Search

Machine learning models are widely used to decide whether to accept or reject credit loan applications. However, similarly to human‐based decisions, they may discriminate between special groups of applicants, for instance based on age, gender, and race. In this paper, we aim to understand whether machine learning credit lending models are biased in a real case study, that concerns borrowers asking for credits in different regions of the United States. We show how to measure model fairness using different metrics, and we explore the capability of explainable machine learning to add further insights. From a constructive viewpoint, we propose a propensity matching approach that can improve fairness. [ABSTRACT FROM AUTHOR]

Accurate rainfall measurement with a precise spatial and temporal resolution is essential for making informed decisions during disasters and conducting scientific studies, particularly in regions characterized by intricate terrain and limited coverage of automated weather stations. Retrieval of precipitation with satellite is currently the most effective means to obtain precipitation over large‐scale areas. The key to enhancing the accuracy of precipitation estimation and forecasting in regions with complex terrain lies in effectively integrating satellite data with topographic information. This paper introduces a deep learning approach called AttUnet_R_SFT that utilizes high temporal, spatial, and spectral resolution data obtained from the Fengyun 4A satellite, and incorporates the Deep Spatial Feature Transform (SFT) layer to incorporate geographical data for estimating half‐hourly precipitation in northeastern China. We assess it by compared to operational near‐real‐time satellite precipitation products demonstrated to be successful in estimating precipitation and baseline deep learning models. According to the experimental findings, the AttUnet_R_SFT model outperforms practical precipitation products and baseline deep learning models in both identifying and estimating precipitation. The main enhancement of the model performance is shown in the windward slope of the Greater Khingan Mountains as a result of the successful incorporation of geographical data. Hence, the suggested framework holds the capability to function as a superior and dependable satellite‐derived precipitation estimation solution in regions characterized by intricate terrain and infrequent rainfall. The findings of this study indicate that the utilization of deep learning algorithms for satellite precipitation estimation shows potential as a fruitful avenue for further research. Plain Language Summary: A deep learning model named AttUnet_R_SFT is proposed, which use high temporal, spatial and spectral resolution data from the Fengyun 4A satellite, and combines with the Deep Spatial Feature Transform (SFT) layer to input geographic information for half‐hourly precipitation estimation in the complex terrain region represented by northeast China. The model can provide a reference for improving the performance of precipitation estimation in areas with complex topography. Key Points: A deep‐learning model is proposed to effectively fuse satellite multispectral data of the Fengyun 4A satellite, with topographic informationHalf‐hourly precipitation is estimated with higher temporal resolution, which is closer to the operational needs of weather forecastingAs precipitation in the study area is a non‐high‐frequency event, data enhancement is attempted to use and obtain effective results [ABSTRACT FROM AUTHOR]

Inversion of magnetic basement interfaces in basins is essential for interpreting potential field data and studying geothermal resource distribution, as well as basin formation and evolution. This paper introduces a novel method for inverting magnetic basement interfaces using a random forest regression (RFR) algorithm that combines potential field processing and machine learning techniques. The method creates magnetic base interface models and corresponding magnetic anomaly data through the random midpoint displacement method and magnetic interface finite element forward simulation. These anomalies are then processed using techniques such as directional transformations, analytical continuation, spatial derivatives, and fractional transformations. Feature attributes are extracted, and Gini importance is utilized to measure the contributions of feature factors, identify effective features, and enhance algorithm efficiency. The validity and practicality of the method are demonstrated through the analysis of both idealized and noisy models. The proposed machine learning‐based approach is more intelligent, efficient, and accurately represents the relief of magnetic base interfaces. When applied to magnetic survey data in the Datong Basin, it produced a reliable basin base model that aligns with known structural information, paving the way for further research in magnetic interface inversion. Key Points: A machine learning method based on random forest regression algorithm is used to recover the relief of the magnetic basement interface by using high‐precision magnetic dataApplying potential field processing and transformation to feature extraction for machine learningThe proposed technique intelligently and efficiently restores the 3D relief of the magnetic basement interface, and it has been successfully implemented in the Datong Basin's Tianzhen‐Yanggao sag [ABSTRACT FROM AUTHOR]

Macromolecular crystallography contributes significantly to understanding diseases and, more importantly, how to treat them by providing atomic resolution 3D structures of proteins. This is achieved by collecting X‐ray diffraction images of protein crystals from important biological pathways. Spotfinders are used to detect the presence of crystals with usable data, and the spots from such crystals are the primary data used to solve the relevant structures. Having fast and accurate spot finding is essential, but recent advances in synchrotron beamlines used to generate X‐ray diffraction images have brought us to the limits of what the best existing spotfinders can do. This bottleneck must be removed so spotfinder software can keep pace with the X‐ray beamline hardware improvements and be able to see the weak or diffuse spots required to solve the most challenging problems encountered when working with diffraction images. In this paper, we first present Bragg Spot Detection (BSD), a large benchmark Bragg spot image dataset that contains 304 images with more than 66000 spots. We then discuss the open source extensible U‐Net‐based spotfinder Bragg Spot Finder (BSF), with image pre‐processing, a U‐Net segmentation backbone, and post‐processing that includes artifact removal and watershed segmentation. Finally, we perform experiments on the BSD benchmark and obtain results that are (in terms of accuracy) comparable to or better than those obtained with two popular spotfinder software packages (Dozor and DIALS), demonstrating that this is an appropriate framework to support future extensions and improvements. [ABSTRACT FROM AUTHOR]

The development of fragility curves is an important step in seismic risk assessment within the scope of performance‐based earthquake engineering. The goal of this work is to use machine learning methods (regression‐based tools) to forecast the large‐span precast parking structural responses and fragility curves. This study proposes five predicting models based on machine learning to evaluate the seismic performance of the large‐span precast parking structures, including: neural networks, genetic algorithm‐based neural networks, support vector machine, decision tree and random forest. A database that includes 453 numerical synthetic results was used to train and test the machine learning models. The seismic performance of large‐span precast parking structures were predicted using the constructed machine learning models. Finally, the sensitivity analysis of input parameters was conducted. From this paper we can conclude that: (1) the genetic optimization‐based neural networks' predicting model has the most accurate predictive ability for seismic fragility estimation and (2) the structural responses and the fragility curves of parking structures are related to the differences of the stiffness of the connectors and the number of floors, of which the stiffness of the connectors should be given special attention. [ABSTRACT FROM AUTHOR]

