Search

Orbit prediction accuracy is often limited by the underlying physics-based models and estimation methods. Instead of advancing the state-of-the-art from those two aspects, we have recently developed a physics-based machine learning (ML) methodology to discover useful information from historical orbit predictions errors. This paper is posed to answer the next question: how can we fuse the ML approach with classical orbit predictions? The classical method provides valuable and reliable information and should not be abandoned. Using the extended Kalman filter (EKF) as the orbit estimation and prediction method, this paper presents an innovative fusion strategy to incorporate the ML output to the conventional framework. We define the pseudo-physical meaning of the ML output and derive an analytical model for fusion. Using a simulation-based space catalog environment, the paper demonstrates that the proposed fusion strategy can improve both the orbit prediction accuracy and precision. Discussions and insights are presented including the possible causes for some unsatisfying results. Although EKF is used in this paper, the design of the fusion strategy for the ML approach can be generalized to systems with different orbit estimation and prediction methods. • Machine learning (ML) approach learns from data to improve orbit prediction accuracy. • Trained gaussian processes (GPs) models generate predictive mean and covariance. • ML-covariance can be fused with classical covariance via defining a physical meaning. • Propose a systematic fusion strategy to fuse the ML-covariance and EKF-covariance. [ABSTRACT FROM AUTHOR]

Multi-target missions are an attractive solution to visit multiple bodies, increasing the scientific return and reducing the cost, compared to multiple missions to individual targets. Examples of multi-target missions are multiple active debris removals (MADR) and multiple near-Earth asteroids rendezvous (MNR) missions. MADR missions allow for the disposal of inactive satellites, preventing the build-up of space junk, while MNR missions allow to reduce the expenses of each asteroid observation. Since those missions are long and highly demanding in terms of energy, it is paramount to select the most convenient propulsion system so that the propellant mass and the duration of the mission are minimized. To this end, this paper proposes the use of a multi-objective optimization and artificial neural networks. The methodology is assessed by optimizing trajectories for MADR and MNR sequences with off-the-shelf thrusters. Multiple Pareto-optimal solutions can be identified depending on the propulsion system characteristics, enabling mission designers to trade-off the different options quickly and reliably. [ABSTRACT FROM AUTHOR]

Images acquired during underwater activities suffer from environmental properties of the water, such as turbidity and light attenuation. These phenomena cause color distortion, blurring, and contrast reduction. In addition, irregular ambient light distribution causes color channel unbalance and regions with high-intensity pixels. Recent works related to underwater image enhancement, and based on deep learning approaches, tackle the lack of paired datasets generating synthetic ground-truth. In this paper, we present a self-supervised learning methodology for underwater image enhancement based on deep learning that requires no paired datasets. The proposed method estimates the degradation present in underwater images. Besides, an autoencoder reconstructs this image, and its output image is degraded using the estimated degradation information. Therefore, the strategy replaces the output image with the degraded version in the loss function during the training phase. This procedure misleads the neural network that learns to compensate the additional degradation. As a result, the reconstructed image is an enhanced version of the input image. Also, the algorithm presents an attention module to reduce high-intensity areas generated in enhanced images by color channel unbalances and outlier regions. Furthermore, the proposed methodology requires no ground-truth. Besides, only real underwater images were used to train the neural network, and the results indicate the effectiveness of the method in terms of color preservation, color cast reduction, and contrast improvement. [Display omitted] • Underwater image enhancement and self-supervised learning. • Image restoration and enhancement based on autoencoder and degradation. • Attention mechanism for high-intensity or saturated regions in the image. [ABSTRACT FROM AUTHOR]

Solving linear system of equations stemming from Laplacian operators is at the heart of a wide range of applications. Due to the sparsity of the linear systems, iterative solvers such as Conjugate Gradient and Multigrid are usually employed when the solution has a large number of degrees of freedom. These iterative solvers can be seen as sparse approximations of the Green's function for the Laplacian operator. In this paper we propose a machine learning approach that regresses a Green's function from boundary conditions. This is enabled by a Green's function that can be effectively represented in a multi-scale fashion, drastically reducing the cost associated with a dense matrix representation. Additionally, since the Green's function is solely dependent on boundary conditions, training the proposed neural network does not require sampling the right-hand side of the linear system. We show results that our method outperforms state of the art Conjugate Gradient and Multigrid methods. [Display omitted] • A multi-scale sparse representation of Green's function for the Laplace Operator. • A machine learning approach that regresses a Green's function solution from boundary conditions. • An efficient linear system solver based on the multi-scale Green's function approximation. [ABSTRACT FROM AUTHOR]

