings in different contexts. Second, the Bidirectional Gated Recurrent Unit (BiGRU) is employed to capture long-term dependencies and bidirectional sentence information from the text context. Next, the multi-head graph attention network is applied to analyze this information, which serves as a node feature for the document. Finally, the classification results are generated through a Softmax layer. Experimental results on three benchmark datasets demonstrate that our method can achieve an accuracy of 71.48%, 98.45%, and 80.32% on Ohsumed, R8, and MR, which is superior to the existing nine text classification approaches.

Castanopsis hystrix, a precious tree species in Southeast Asia, has the advantages of rapid growth and high-quality wood materials. However, there are problems such as long breeding cycle, time-consuming and low efficiency, which greatly restricts the industrial development of C. hystrix. To perform the genome selection (GS) for growth and wood traits and the early selection of superior progeny have great significance for the rapid breeding of new superior varieties of C. hystrix. The 226 clones in the main distribution and 479 progenies within 23 half-sib families were used as experimental materials in this study. Genotyping datasets were obtained by high-throughput re-sequencing technology, and GS studies were conducted on the growth (tree height (H), diameter at breast height (DBH)) and wood (wood density (WD), fiber length (FL), and fiber length-width ratio (LWR)) traits. The coefficient of variation (CV) of five phenotypic traits ranged from 10.1% to 22.73%, the average CV of growth traits was 19.93%, and the average CV of wood traits was 9.72%. The Pearson correlation coefficients between the five traits were almost significantly positive. Based on the Genomic Best Linear Unbiased Prediction (GBLUP) model, the broad-sense heritabilities of growth traits were higher than those of wood quality traits, and the different number of SNPs had little effect on the heritability estimation. GS prediction accuracy first increased and then reached a plateau around 3K SNPs for all five traits. The broad-sense heritability of these five traits was significantly positively correlated with their GS predictive ability (r=0.564, P

Chickens have extensive phenotypic variation. The Wuhua yellow chicken (WHYC) is an important traditional yellow-feathered chicken in China, characterized by white tail feathers, white flight feathers, and strong disease resistance. However, the genomic basis of traits associated with WHYC is still poorly understood. In this study, whole genome resequencing was performed with an average coverage of 20.77-fold to investigate heritable variation and identify selection signals in WHYC. Reads were mapped onto the chicken reference genome (Galgal5) with a coverage of 85.95%. After quality control, 11,953,471 SNPs and 1,069,574 InDels were obtained. In addition, 41,408 structural variants and 33,278 copy number variants were found. A comparative genomic analysis of WHYC and other yellow-feathered chicken showed that selected regions were enriched in genes involved in transport and catabolism, immune system, infectious diseases, signal transduction, and signaling molecules and interaction. Several genes associated with disease resistance were identified, including IFNA, IFNB, CD86, IL18, IL11RA, VEGFC, and ATG10. Furthermore, PMEL and TYRP1 may contribute to the coloring of white feathers in WHYC. These findings improve our understanding of the genetic characteristics of WHYC and may contribute to future breed improvement.

The decline in global pollinator populations has raised serious concerns about the sustainability of ecosystems and agricultural productivity. Urban environments, often characterized by habitat loss and environmental stressors, are considered challenging habitats for pollinators. However, urban green spaces, including street and ornamental trees, can play a crucial role in supporting pollinators by providing essential food resources. This study aimed to evaluate the sugar and amino acid production of eight urban tree species to determine their potential contributions to pollinator nutrition. Our findings revealed significant variability among species regarding nectar volume, sugar content, and amino acid composition, emphasizing the importance of considering multiple factors when assessing the utility of floral resources. Consequently, Tilia amurensis, Heptacodium miconioides, Aesculus turbinata, and Wisteria floribunda demonstrated superior potential in supporting urban pollinator communities. Contrastingly, Sorbus commixta, Styrax japonicus, and Cornus kousa, often favored for their aesthetic appeal, showed less potential. This study underscores the need for urban tree selection that prioritizes species that provide diverse and abundant nutritional resources for pollinators while balancing aesthetic and ecological values. Our results offer a foundation for better-informed urban biodiversity management and contribute to creating pollinator-friendly urban environments.

This study addresses the implementation of the International Financial Reporting Standard 9 (IFRS 9) in the European Union as of January 1, 2018, replacing the International Accounting Standard 39 (IAS 39) to introduce a new model for recognizing Loan Loss Provisions (LLP) based on Expected Credit Loss (ECL). This model responds to criticisms of the former Incurred Credit Loss (ICL) system for its inability to reflect credit losses in a timely manner, potentially exacerbating the effects of financial crises (Bushman &amp; Williams, 2015; Gebhardt &amp; Novotny-Farkas, 2011). The study focuses on the effects of adopting the ECL model on the level of Loan Loss Allowances (LLA) in loans, own equity, and the Common Equity Tier 1 (CET1) ratio across 13 Portuguese commercial banks. A mean comparison test is used to evaluate scenarios before and after the application of the ECL model, highlighting the importance of regulator actions and the adequacy of loss recognition policies, including the effects of Regulation (EU) 2017/2395 of December 12. The results obtained demonstrate significant negative impacts on the net values of loans, own equity, and the CET1 ratio upon adopting the IFRS 9 ECL model, due to the widespread increase in LLAs.