Cost‐sensitive ensemble learning as a combination of two approaches, ensemble learning and cost‐sensitive learning, enables generation of cost‐sensitive tree‐based ensemble models using the cost‐sensitive decision tree (CSDT) learning algorithm. In general, tree‐based models characterize nice graphical representation that can explain a model's decision‐making process. However, the depth of the tree and the number of base models in the ensemble can be a limiting factor in comprehending the model's decision for each sample. The CSDT models are widely used in finance (e.g., credit scoring and fraud detection) but lack effective explanation methods. We previously addressed this gap with cost‐sensitive tree Shapley Additive Explanation Method (CSTreeSHAP), a cost‐sensitive tree explanation method for the single‐tree CSDT model. Here, we extend the introduced methodology to cost‐sensitive ensemble models, particularly cost‐sensitive random forest models. The paper details the theoretical foundation and implementation details of CSTreeSHAP for both single CSDT and ensemble models. The usefulness of the proposed method is demonstrated by providing explanations for single and ensemble CSDT models trained on well‐known benchmark credit scoring datasets. Finally, we apply our methodology and analyze the stability of explanations for those models compared to the cost‐insensitive tree‐based models. Our analysis reveals statistically significant differences between SHAP values despite seemingly similar global feature importance plots of the models. This highlights the value of our methodology as a comprehensive tool for explaining CSDT models. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) is a distributed machine learning paradigm that enables multiple data holders to collaborate on building machine learning models while preserving the privacy of their data. FL can be categorized as horizontal or vertical, depending on the distribution characteristics of the data. Specifically, horizontal FL uses data partitioned in the sample space, whereas vertical FL uses data partitioned in the feature space. Traditional vertical FL methods aim to facilitate collaboration among clients to infer a single global target. However, these methods may be impractical because each client often has a unique target to be inferred. In this paper, we propose a novel vertical FL method, called personalized vertical federated learning (pvFed), which addresses this limitation by allowing each client to perform inferences specific to their individual task. To the best of our knowledge, no existing method currently addresses this limitation. The objective of pvFed is to construct a global model that generates a representation vector to support client inference. The global model, constructed using distillation and dimensionality reduction, takes a sample ID common to all clients as input and outputs a sample‐specific representation vector. Clients utilize the intermediate representation of their own model and the representation vectors output by the global model for inference. Because these vectors are not dependent on client‐specific tasks, clients can repurpose them for any additional tasks. Our experiments, conducted on two distinct data types—image and tabular data sets, under a vertical partitioning where each client had its own specific task, demonstrated the efficacy of vectors generated by the global model in pvFed for client inference. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Background: Malnutrition is associated with increased morbidity, mortality, and healthcare costs. Early detection is important for timely intervention. This paper assesses the ability of a machine learning screening tool (MUST‐Plus) implemented in registered dietitian (RD) workflow to identify malnourished patients early in the hospital stay and to improve the diagnosis and documentation rate of malnutrition. Methods: This retrospective cohort study was conducted in a large, urban health system in New York City comprising six hospitals serving a diverse patient population. The study included all patients aged ≥ 18 years, who were not admitted for COVID‐19 and had a length of stay of ≤ 30 days. Results: Of the 7736 hospitalisations that met the inclusion criteria, 1947 (25.2%) were identified as being malnourished by MUST‐Plus‐assisted RD evaluations. The lag between admission and diagnosis improved with MUST‐Plus implementation. The usability of the tool output by RDs exceeded 90%, showing good acceptance by users. When compared pre‐/post‐implementation, the rate of both diagnoses and documentation of malnutrition showed improvement. Conclusion: MUST‐Plus, a machine learning‐based screening tool, shows great promise as a malnutrition screening tool for hospitalised patients when used in conjunction with adequate RD staffing and training about the tool. It performed well across multiple measures and settings. Other health systems can use their electronic health record data to develop, test and implement similar machine learning‐based processes to improve malnutrition screening and facilitate timely intervention. Key points/Highlights: Malnutrition is prevalent among hospitalised patients and frequently goes unrecognised, with the potential for severe sequelae. Accurate diagnosis, documentation and treatment of malnutrition have the potential of having a positive impact on morbidity rate, mortality rate, length of inpatient stay, readmission rate and hospital revenue. The tool's successful application highlights its potential to optimise malnutrition screening in healthcare systems, offering potential benefits for patient outcomes and hospital finances. [ABSTRACT FROM AUTHOR]

Summary: To ensure smooth power exchange in a three‐phase inverter, it is important to accurately detect the faults of insulated gate bipolar transistor (IGBT) switches. However, the fault characteristics of power tubes are complex, the fault diagnosis results are affected by the load, and the recognition accuracy of some fault diagnosis models is low. To tackle this issue, this paper proposes an inverter open circuit fault diagnosis method named SR‐WOA‐ELM, which integrates signal reconstruction (SR), the whale optimization algorithm (WOA), and an extreme learning machine (ELM). First, the three‐phase output current is processed by the signal reconstruction method to eliminate the effect of load fluctuation, the average value of low frequency coefficients and wavelet entropy is extracted from the reconstructed three‐phase currents using the improved wavelet packet transform, and the fault feature vector is constructed by fusing the above two feature parameters. Second, the parameters of the ELM fault diagnosis model are optimized using WOA. Finally, the fault feature vector is added in the SR‐WOA‐ELM model to obtain the fault diagnosis results. Through simulation and experimental verification, the model can accurately identify the single‐tube and double‐tube faults of the inverter and is not affected by load fluctuations. [ABSTRACT FROM AUTHOR]

WeatherBench 2 is an update to the global, medium‐range (1–14 days) weather forecasting benchmark proposed by (Rasp et al., 2020, https://doi.org/10.1029/2020ms002203), designed with the aim to accelerate progress in data‐driven weather modeling. WeatherBench 2 consists of an open‐source evaluation framework, publicly available training, ground truth and baseline data as well as a continuously updated website with the latest metrics and state‐of‐the‐art models: https://sites.research.google/weatherbench. This paper describes the design principles of the evaluation framework and presents results for current state‐of‐the‐art physical and data‐driven weather models. The metrics are based on established practices for evaluating weather forecasts at leading operational weather centers. We define a set of headline scores to provide an overview of model performance. In addition, we also discuss caveats in the current evaluation setup and challenges for the future of data‐driven weather forecasting. Plain Language Summary: Traditionally, weather forecasts are made by models that attempt to replicate the physical processes of the atmosphere. This has been very successful over the last few decades as better computers, better observations and model upgrades have lead to steadily improving weather forecasts. However, with rapid advances in artificial intelligence (AI), the question can be asked whether one can simply learn a weather model from past observations or reanalyzes. In the last couple of years, we have seen tremendous progress with state‐of‐the‐art AI models rivaling the best "traditional" weather models in skill. WeatherBench 2 is a benchmark data set designed to evaluate and compare the quality of AI and traditional models. By setting a standard for evaluation, alongside providing open‐source data and code, this project aims to accelerate this research direction and lead to better weather prediction. Key Points: WeatherBench 2 is a framework for evaluating and comparing data‐driven and traditional numerical weather forecasting modelsIt provides an evaluation framework, publicly available data sets and a website to assess the state‐of‐the‐art weather modelsThe evaluation protocol has been designed following best practices established in the operational weather forecasting community [ABSTRACT FROM AUTHOR]

Background: The use of artificial intelligence (AI) is increasing in many areas of healthcare, including mental healthcare. The automated nature of such technologies has the potential to be developed to work with large numbers of people. This paper examines the way that student therapists experience using an interactive text‐based machine client as a training tool. Methodology: Chatbot technology has been used to develop an emotionally responsive interactive client (ERIC). This introduces individuals to concepts of person‐centred therapy (empathy, congruence and unconditional positive regard) by using a series of pre‐programmed scenarios. Twenty‐eight student therapists evaluated ERIC's potential as a learning tool. Individuals were recruited from one university from a postgraduate and an undergraduate counselling programme. Findings: Feedback was generally positive, with all reporting that they enjoyed engaging with ERIC as a learning method. ERIC helped individuals consider their understanding of counselling skills in a non‐judgemental environment. Participants felt the scenarios were realistic and engaging, with many reporting that they felt they were engaging with a real client/person due to ERIC's ability to express emotions. Discussion: ERIC is at the proof‐of‐concept phase. From the feedback presented here, it is evident that it can be a useful learning tool. Further development of ERIC with feedback from a larger sample is, however, required. ERIC is currently a text‐based client, and further development would like to see the intervention be voice‐activated to enhance the experience. ERIC can be further enhanced and adapted to be a useful learning platform for student therapists, as well as for students in other (healthcare‐related) disciplines, whereby a client or patient is required. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method based on continuum damage mechanics (CDM) and machine learning (ML) models to evaluate the vibration fatigue behavior of W1‐type railway fastener clips subjected to high‐frequency vibration. Firstly, static and fatigue tests are conducted on 60Si2Mn spring steel to acquire elastic modulus, tensile strength, and P‐S‐N curves. Subsequently, a CDM model is established, and numerical simulations are performed under various working conditions to obtain the fatigue characteristics of the clips. Finally, the ML model is trained using numerical simulation results, thereby establishing a mapping model between the working conditions and fatigue characteristics. The developed ML model demonstrates high accuracy in predicting the vibration fatigue life of the clips. Moreover, the Shapley Additive Explanations (SHAP) algorithm is employed to elucidate the ML model, revealing that the vibration frequency has a greater impact on the fatigue life of the clips compared to the vibration displacement. Highlights: A novel approach is developed for vibration fatigue assessment of fastener clip.The approach effectively combines the continuum damage model and ML (ANN) model.Static and fatigue tests of 60Si2Mn spring steel are conducted.Fatigue characteristic of clips subjected to high‐frequency vibration is studied. [ABSTRACT FROM AUTHOR]

The action responses of controlled mechanisms are often multiparametric, nonlinear, and uncertain. Complex dynamics and limited uncertain information pose difficulties for action reliability analysis. This paper develops an adaptive intelligent extremum surrogate model (AIESM) method for the action reliability under random‐interval hybrid uncertainty of a chain conveyor. First, a dynamic model of the chain conveyor is established, which considers the impact and frictional effects within the mechanical system, the regulating effects of the control system, and the external disturbances of the system. After that, a hybrid kernel extreme learning machine optimized by the sparrow search algorithm is employed as an intelligent surrogate model to construct the initial surrogate model from the hybrid uncertain variables to the limit state function (LSF) response and the extremum surrogate model (ESM) from the random variables to the LSF extremum response. An adaptive infilling strategy combining active learning and opposition‐based learning is applied to improve the accuracy and efficiency of the ESM and reduce the estimation error of action reliability. Finally, the action reliability interval bounds are obtained by Monte Carlo simulation based on the ESM. Two numerical examples are presented to illustrate the validity of the AIESM method. The action reliability interval of the chain conveyor provided by the proposed method is [0.9706, 0.9923]. [ABSTRACT FROM AUTHOR]

In carbonate reservoirs characterized by the fracture‐cavity system as storage spaces, the drilling process is highly prone to the loss of drilling fluid. This not only affects drilling efficiency but can also lead to severe accidents, such as blowouts. Therefore, it is crucial to understand the distribution pattern of these fractures. However, the formation of carbonate rock fracture‐cavity system systems, being controlled by various factors, is difficult to precisely identify. This limitation hampers the efficient development of such types of oil and gas fields. This paper presents a case study of the M55 sub‐section carbonate gas reservoir in the Sulige gasfield, proposing an improved You Only Look Once v5s (YOLOv5s) deep learning algorithm. It utilizes enhanced training with conventional logging data to identify response characteristics of fractures in the carbonate reservoirs. And its identification results have been confirmed to be accurate by various fracture data obtained through different means, such as the core samples, cast thin section photographs, imaging logging data, and seismic attributes. This method incorporates the Ghost convolution module to replace the Conv module in the backbone network of the YOLOv5s model, and modifies the C3 module into a Ghost Bottleneck module, effectively making the model more lightweight. Additionally, a Convolutional Block Attention Module is integrated into the Neck network, enhancing the model's feature extraction capabilities. Finally, the method employs the Efficient Intersection over Union Loss function instead of the Complete Intersection over Union Loss, reducing the network's regression loss. The validation results using actual data demonstrate that this method achieves an average recognition accuracy of 87.3% for the fracture‐cavity system, which is a 3% improvement over the baseline model (YOLOv5s). This enhancement is beneficial for precisely locating the drilling fluid loss positions in carbonate reservoirs. [ABSTRACT FROM AUTHOR]

Background: Learning analytics (LA) research often aggregates learning process data to extract measurements indicating constructs of interest. However, the warranty that such aggregation will produce reliable measurements has not been explicitly examined. The reliability evidence of aggregate measurements has rarely been reported, leaving an implicit assumption that such measurements are free of errors. Objectives: This study addresses these gaps by investigating the psychometric pros and cons of aggregate measurements. Methods: This study proposes a framework for aggregating process data, which includes the conditions where aggregation is appropriate, and a guideline for selecting the proper reliability evidence and the computing procedure. We support and demonstrate the framework by analysing undergraduates' academic procrastination and programming proficiency in an introductory computer science course. Results and Conclusion: Aggregation over a period is acceptable and may improve measurement reliability only if the construct of interest is stable during the period. Otherwise, aggregation may mask meaningful changes in behaviours and should be avoided. While selecting the type of reliability evidence, a critical question is whether process data can be regarded as repeated measurements. Another question is whether the lengths of processes are unequal and individual events are unreliable. If the answer to the second question is no, segmenting each process into a fixed number of bins assists in computing the reliability coefficient. Major Takeaways: The proposed framework can be a general guideline for aggregating process data in LA research. Researchers should check and report the reliability evidence for aggregate measurements before the ensuing interpretation. Lay Description: What is currently known about this topic: Aggregating learning process data is common in learning analytics.The psychometric pros and cons of aggregating process data are rarely examined. What this paper adds: If the construct of interest is stable during a period, aggregation over this period is desirable.Aggregation over a long period masks meaningful changes in learning behaviours.A guideline for choosing proper reliability coefficients for aggregate measurements is proposed.Methods for computing reliability estimates when processes vary in length are provided. Implications for practice: Report reliability evidence for aggregate measurements for the sake of psychometric rigour.A short period causes unreliable action‐related indicators in learning analytics dashboards.A long period causes inaccurate indicators of learners' current state. [ABSTRACT FROM AUTHOR]

Material science has historically evolved in tandem with advancements in technologies for characterization, synthesis, and computation. Another type of technology to add to this mix is machine learning (ML) and artificial intelligence (AI). Now increasingly sophisticated AI‐models are seen that can solve progressively harder problems across a variety of fields. From a material science perspective, it is indisputable that machine learning and artificial intelligence offer a potent toolkit with the potential to substantially accelerate research efforts in areas such as the development and discovery of new functional materials. Less clear is how to best harness this development, what new skill sets will be required, and how it may affect established research practices. In this paper, those question are explored with respect to increasingly more sophisticated ML/AI‐approaches. To structure the discussion, a conceptual framework of an AI‐ladder is introduced. This AI‐ladder ranges from basic data‐fitting techniques to more advanced functionalities such as semi‐autonomous experimentation, experimental design, knowledge generation, hypothesis formulation, and the orchestration of specialized AI modules as stepping‐stones toward general artificial intelligence. This ladder metaphor provides a hierarchical framework for contemplating the opportunities, challenges, and evolving skill sets required to stay competitive in the age of artificial intelligence. [ABSTRACT FROM AUTHOR]

Literature screening is the process of identifying all relevant records from a pool of candidate paper records in systematic review, meta-analysis, and other research synthesis tasks. This process is time consuming, expensive, and prone to human error. Screening prioritization methods attempt to help reviewers identify most relevant records while only screening a proportion of candidate records with high priority. In previous studies, screening prioritization is often referred to as automatic literature screening or automatic literature identification. Numerous screening prioritization methods have been proposed in recent years. However, there is a lack of screening prioritization methods with reliable performance. Our objective is to develop a screening prioritization algorithm with reliable performance for practical use, for example, an algorithm that guarantees an 80% chance of identifying at least 80% of the relevant records. Based on a target-based method proposed in Cormack and Grossman, we propose a screening prioritization algorithm using sampling with replacement. The algorithm is a wrapper algorithm that can work with any current screening prioritization algorithm to guarantee the performance. We prove, with mathematics and probability theory, that the algorithm guarantees the performance. We also run numeric experiments to test the performance of our algorithm when applied in practice. The numeric experiment results show this algorithm achieve reliable performance under different circumstances. The proposed screening prioritization algorithm can be reliably used in real world research synthesis tasks. [ABSTRACT FROM AUTHOR]