Considering characteristics of high river density, special underlying surface in plain river network region, and municipal drainage system function, river network drainage unit model is proposed, which is defined as a region surrounded by main river or embankment. Flood storage variety and control projects regulation of small rivers in each unit is simulated. With drainage catchment as an object, according to its drainage capacity, simplified municipal drainage model was developed. Coupling river network drainage unit model, simplified municipal drainage model and 2D flood routing model, urban flood analysis model for plain tidal river network region was developed, which could be applied to analyzing flood from upstream river, storm surge and local rainfall. Demonstration research was carried out in Puxi flood protected area in Shanghai.

Assessing the quality of corn seeds necessitates evaluating their content of water, fat, protein, and starch. This study integrates hyperspectral imaging technology with chemometric analysis techniques to achieve non-invasive and rapid detection of multiple key components in corn seeds. Hyperspectral images of the embryo surface of maize seeds were collected within the wavelength range of 1100~2498nm. Subsequently, image segmentation techniques were applied to extract the germ structure of the corn seeds as the region of interest. Seven spectral data preprocessing algorithms were employed, and the Detrending Transformation (DT) algorithm was identified as the optimal preprocessing method through comparative analysis using the Partial Least Squares Regression (PLSR) model. To reduce spectral redundancy and streamline the prediction model, three algorithms were employed for characteristic wavelength extraction: Successive Projections Algorithm (SPA), Competitive Adaptive Reweighted Sampling (CARS), and Uninformative Variable Elimination (UVE). Using both the original spectra and the extracted characteristic wavelengths, four content detection models were constructed: PLSR, Back Propagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFNN), and Least Squares Support Vector Machine (LSSVM). The experimental results demonstrate that the DT-CARS-LSSVM model exhibits exceptional accuracy and stability in predicting these four key components, with determination coefficients of 0.9877, 0.9344, 0.9827, and 0.9592, respectively. This study not only provides a scientific basis for evaluating the quality of corn seeds but also opens up new avenues for the development of non-invasive detection technology in related fields.

This study aims to propose a method for constructing basic digital twin data in South Korea by adhering to international standards and utilizing publicly available data. Specifically, the study focuses on designing and proposing a digital twin data model for buildings, which are the most applicable among the basic digital twin data. To achieve this, the first section provides essential background information, introduces concepts and requirements related to digital twin basic data, and offers a brief overview of CityGML. The second section explains the methodology and data used in this study. The third section presents the main findings: the selection of public data (buildings) for constructing digital twin basic data, the mapping process using CityGML, and the creation of UML diagrams. The fourth section discusses these findings. Finally, the conclusion and suggestions for future research are provided. This approach enhances the accuracy of building-related digital twin data and supports the use of digital twin services in both public and private sectors by enabling various spatial analyses.

Traffic sign detection plays a pivotal role in autonomous driving systems. The intricacy of the detection model necessitates high-performance hardware. Real-world traffic environments exhibit considerable variability and diversity, posing challenges for effective feature extraction by the model. Therefore, it is imperative to develop a detection model that is not only highly accurate but also lightweight. In this paper, we proposed YOLO-ADual, a novel lightweight model. Our method leverages the C3Dual and Adown lightweight modules as replacements for CPS and CBL modules in YOLOv5. The Adown module effectively mitigates feature loss during downsampling while reducing computational costs. Meanwhile, C3Dual optimizes the processing power for kernel feature extraction, enhancing computation efficiency while preserving network depth and feature extraction capability. Furthermore, the inclusion of the CBAM module enables the network to focus on salient information within the image, thus augmenting its feature representation capability. Our proposed algorithm achieves a [email protected] of 70.1% while significantly reducing the number of parameters and computational requirements to 51.83% and 64.73% of the original model, respectively. Compared to various lightweight models, our approach demonstrates competitive performance in terms of both computational efficiency and accuracy.