This paper aims to explore machine learning techniques for post‐processing high‐resolution Numerical Weather Prediction (NWP) products for the early detection of convection. Data from the Arome Ensemble Prediction System and satellite observations from the Rapidly Developing Thunderstorm (RDT) product by Météo‐France are used to train a recurrent neural network model to predict areas of total convection and moderate convection. The learning task is formulated as a binary classification problem using a long short‐term memory (LSTM) network architecture. Results from the LSTM model are compared with an object‐based probabilistic approach to forecast convection using metrics such as a receiver operating characteristics (ROC) curve, the Brier score and reliability. Results indicate that the LSTM model performs similarly to the object‐based probabilistic benchmark when classifying moderate convection areas and shows improved skill when classifying areas of total convective. Finally, the LSTM model results are presented within an air traffic management context to showcase the potential use of machine learning models within an operational application. [ABSTRACT FROM AUTHOR]

On the one hand, unemployment is known to have detrimental effects on individuals' mental health. On the other hand, poor mental health reduces re‐employment chances quite drastically, creating a vicious cycle. Active labour market policies (ALMPs) such as training programs or wage subsidies have been shown to ameliorate negative effects on mental health and improve labour market integration on average for the general unemployed population. In the context of individuals with severe mental health issues, however, it is unclear whether these interventions can be expected to deliver similar positive effects. In fact, one may argue that they have the potential to worsen employment prospects of individuals by adding additional stress to their pre‐existing mental health problems. Hence, this paper estimates the long‐term causal effects of ALMPs on the labour market integration of individuals with self‐reported severe mental health issues and compares estimates to individuals without such issues using unique combined survey and administrative data. Effects are estimated using the innovative double machine learning method and show that ALMPs do not only improve labour market integration of unemployed individuals with severe mental health issues, but they do so more effectively than for other unemployed individuals. [ABSTRACT FROM AUTHOR]

This research paper delves into the security concerns within Internet of Things (IoT) networks, emphasizing the need to safeguard the extensive data generated by interconnected physical devices. The presence of anomalies and faults in the sensors and devices deployed within IoT networks can significantly impact the functionality and outcomes of IoT systems. The primary focus of this study is the identification of anomalies in IoT devices arising sensor tampering, with an emphasis on the application of machine learning techniques. While supervised methods like one‐class SVM, Gaussian Naive Bayes, and XG Boost have proven effective in anomaly detection, there has been a noticeable scarcity of research employing unsupervised methods. This scarcity is mainly attributed to the absence of well‐defined ground truths for model training. This research takes an innovative approach by investigating the utility of unsupervised algorithms, including Isolation Forest and Local Outlier Factor, alongside supervised techniques to enhance the precision of anomaly detection. [ABSTRACT FROM AUTHOR]

Summary: This paper presents an extended version of Deeper, a search‐based simulation‐integrated test solution that generates failure‐revealing test scenarios for testing a deep neural network‐based lane‐keeping system. In the newly proposed version, we utilize a new set of bio‐inspired search algorithms, genetic algorithm (GA), (μ+λ) and (μ,λ) evolution strategies (ES), and particle swarm optimization (PSO), that leverage a quality population seed and domain‐specific crossover and mutation operations tailored for the presentation model used for modeling the test scenarios. In order to demonstrate the capabilities of the new test generators within Deeper, we carry out an empirical evaluation and comparison with regard to the results of five participating tools in the cyber‐physical systems testing competition at SBST 2021. Our evaluation shows the newly proposed test generators in Deeper not only represent a considerable improvement on the previous version but also prove to be effective and efficient in provoking a considerable number of diverse failure‐revealing test scenarios for testing an ML‐driven lane‐keeping system. They can trigger several failures while promoting test scenario diversity, under a limited test time budget, high target failure severity, and strict speed limit constraints. [ABSTRACT FROM AUTHOR]

Software effort estimation is a vital process in the software industry for successfully administering 5Ds of the software development life cycle (SDLC). The 5Ds stand for demand, development, direction, deployment, and designated cost of the software. Software development effort estimation (SDEE) is an effort prediction mechanism to calculate the effort for the development of the software product in order to minimize the challenges in the software field. Academics and practitioners are striving to identify which machine learning estimation technique yields more accurate results based on evaluation metrics, datasets, and other pertinent aspects. The feature selection techniques impact accuracy by selecting the main and relevant features in the dataset and eliminating the redundant and irrelevant features in the dataset. To achieve accurate estimations, the paper utilizes feature selection algorithms, along with various machine learning techniques, which predict the desired effort and the performance of the model has been measured in terms of prediction accuracy, R2 value, relative error, and mean absolute error. The datasets China and Maxwell are trained with the relevant features by applying feature selection algorithms, and estimation techniques are applied to predict the effort. The performance is compared with the regression models and feature selection techniques utilized by many authors previously. The result of the proposed methodology significantly gives the best performance with the combination of feature selection and estimation models than all regression models when applied alone, to both datasets. From the results, it is perceptible that random forest is performing well with the feature selection techniques and obtains the highest prediction accuracy of 99.33% with the China and 89.47% with the Maxwell datasets. [ABSTRACT FROM AUTHOR]

Interpreting a seemingly simple function word like "or," "behind," or "more" can require logical, numerical, and relational reasoning. How are such words learned by children? Prior acquisition theories have often relied on positing a foundation of innate knowledge. Yet recent neural‐network‐based visual question answering models apparently can learn to use function words as part of answering questions about complex visual scenes. In this paper, we study what these models learn about function words, in the hope of better understanding how the meanings of these words can be learned by both models and children. We show that recurrent models trained on visually grounded language learn gradient semantics for function words requiring spatial and numerical reasoning. Furthermore, we find that these models can learn the meanings of logical connectives and and or without any prior knowledge of logical reasoning as well as early evidence that they are sensitive to alternative expressions when interpreting language. Finally, we show that word learning difficulty is dependent on the frequency of models' input. Our findings offer proof‐of‐concept evidence that it is possible to learn the nuanced interpretations of function words in a visually grounded context by using non‐symbolic general statistical learning algorithms, without any prior knowledge of linguistic meaning. [ABSTRACT FROM AUTHOR]

Calculating the elastic and mechanical characteristics of non‐crystalline solids can be challenging due to the high computational cost of ab initio methods and the low accuracy of empirical potentials. This paper proposes a computational technique for efficient calculations of mechanical properties of polycrystals, composites, and multi‐phase systems from atomistic simulations with high accuracy and reasonable computational cost. The calculated elastic moduli of polycrystalline diamond and their dependence on grain size are determined using a developed approach based on actively learned machine learning interatomic potentials (MLIPs). These potentials are trained on local fragments of the polycrystalline system, and ab initio calculations are used to compute forces, stresses, and energies. This technique allows researchers to perform extensive calculations of the mechanical properties of complex solids with different compositions and structures, achieving high accuracy and facilitating the transition from ideal (single crystal) systems to more realistic ones. [ABSTRACT FROM AUTHOR]

As one of the classic tasks in information retrieval, the core of image retrieval is to identify the images sharing similar features with a query image, aiming to enable users to find the required information from a large number of images conveniently. Street view image retrieval, in particular, finds extensive applications in many fields, such as improvements to navigation and mapping services, formulation of urban development planning scheme, and analysis of historical evolution of buildings. However, the intricate foreground and background details in street view images, coupled with a lack of attribute annotations, render it among the most challenging issues in practical applications. Current image retrieval research mainly uses the visual model that is completely dependent on the image visual features, and the multimodal learning model that necessitates additional data sources (e.g., annotated text). Yet, creating annotated datasets is expensive, and street view images, which contain a large amount of scene texts themselves, are often unannotated. Therefore, this paper proposes a deep unsupervised learning algorithm that combines visual and text features from image data for improving the accuracy of street view image retrieval. Specifically, we employ text detection algorithms to identify scene text, utilize the Pyramidal Histogram of Characters encoding predictor model to extract text information from images, deploy deep convolutional neural networks for visual feature extraction, and incorporate a contrastive learning module for image retrieval. Upon testing across three street view image datasets, the results demonstrate that our model holds certain advantages over the state‐of‐the‐art multimodal models pre‐trained on extensive datasets, characterized by fewer parameters and lower floating point operations. Code and data are available at https://github.com/nwuSY/svtRetrieval. [ABSTRACT FROM AUTHOR]

Selecting designs that efficiently optimize multiple objectives simultaneously is an important problem in several distinct industries. Typically, there is not a single ideal design; rather, there are several Pareto‐optimal designs that provide the best possible trade‐offs between the objectives. However, evaluating every design might be expensive, making a thorough search for the whole Pareto optimum set impractical. The aforementioned issue with technology computer‐aided design (TCAD) while investigating a multidimensional parameter set for device design is addressed using Pareto active learning (PAL) and the nondominated sorting genetic algorithm‐III (NSGA‐III) which are metaheuristics‐based multiobjective optimization (MOO) techniques. NSGA‐III adeptly analyzes the tradeoffs among multiple objectives while ensuring diversity in the design space. PAL forecasts the Pareto‐optimal set with intelligence by deliberately sampling the design space. This work focusses on improving the performance of surrounding gate tunnel field‐effect transistors (SGTFETs) by optimizing and assessing their complex designs in terms of multiple objectives, including power, energy, speed, and variability. This paper presents a novel MOO framework that incorporates machine learning (ML) approaches, including NSGA‐III and PAL in SGTFETs technology. The framework provides effective global optimization without gradients, allowing for the automatic recognition of the best solutions. The outcomes show the possibility of ML‐based MOO to create next‐generation nanoscale transistors. [ABSTRACT FROM AUTHOR]

Microplastics (MPs) are present not only in the environment but also in drinking water, food, and consumer products. These MPs being toxic, carcinogenic, endocrine disrupting, and genetic risk creators cause several diseases. Despite various approaches, the development of onsite applicable, facile, and quick MP detection methods is still challenging. Here, 3D‐plasmonic gold nanopocket (3D‐PGNP) nanoarchitecture is formed on a paper substrate for simultaneous MP filtration and detection. The paper‐based 3D‐PGNP is integrated with a syringe filter device, and then, MP‐containing solutions are injected through the syringe. Subsequent detection of the MPs using the surface‐enhanced Raman scattering (SERS) successfully identifies the MPs without pretreatment. The interface and volumetric hotspot generation of 3D‐PGNP around the captured MPs significantly improves the sensitivity, which is confirmed by finite‐difference time‐domain simulation. Then, the SERS mapping images obtained from a portable Raman spectrometer are transformed into digital signals via machine learning (ML) technique to identify and quantify the MP distribution. The developed SERS‐ML‐based MP detection method is applied for mixture MPs and for real matrix samples, demonstrating that the method provides improved accuracy. This system is expected to be used for various MPs detection and for environmentally hazardous substances, such as bacteria, viruses, and fungi. [ABSTRACT FROM AUTHOR]

Advances in data assimilation (DA) methods and the increasing amount of observations have continuously improved the accuracy of initial fields in numerical weather prediction during the last decades. Meanwhile, in order to effectively utilize the rapidly increasing data, Earth scientists must further improve DA methods. Recent studies have introduced machine learning (ML) methods to assist the DA process. In this paper, we explore the potential of a four‐dimensional variational (4DVar) constrained neural network (NN) method for accurate DA. Our NN is trained to approximate the solution of the variational problem, thereby avoiding the need for expensive online optimization when generating the initial fields. In the context that the full‐field system truths are unavailable, our approach embeds the system's kinetic features described by a series of analysis fields into the NN through a 4DVar‐form loss function. Numerical experiments on the Lorenz96 physical model demonstrate that our method can generate better initial fields than most traditional DA methods at a low computational cost, and is robust when assimilating observations with higher error outside of the distributions where it is trained. Furthermore, our NN‐based DA model is effective against Lorenz96 physical models with larger variable numbers. Our approach exemplifies how ML methods can be leveraged to improve both the efficiency and accuracy of DA techniques. Plain Language Summary: The use of machine learning (ML) to approximate mappings from data has made a significant impact on numerical weather prediction. In the data assimilation (DA) process, several recent studies have applied ML to accelerate or improve the accuracy of DA output. In this paper, we investigate the potential of employing physical constraints based on four‐dimensional variational (4DVar) DA to further enhance the accuracy of an end‐to‐end ML‐based DA model. Our objective is to determine whether the 4DVar‐constrained ML model can perform the DA task more efficiently and produce comparable accuracy to the traditional DA methods. We trained our NN‐based model without true values as labels and tested it on the Lorenz96 physical model. Several experiments have been applied to verify that the 4DVar‐constrained ML model can be used as a potential substitute for the DA process. Key Points: A physics‐informed neural network trained without ground truths can provide accurate initial fields for numerical predictionsThe system's kinetic features are embedded into the model through our four‐dimensional variational form loss functionWe show on Lorenz96 that the proposed method can be used directly for accurate data assimilation as a low computational cost [ABSTRACT FROM AUTHOR]

This article introduces a special issue on machine learning (ML) applications in geophysical exploration and monitoring. ML techniques have shown promise in streamlining workflows, extracting insights from large datasets, and solving computational problems in geophysics. The special issue includes 17 papers covering a range of geophysical applications, such as seismic data processing, electromagnetic inversion, and well logging. These papers demonstrate the current state of ML applications in geophysics and highlight challenges and potential directions for future research. The hope is that this special issue will serve as a valuable resource for geophysicists interested in ML techniques and their applications in geophysics. [Extracted from the article]

Sleep affects the functioning of all biological processes in the human body. Sleep disorders disrupt the well‐being of an individual and can potentially lead to other health complications. It affects a large part of the population, and their timely and efficient detection is crucial for improving the quality of health. Sleep disorders are generally analyzed using polysomnogram (PSG) signals, which must be captured in sophisticated laboratory settings. However, electrocardiogram (ECG) signals provide information about the electrical activity of the heart, which is strongly linked with disturbances in sleep and can be used as an indicator of disordered sleep. Along with that, the recording of ECG signals is much easier than other signals and can be done remotely without causing any significant disturbance to the subject. This brings practicality to the systems that are already being employed for sleep disorder detection. In this paper, we present a method for identifying types of sleep disorders using ECG signals. The objective of this paper is to investigate the use of ECG signals for the automated identification of insomnia, narcolepsy, periodic leg movement (PLM), rapid eye movement (REM) behavior disorder (RBD), and nocturnal frontal lobe epilepsy (NFLE) against healthy subjects. We aim to develop a machine learning‐based algorithm that automatically classifies ECG signals into these sleep disorder categories. The cyclic alternating pattern (CAP) sleep database was used in this study, which contains PSG recordings from individuals with and without sleep disorders, including insomnia, narcolepsy, PLM, RBD, and NFLE. A wavelet scattering network has been used to extract features from the ECG signals. Various classifiers were tested, and the ensemble bag of trees classifier provided the optimum performance. An overall accuracy of 98% was obtained for the identification of sleep disorders, along with a classification accuracy of 99.37%, 99.45%, 99.23%, 99.4%, and 99.65% for insomnia, narcolepsy, NFLE, PLM, and RBD, respectively, for binary classification against healthy subject data. Our results show that wavelet scattering network and ensemble of bagged tree (EbagT) classification can accurately identify various sleep disorders. They provided evidence that ECG signals can be used to identify and diagnose sleep disorders, which could lead to the development of accurate detection of these sleep disorders. Also, our study demonstrated the effectiveness of the proposed algorithm in identifying multiple sleep disorders, which could lead to more efficient and cost‐effective diagnosis and treatment of sleep disorders. [ABSTRACT FROM AUTHOR]