The critical systems, which the failure and malfunction may result in human, environment and financial severe damages, are essential components in various sectors and particularly in energy domains. Although unwished, integration error problems in supervision of critical systems occurs, incurring significant expenses because of operator’s subjective analysis and on hardware topology failures. In this work, a malleable model design approach is proposed to formulate and solve the integration error problem in the critical systems supervision in terms of reliability. A real Hybrid Power Plant (HPP) case is considered as a requirement for a study case with simulated data. A method framework with informal approach (C4 diagram) and formal approach (Hierarchical Coloured Petri Nets) in radial spectrum is applied to the HPP supervision design. Using formal methods, a formulation and solution to this problem through structured, scalable and compact mathematical representations are possible. This malleable model intends to guarantee functional correctness and then reliability of the plant supervision system based on system software architecture. Outcomes suggest corroboration that the malleable model is appropriate for energy domain, and can be used for other types of critical systems, bringing all the benefits of this methodology to the context in which it will be applied.

We propose a pricing formula for a defaultable zero-coupon bond with imperfect information under a regime-switching model using a structural form of credit risk modelling. While the value of the firm’s equity is observed continuously, we assume that the total value of the firm is only observed at discrete times, such as the dates of the release of the firm’s annual reports, or quarterly reports. This uncertainty about the true value of the firm results in credit spreads that do not approach zero as the debt approaches maturity, which is a problem with many structural models. The firm’s value is typically defined as its equity and debt; however, we consider the asset-to-equity ratio, an accounting ratio used to examine a firm’s financial well-being. A dependent regime-switching process models the components of this ratio, and the Markov chain represents the states of the economy. The main contribution is to study this problem when the dynamics of a firm’s assets have different parameters with regime changes.

Extracorporeal membrane oxygenation (ECMO) is increasingly used in intensive care units; however, ECMO can modify drug pharmacokinetics (PK), leading to underexposure and associated treatment failure. The aim of the present study was to determine the effect of ECMO on the PK of dexmedetomidine (DEX). In vivo rat models were developed, both of which involved a bolus injection of DEX and concentration monitoring. In the in vivo model experiment, rats which underwent ECMO were compared with a control group. PK analysis of in vivo data (noncompartmental analysis and nonlinear mixed-effects modelling) was carried out to determine the effect of ECMO. In vivo PK exploration showed that ECMO induced a decrease in DEX clearance. Because the effect of ECMO on the PK of DEX is not clinically significant, normal DEX dosing for critically ill patients should be effective for patients undergoing ECMO.

By introducing environmental mediator, for avoiding randomness in selecting indicators and subjectivity in deciding interaction path coefficients to reveal interaction mechanism among forest industry, ecology and environmental capacity, structural Pressure–State–Impact–Response (PSIR) and quantitative Structural Equation Modeling (SEM) are utilized with data on thirty–one provinces of China. We can find that: (i) forest industry has a negative influence on ecology, whereas ecology has a positive influence on industry; (ii) the destructive influence that industry has on ecology is much greater than the positive effect ecology has on industry; and (iii) environmental capacity plays a partial mediating role between industry and ecology. According to these results we can conclude that: (i) forest industry and ecology are not in a symbiotic relationship and have not reached a level of ecological security; (ii) the interaction between industry and ecology is in a period of transition from antagonistic to beneficial; and (iii) industry dominates ecology. However, we prospect the following advice: (i) methods of forest industry should be changed; (ii) new modes of industrial integration and circular economy should be developed; and (iii) the ability of the environment to sustain itself should be enhanced. The level of forest ecological security to discuss the symbiotic mechanism of industry and ecology will propose to be measured in future.

This article introduces an innovative design method for public lighting systems that surpasses the limitations of conventional approaches, which rely on predefined lamp characteristics and spatial arrangement. By employing a multi-criteria decision algorithm, our study proposes an optimal design methodology considering several key aspects, including the distance between lamps, their type, power, and light distribution. The goal is to achieve optimal illumination that enhances visibility on public roads for drivers and pedestrians while simultaneously minimizing glare, installation costs and maximizing energy efficiency. The proposed methodology is implemented through an algorithm developed in Matlab, with results validated through simulations in Dialux. This information is used to construct a decision matrix, assessed using the CRITIC method across 180 different scenarios within a specific case study. The findings demonstrate the effectiveness of multi-criteria decision-making as a tool for significantly improving the planning and design of lighting in public illumination systems, allowing for selecting the optimal combination of parameters that ensure the best lighting conditions.

The assortment of low-cost 3D printers for “in-practice” use, e.g., for clear aligner therapies, is ever increasing. To address concerns about the accuracy of orthodontic models produced on such printers when cost efficient modes of 3D printing are employed, this study examined the effect of print model body type and print angulation on accuracy. Six printing-configuration groups were included: 2 model types (solid or hollow shell) combined with 3 print angles (0°, 70°, or 90°) with 10 models/group; all models were printed with 100-µm layer thickness using a digital light processing-based 3-dimensional printer. Eleven selected structures and distances were measured on the printed models with a digital microscope and compared to the same measures on a digitized master model. The clinically-acceptability range was set at ±0.25 mm difference from the master model for single tooth measurements (intra-tooth) and ±0.5 mm for cross-arch measurements (inter-tooth). For individual measurements across all models, 98% fell within clinical acceptability. For mean measurements within each model group, only canine height for the shell-0° model had a mean difference (0.26 mm ± 0.03) outside the clinically acceptable range for intra-tooth measurements. Standard deviations for all intra-tooth measurements were within 0.07 mm. While none of the mean inter-tooth measurements exceeded the acceptability range, the standard deviations were larger (0.04 to 0.30 mm). Accuracy of orthodontic models for clear aligner therapies was not impacted beyond the clinically acceptable range when altering model body type and print angulation to improve efficiency of 3D printing. These findings suggest greater flexibility of the practitioner to alter print settings to address time and cost efficiency in various clinical scenarios and still maintain clinically acceptable model accuracy.