Parkinson's Disease (PD) is a brain‐related disease that eventually causes disability and disrupts a person's normal life. Most physicians and researchers try to diagnose it quickly and treat it on time. In recent years, computer science and the field of artificial intelligence (machine learning) have helped researchers find a way to detect the disease early. This article proposes a method that diagnoses Parkinson's disease by analyzing the hand drawing shaped by the individuals using Bi‐Directional Long Short‐Term Memory (Bi‐LSTM) neural network. In addition, this paper proposes a Fuzzy Inferential Classifier for the Dense layer, which classifies the output of LSTM Blocks to the associated classes by modifying the Soft‐max function. Our decision to propose this classifier was because, in some cases, hand‐drawing data related to people with Parkinson's disease have no significant difference with the healthy subjects for the distinguishing and are often very similar to each other. A standard dataset has been used in this paper, which includes spirals drawn test (including static spiral, dynamic spiral, and stability specific point) by a group of healthy people and people with Parkinson's disease. The proposed method has reached 97%, 98.5%, and 100% accuracy rates for the three mentioned spiral tests with a smoother training loss and accuracy plots. In addition, the results outperform state‐of‐the‐art research conducted on this dataset and show at least more than 2.5% improvement in the accuracy rate in comparison. [ABSTRACT FROM AUTHOR]

Malware developers install malware on mobile users' devices and steal their personal information without their knowledge. According to recent studies, it has been observed that malware developers are now targeting Android mobile devices. Researchers have examined the issues of detecting malware in these devices and proposed different methods and techniques. This study's main goal is to aid researchers in gaining a basic understanding of Android malware and its numerous detection methods. Earlier experiments that used machine learning to detect Android malware will be carefully reviewed in this paper. This in‐depth review article thoroughly examines the origins, evolution, and sustainability of Android malware detection. It offers an in‐depth literature review that includes the most recent approaches and research trends for detecting malware, from static analysis to dynamic analysis, machine learning, and deep learning. Additionally, we review current approaches' shortcomings and difficulties and suggest possible paths for further investigation. The paper aims to stimulate further innovation in this essential field by providing researchers and practitioners with a comprehensive overview of the current status of Android malware detection. [ABSTRACT FROM AUTHOR]

With the promotion and development of oversized data technology, many data analysis platforms based on super large data storage and computing frameworks have emerged in the industry. While the platforms with oversized economic data analysis combined with machine learning models are still relatively lacking. And oversized data also brings a new problem, that is the security of economic development. It is an important and difficult task to analyse and detect risks from oversized economic data. Based on machine learning, data analysis, economic market and other multidisciplinary fields, this paper proposes a machine learning method, which is a genetic algorithm (GA) based feature selection method: FSGA. This method abstracts every possible feature selection result into an individual in GA, generates a population through genetic operation, and measures the merits of the individual through fitness. In addition, this paper has conducted multitudinous simulation experiments on the GA‐based FSGA method and the traditional LSTM data analysis method respectively. The accuracy rate and other indicators are obtained by comparing the training. The experimental results show that the GA‐based FSGA machine learning method has higher prediction accuracy when analysing oversized economic data. And it is practical to accelerate the development of digital economy. [ABSTRACT FROM AUTHOR]

Hypovigilance represents a major contributor to accidents. In operational contexts, the burden of monitoring/managing vigilance often rests on operators. Recent advances in sensing technologies allow for the development of psychophysiology‐based (hypo)vigilance prediction models. Still, these models remain scarcely applied to operational situations and need better understanding. The current scoping review provides a state of knowledge regarding psychophysiological models of hypovigilance detection. Records evaluating vigilance measuring tools with gold standard comparisons and hypovigilance prediction performances were extracted from MEDLINE, PsychInfo, and Inspec. Exclusion criteria comprised aspects related to language, non‐empirical papers, and sleep studies. The Quality Assessment tool for Diagnostic Accuracy Studies (QUADAS) and the Prediction model Risk Of Bias ASsessment Tool (PROBAST) were used for bias evaluation. Twenty‐one records were reviewed. They were mainly characterized by participant selection and analysis biases. Papers predominantly focused on driving and employed several common psychophysiological techniques. Yet, prediction methods and gold standards varied widely. Overall, we outline the main strategies used to assess hypovigilance, their principal limitations, and we discuss applications of these models. We conducted a scoping review on psychophysiological models of hypogivilant state. Studies reviewed relied either on diagnostic or machine learning approaches. Induction methods and levels of hypovigilance varied importantly between studies. Hypovigilance detection mainly relied on electrocardiography (ECG),photoplethysmography (PPG), electroencephalography (EEG), electrooculography (EOG), and eye tracking. Results can help to develop user‐tailored systems to mitigate hypovigilance. [ABSTRACT FROM AUTHOR]

Theories are the vehicle of cumulative knowledge acquisition. At this time, however, many (developmental) psychological theories are insufficiently precise to derive testable hypotheses. This limits the advancement of our principled understanding of development. This problem cannot be resolved by improving the way deductive (confirmatory) research is conducted (e.g., through preregistration and replication), because theory formation requires inductive (exploratory) research. This paper argues that machine learning can help advance theory formation in (developmental) psychology, because it enables rigorous exploration of patterns in data. The paper discusses specific advantages of machine learning, explains core methodological concepts, introduces relevant methods, and describes how data‐driven insights are consolidated into theory. Machine learning automates exploration, and incorporates checks and balances to ensure generalizable results. It can assist in phenomenon detection and offers a more holistic understanding of the phenomena associated with an outcome or process of interest. [ABSTRACT FROM AUTHOR]

Nowadays, the development of Artificial Intelligence of Things (AIoT) is advancing rapidly, and intelligent devices are increasingly exposed to more security risks on the network. Deep learning‐based intrusion detection is an effective security defence approach. Federated learning (FL) is capable of enabling deep learning models to be trained on local clients without uploading their data to a central server. This paper proposes a novel federated learning aggregation algorithm called fed‐dynamic gravitational search algorithm (Fed‐DGSA), which incorporates the GSA algorithm to optimize the weight updating process of FL local models. During the updating process, the decay rate of the gravity coefficient is optimized and random perturbations and dynamic weights are introduced to ensure a more stable and efficient FL aggregation process. The experimental results show that the detection accuracy of Fed‐DGSA has reached about 97.8%, and it is demonstrated that the model trained using Fed‐DGSA achieves higher accuracy compared to Fed‐Avg. [ABSTRACT FROM AUTHOR]

When ground communication infrastructure within a region cannot be used for some reason, deploying unmanned aerial vehicle (UAV)- mounted base stations is undoubtedly the most effective way to provide communication services. This paper investigates the problem of joint deployment and power allocation of multiple UAVs, where ground terminals (GTs) seek to maximize quality of experience (QoE). In the mixed line-of-sight and non-line-of-sight environment, UAVs need to change position in order to collect channel information until deployment problem is solved. Moreover, only neighboring UAVs communicate with each other, which makes the problem more difficult to solve. In order to solve this problem, game theory is used to model this problem and design a distributed learning algorithm to maximize the QoE of all GTs in the entire system. Simulation results validate the effectiveness of the proposed learning algorithm in improving the QoE fairness and achieving the rapid deployment of UAVs. [ABSTRACT FROM AUTHOR]

Prediction models are being increasingly used in the medical field to identify risk factors and possible outcomes. Some of these are presently being used to develop guidelines for improving clinical practice. The application of machine learning (ML), comprising a powerful set of computational tools for analysing data, has been clearly expanding in the role of predictive modelling. This paper reviews the latest developments of supervised ML techniques that have been used to analyse data related to post‐operative total hip and knee replacements. The aim was to review the most recent findings of relevant published studies by outlining the methodologies employed (most‐widely used supervised ML techniques), data sources, domains, limitations of predictive analytics and the quality of predictions. [ABSTRACT FROM AUTHOR]

In complex systems with multiple variables monitored at high‐frequency, variables are not only temporally autocorrelated, but they may also be nonlinearly related or exhibit nonstationarity as the inputs or operation changes. One approach to handling such variables is to detrend them prior to monitoring and then apply control charts that assume independence and stationarity to the residuals. Monitoring controlled systems is even more challenging because the control strategy seeks to maintain variables at prespecified mean levels, and to compensate, correlations among variables may change, making monitoring the covariance essential. In this paper, a vector autoregressive model (VAR) is compared with a multivariate random forest (MRF) and a neural network (NN) for detrending multivariate time series prior to monitoring the covariance of the residuals using a multivariate exponentially weighted moving average (MEWMA) control chart. Machine learning models have an advantage when the data's structure is unknown or may change. We design a novel simulation study with nonlinear, nonstationary, and autocorrelated data to compare the different detrending models and subsequent covariance monitoring. The machine learning models have superior performance for nonlinear and strongly autocorrelated data and similar performance for linear data. An illustration with data from a reverse osmosis process is given. [ABSTRACT FROM AUTHOR]

Liquefaction‐induced lateral spread is a kind of ground deformation caused by soil liquefaction, which is a danger to houses, roads and other infrastructures. In order to systematically investigate the influence law of different parameters on lateral displacement, this paper establishes a numerical model of the seismic responses of gently sloping grounds through the open‐source finite element software OpenSees and carries out a large number of calculations considering various working conditions. Based on the calculation results, eXtreme Gradient Boosting (XGBoost) and random forest (RF) regression are used to build the proxy models for lateral spread displacement prediction. The finite element model was verified by using the multiple VELACS No. 2 centrifuge experiments. Finally, the model was interpreted using SHapley Additive exPlanation (SHAP) method. The results of the model training showed that both models were able to achieve a good fit to the numerical calculation results, with the RF model having a smaller prediction error for the centrifuge experiments. The model interpretation results showed that the modified cumulative absolute velocity (CAV5) was the most important input variable in the model, and the importance of ground slope (S), relative density (Dr) and thickness of liquefiable soil layer (HL) was relatively high. In addition, the influence of each parameter on the lateral displacement is consistent with the actual situation, reflecting the rationality of the model prediction process. In addition, the results showed that there is a threshold for the modified cumulative absolute velocity (CAV5) and Arias intensity (Ia) that leads to a significant increase in lateral displacement. The thresholds of CAV5 and Ia are 1.3 g s and 1.0 m/s, respectively. These thresholds are in good agreement with the thresholds for triggering the overall initial liquefaction of the soil layer determined by related studies, which provides a reference for the evaluation of liquefaction‐induced lateral displacement. [ABSTRACT FROM AUTHOR]

Summary: This paper examines the controllability of a novel Lyapunov‐based model reference adaptive control (MRAC) system designed with a meta‐learning‐based physics‐informed neural network (MLPINN) for linear and nonlinear single‐input and single‐output (SISO) plants without labeled data (MLPINN‐MRAC system). It is devised with the benefits of several techniques: the integration of the identification process in a training mode into an online control mode (straightforward design); no labeled data generation for online identification by a physics‐informed neural network; the prevention of degradation in tracking performance by meta‐learning, as the system triggers a meta‐learning process only when an error threshold detects the deterioration (high efficiency and the reduction of computation cost); quick adaptation to new inputs and an updated control input for each sub‐time span by transfer learning. It is worth noting that the frequency of the meta‐learning event detection significantly affects the step response stability of the nonlinear plant. To achieve a better quality of the stabilization, more frequent event detection is necessary for both beginning and end intervals in control. Sixteen triggering events are enough to shape the acceptable step response of the nonlinear plant, and 44 triggering events achieve the plant's desired step response with its minor modeling error. While, as for the linear plant, a single triggering event is sufficient to attain its tolerable step response and modeling error, implying that intensive event detection is not critical in the identification. It is obvious that the MLPINN‐MRAC system functions well and is more beneficial and efficient for the nonlinear plant. [ABSTRACT FROM AUTHOR]

Serial crystallography experiments at synchrotron and X‐ray free‐electron laser (XFEL) sources are producing crystallographic data sets of ever‐increasing volume. While these experiments have large data sets and high‐frame‐rate detectors (around 3520 frames per second), only a small percentage of the data are useful for downstream analysis. Thus, an efficient and real‐time data classification pipeline is essential to differentiate reliably between useful and non‐useful images, typically known as 'hit' and 'miss', respectively, and keep only hit images on disk for further analysis such as peak finding and indexing. While feature‐point extraction is a key component of modern approaches to image classification, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. This paper proposes a pipeline to categorize the data, consisting of a real‐time feature extraction algorithm called modified and parallelized FAST (MP‐FAST), an image descriptor and a machine learning classifier. For parallelizing the primary operations of the proposed pipeline, central processing units, graphics processing units and field‐programmable gate arrays are implemented and their performances compared. Finally, MP‐FAST‐based image classification is evaluated using a multi‐layer perceptron on various data sets, including both synthetic and experimental data. This approach demonstrates superior performance compared with other feature extractors and classifiers. [ABSTRACT FROM AUTHOR]

Class imbalance is a common and critical challenge in machine learning classification problems, resulting in low prediction accuracy. While numerous methods, especially data augmentation methods, have been proposed to address this issue, a method that works well on one dataset may perform poorly on another. To the best of our knowledge, there is still no one single best approach for handling class imbalance that can be uniformly applied. In this paper, we propose an approach named smart data augmentation (SDA), which aims to augment imbalanced data in an optimal way to maximize downstream classification accuracy. The key novelty of SDA is an equation that can bring about an augmentation method that provides a unified representation of existing sampling methods for handling multi‐level class imbalance and allows easy fine‐tuning. This framework allows SDA to be seen as a generalization of traditional methods, which in turn can be viewed as specific cases of SDA. Empirical results on a wide range of datasets demonstrate that SDA could significantly improve the performance of the most popular classifiers such as random forest, multi‐layer perceptron, and histogram‐based gradient boosting. [ABSTRACT FROM AUTHOR]

Many object‐oriented metrics have been proposed in the literature to measure various structural properties of object‐oriented software. Furthermore, many centrality measures have been introduced to identify central nodes in large networks. However, few studies have used them to measure dependencies in software systems. In fact, centrality measures, as opposed to most traditional object‐oriented metrics that mainly focus on intrinsic properties of classes, can be used to better model the control flow and to identify the most important classes in a software system. This paper aims (1) to investigate the relationships between object‐oriented metrics and centrality measures and (2) to explore the ability of their combination to support fault‐proneness prediction from different perspectives (fault‐prone classes, fault severity, and number of faults). Many studies in the literature have addressed the prediction of fault‐prone classes, from different perspectives, using object‐oriented metrics. The main motivation here is in fact to investigate if the information captured by centrality measures is related to fault proneness and complementary to the information captured by object‐oriented metrics and to investigate if the combination of object‐oriented metrics and centrality measures improves the performance of fault‐proneness prediction significantly. We used size, complexity, and coupling object‐oriented metrics in addition to various centrality measures. We collected data from 20 different versions of five open‐source Java software systems. We first studied the relationships between selected metrics and their relationships to fault proneness. Then, we built different models to predict fault‐prone classes using several machine learning algorithms. In addition, we built models to predict if a class contains a high severity fault, and the number of faults in a class. Results indicate that using centrality measures in combination with object‐oriented metrics improves the prediction of fault‐prone classes as well as the prediction of the number of faults in a class. However, the combination has no significant impact, according to the data we collected, on the quality of the prediction of fault severity. Moreover, using centrality measures in combination with object‐oriented metrics also improves the prediction performance of fault proneness and the number of faults in both cross‐version and cross‐system validation. [ABSTRACT FROM AUTHOR]