The correct selection of the value of p is a complex and iterative procedure that requires experience in the interpretation of the obtained interpolated maps. Inverse Distance Weighting is a method applied to the porosities of the K and L hydrocarbon reservoirs, discovered in the Neogene (Lower Pontian) subsurface sandstones in the northern Croatia (Pannonian Basin System). They represent small and large data samples. Also a standard statistical analysis of the data was made, followed by the qualitative-quantitative analysis of the maps, based on the selection of different values of the power distance exponent (p-value) for the K and L reservoirs maps. According to the qualitative analysis, for a small data set, p-value could be set on 1 or 2 giving the most optimal result, while for a large data set, a p value of 3 and 4 could be applied. By quantitative analysis, for the case of small data p=2 is recommended, resulting in a root mean square error value of 0.03458, a mean absolute error of 0.02013 and a median absolute deviation of 0.00546. Oppositely, a p-value of 3 and 4 is selected as appropriate for a large data set, with root mean square errors of 0.02435 and 0.02437, mean square errors of 0.01582 and 0.01509 and median absolute deviations 0.00896 and 0.00444. Eventually for a small data set, it is recommended to use a p-value of 2, and for a large data set, a p-value of 3 or 4.

In the intersection of the Internet of Things (IoT) and Machine Learning (ML), the choice between high-level and low-level programming libraries presents a significant dilemma for developers, impacting not only the efficiency and effectiveness of ML models but also their environmental footprint. We have proposed a comprehensive framework to aid in this decision-making process, underpinned by a detailed comparative analysis of both types of libraries on one of the key IoT ML task; image classification. We have introduced a novel algorithm designed to calculate the green footprint of ML model training, factoring in execution time, memory utilization, power consumption, and CPU temperature, addressing the urgent need for sustainable ML practices. Through an empirical evaluation of popular libraries such as PyTorch for high-level and Libtorch for low-level development, we have assessed their performance, development efficiency, and hardware compatibility. The culmination of our research is a decision support system that synthesizes the experimental findings to guide developers toward choices that harmonize model performance with environmental sustainability.

The traffic light detection and recognition are crucial for enhancing the security of unmanned systems. This study proposes a YOLOv5-based traffic light detection algorithm to tackle the challenges posed by small targets and complex urban backgrounds. Initially, the mosaic-9 method is employed to enhance the training dataset, thereby boosting the network’s ability to generalize and adapt to real-world scenarios. Furthermore, the network incorporates the Squeezed-and-Excitation (SE) attention mechanism to improve. Moreover, the YOLOv5 algorithm’s loss function has been optimized by substituting it with EIoU_loss, which addresses issues like missed detection and false alarms. Experimental results demonstrate that the model , trained with this enhanced network, achieves a 99.4% mAP on a custom dataset, which is 6.3% higher than the original YOLOv5, while maintaining a detection speed of 74 f/s. Therefore, this algorithm offers higher detection accuracy and effectively meets real-time operational requirements.

CAMx-LPiG (Comprehensive Air Quality Model with Extensions – Linear Plume in Grid) is an online hybrid model, based on the Chemistry and Transport Model (CTM) CAMx, that includes a sub-grid scale module to simulate the dispersion of linear road traffic emissions, called LPiG. LPiG is a plume in grid module specifically developed by extending the capabilities of the Lagrangian puff sub-grid model available in CAMx. The online integration of the local scale model within the Eulerian CTM allows for a multiscale simulation of air quality from the regional scale to the urban scale, preserving a coherent description of the chemical state of the atmosphere at all spatial scales and avoiding any double counting of the emissions simulated by the sub-grid module. In this work the model is presented and evaluated against measured NO2 concentrations for the city of Milan for the month of January 2017. The model is able to introduce road traffic induced gradient in NO2 concentration at sub-grid resolution. Moreover, CAMx-LPiG is shown to reduce the bias compared to CAMx stand-alone simulations.

To address the problems of insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, attention mechanism, and self-attention mechanism, the proposed model achieves comprehensive semantic fusion between text and questions. The probabilities distribution of answers is computed using Softmax. Experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.