Data on infrastructure project costs are often unstructured and lack consistency. To enable costs to be compared within and between organizations, large amounts of data must be classified to a common standard, typically a manual process. This is time‐consuming, error‐prone, inconsistent, and subjective, as it is based on human judgment. This paper describes a novel approach for automating the process by harnessing natural language processing identifying the relevant keywords in the text descriptions and implementing machine learning classifiers to emulate the expert's knowledge. The task was to identify "extra over" cost items, conversion factors, and to recognize the correct work breakdown structure (WBS) category. The results show that 94% of the "extra over" cases were correctly classified, and 90% of cases that needed conversion, correctly predicting an associated conversion factor with 87% accuracy. Finally, the WBS categories were identified with 72% accuracy. The approach has the potential to provide a step change in the speed and accuracy of structuring and classifying infrastructure cost data for benchmarking. [ABSTRACT FROM AUTHOR]

This study aimed to comprehensively evaluate the current utilization and future potential of ChatGPT, an AI-based chat model, in the field of radiology. The primary focus is on its role in enhancing decision-making processes, optimizing workflow efficiency, and fostering interdisciplinary collaboration and teaching within healthcare. A systematic search was conducted in PubMed, EMBASE and Web of Science databases. Key aspects, such as its impact on complex decision-making, workflow enhancement and collaboration, were assessed. Limitations and challenges associated with ChatGPT implementation were also examined. Overall, six studies met the inclusion criteria and were included in our analysis. All studies were prospective in nature. A total of 551 chatGPT (version 3.0 to 4.0) assessment events were included in our analysis. Considering the generation of academic papers, ChatGPT was found to output data inaccuracies 80% of the time. When ChatGPT was asked questions regarding common interventional radiology procedures, it contained entirely incorrect information 45% of the time. ChatGPT was seen to better answer US board-style questions when lower order thinking was required (P = 0.002). Improvements were seen between chatGPT 3.5 and 4.0 in regard to imaging questions with accuracy rates of 61 versus 85%(P = 0.009). ChatGPT was observed to have an average translational ability score of 4.27/5 on the Likert scale regarding CT and MRI findings. ChatGPT demonstrates substantial potential to augment decision-making and optimizing workflow. While ChatGPT’s promise is evident, thorough evaluation and validation are imperative before widespread adoption in the field of radiology. [ABSTRACT FROM AUTHOR]

Raman spectroscopy can be effectively used for detection and analysis of chemical agents that are serious threats in modern warfare, but the detection and analysis performance is prone to deterioration due to noise. The existing denoising technique has limitations that there is no criterion for selecting the window length and that the filtering distorts the peaks, key features for Raman spectral data analysis. To overcome such limitations, in this paper, we propose the peak‐aware adaptive denoising for Raman spectroscopy based on machine learning approach. The proposed technique utilizes the information of detected peaks to eliminate noise effectively using different window values optimal for each region in the Raman spectrum while preserving the shape of peaks. We conducted the various analyses and experiments, and the proposed technique showed a 28% lower Euclidean distance and a 48% lower Fréchet inception distance compared to the existing technique, meaning the proposed technique outperformed the existing one. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Cushing's Disease (CD) is a rare clinical syndrome characterized by excessive secretion of adrenocorticotrophic hormone, leading to significant functional and structural brain alterations as observed in Magnetic Resonance Imaging (MRI). While traditional statistical analysis has been widely employed to investigate these MRI changes in CD, it has lacked the ability to predict individual‐level outcomes.To address this problem, this paper has proposed an interpretable machine learning (ML) framework, including model‐level assessment, feature‐level assessment, and biology‐level assessment to ensure a comprehensive analysis based on structural MRI of CD.The ML framework has effectively identified the changes in brain regions in the stage of model‐level assessment, verified the effectiveness of these altered brain regions to predict CD from normal controls in the stage of feature‐level assessment, and carried out a correlation analysis between altered brain regions and clinical symptoms in the stage of biology‐level assessment.The experimental results of this study have demonstrated that the Insula, Fusiform gyrus, Superior frontal gyrus, Precuneus, and the opercular portion of the Inferior frontal gyrus of CD showed significant alterations in brain regions. Furthermore, our study has revealed significant correlations between clinical symptoms and the frontotemporal lobes, insulin, and olfactory cortex, which also have been confirmed by previous studies.The ML framework proposed in this study exhibits exceptional potential in uncovering the intricate pathophysiological mechanisms underlying CD, with potential applicability in diagnosing other diseases. [ABSTRACT FROM AUTHOR]

The reliability of hourly PM2.5 data obtained from air quality monitoring stations is compromised as a result of the missing values, thereby impeding the thorough examination of crucial information. In this paper, we present a spatiotemporal (ST) stacking machine learning (ML) method with daily‐cycle restrictions for reconstructing missing hourly PM2.5 records. First, the ST neighbors for the target station with missing values are selected at a daily scale. Subsequently, the non‐null data within the ST neighbors undergo an iterative P‐BSHADE interpolation process for re‐interpolation. Next, a stacking ML model is constructed using the re‐interpolation values and several environmental factors associated with PM2.5 as the predictors, while the observed PM2.5 is taken as the independent variable. Finally, the missing values are reconstructed by inputting the predictors into the trained stacking model. The study utilized hourly PM2.5 data in the Beijing‐Tianjin‐Hebei region as a case study to assess the effectiveness of the proposed method, using daily missing ratios of 10%, 30%, and 50%, respectively. The accuracy of the proposed method was then compared to four contemporary ST interpolation methods. The results indicate that the proposed method exhibits superior performance compared to the classical methods. Specifically, it achieves a reduction in the average root mean square error and mean absolute error by at least 40.6% and 40.1%, respectively. Additionally, the proposed method demonstrates the successful recovery of extreme values in the hourly PM2.5 records, in contrast to the classical methods which often exhibit a tendency to overestimate low values and underestimate high values. Overall, the proposed method presents a viable and efficient approach to recover missing values in the hourly PM2.5 records that demonstrate evident daily periodic patterns. [ABSTRACT FROM AUTHOR]

This paper provides a method for improving the photovoltaic conversion efficiency and optical attributes of silicon solar cells manufactured from as‐cut boron doped p‐type multi‐crystalline silicon wafers using acid‐based chemical texturization via machine learning. A decreased reflectance, which can be attained by the right chemical etching conditions, is one of the key elements for raising solar cell efficiency. In this work, the mc‐Silicon wafer surface reflectance is obtained under (<2%) after optimization of wet chemical etching. The HF + HNO3 + CH3COOH chemical etchant is used in the ratio 1:3:2 at different conditions of the etching duration of 1 min, 2 min, 3 min, and 4 min, respectively. The as‐cut boron doped p‐type mc‐silicon wafers are analysed with ultraviolet–visible spectroscopy, optical microscopy, Fourier transforms infrared spectroscopy, thickness profilometer, and scanning electron microscopy before and after etching. The chemical etching solution produces good results in 3 min etched wafer, with a reflectivity value of <2%.The reflectivity and optical images are inputs to the convolutional neural network model and the linear regression model to obtain the etching rate for better reflectivity. The classification model provides 99.6% accuracy and the regression model results in the minimum mean squared error (MSE) of 0.062. [ABSTRACT FROM AUTHOR]