Outdoor point-cloud object localization is an essential processing step for urban scene analysis and modeling in numerous applications, especially in land surveying and site analysis. Given the increasingly use of Terrestrial Laser Scanning (TLS) and LiDAR 3D data acquisition, numerous annotated point-cloud datasets are available and can be used to evaluate computer vision and machine learning based algorithms. Nevertheless, current point-cloud datasets mainly focus on object detection and classification in autonomous driving or urban planning type of applications, and share redundant object classes, e.g., trees, vehicles and pedestrians, which limit their usefulness for land surveying and site analysis. This paper introduces a novel 3D benchmark dataset LiSurveying, which is a large-scale point-cloud dataset with over a billion points and uncommon urban object categories in complex outdoor environments. Our dataset incorporates more urban object classes than existing datasets. Its instances have diverse point densities, shapes and dimensions, which also impose a challenge for point-cloud detection and classification algorithms. We conducted baselines experiments for point-cloud classification using machine learning classifiers and deep learning methods on different subsets of the LiSurveying dataset, and we are able to demonstrate that the various types of object classes, number of instances per class, distribution of object points, and variety of complex scenes, make this LiSurveying benchmark dataset suitable for evaluating 3D point-cloud classification, semantic segmentation, and object detection algorithms. [Display omitted] • Large-scale (point-wise and 3D bounding boxes) TLS-LiDAR dataset for Land Surveying. • 3D Urban benchmark for object classification y detection. • Learning-based methods applied on complex urban environments. • Comparative performance of existing algorithms for LiDAR classification. [ABSTRACT FROM AUTHOR]

This paper presents the methods that have participated in the SHREC 2022 contest on protein–ligand binding site recognition. The prediction of protein- ligand binding regions is an active research domain in computational biophysics and structural biology and plays a relevant role for molecular docking and drug design. The goal of the contest is to assess the effectiveness of computational methods in recognizing ligand binding sites in a protein based on its geometrical structure. Performances of the segmentation algorithms are analyzed according to two evaluation scores describing the capacity of a putative pocket to contact a ligand and to pinpoint the correct binding region. Despite some methods perform remarkably, we show that simple non-machine-learning approaches remain very competitive against data-driven algorithms. In general, the task of pocket detection remains a challenging learning problem which suffers of intrinsic difficulties due to the lack of negative examples (data imbalance problem). [Display omitted] • A new contest for binding site detection in a protein. • Proteins are provided both as molecular surfaces and in anonymized PQR format. • Analysis of computational methods for recognizing ligand binding sites in a protein. • Analysis of the performances of the methods that participated in SHREC 2022. [ABSTRACT FROM AUTHOR]

Analyzing satellite images and remote sensing (RS) data using artificial intelligence (AI) tools and data fusion strategies has recently opened new perspectives for environmental monitoring and assessment. This is mainly due to the advancement of machine learning (ML) and data mining approaches, which facilitate extracting meaningful information at a large scale from geo-referenced and heterogeneous sources. This paper presents the first review of AI-based methodologies and data fusion strategies used for environmental monitoring, to the best of the authors' knowledge. The first part of the article discusses the main challenges of geographical image analysis. Thereafter, a well-designed taxonomy is introduced to overview the existing frameworks, which have been focused on: (i) detecting different environmental impacts, e.g. land cover land use (LULC) change, gully erosion susceptibility (GES), waterlogging susceptibility (WLS), and land salinity and infertility (LSI); (ii) analyzing AI models deployed for extracting the pertinent features from RS images in addition to data fusion techniques used for combining images and/or features from heterogeneous sources; (iii) describing existing publicly-shared and open-access datasets; (iv) highlighting most frequent evaluation metrics; and (v) describing the most significant applications of ML and data fusion for RS image analysis. This is followed by an overview of existing works and discussions highlighting some of the challenges, limitations and shortcomings. To provide the reader with insight into real-world applications, two case studies illustrate the use of AI for classifying LULC changes and monitoring the environmental impacts due to dams' construction, where classification accuracies of 98.57% and 97.05% have been reached, respectively. Lastly, recommendations and future directions are drawn. • DCNNs and deep fusion strategies of remote sensing image classification. • Detection of LULC change, waterlogging, gully erosion, and land salinity and infertility. • Semantic and panoptic remote sensing image segmentation for change detection. • Transfer learning and active learning to improve classification and reduce computational cost. • Explainable AI and point clouds for better remote sensing image understanding. [ABSTRACT FROM AUTHOR]

Multi-view learning exploits structural constraints among multiple views to effectively learn from data. Although it has made great methodological achievements in recent years, the current generalization theory is still insufficient to prove the merit of multi-view learning. This paper blends stability into multi-view PAC-Bayes analysis to explore the generalization performance and effectiveness of multi-view learning algorithms. We propose a novel view-consistency regularization to produce an informative prior that helps to obtain a stability-based multi-view bound. Furthermore, we derive an upper bound on the stability coefficient that is involved in the PAC-Bayes bound of multi-view regularization algorithms for the purpose of computation, taking the multi-view support vector machine as an example. Experiments provide strong evidence on the advantageous generalization bounds of multi-view learning over single-view learning. We also explore strengths and weaknesses of the proposed stability-based bound compared with previous non-stability multi-view bounds experimentally. • We propose a novel view-consistency regularization to deduce PAC-Bayes bounds. • We upper-bound the stability coefficient of MvSVM to compute specific bounds. • Experimental results validate the theoretical superiority of multi-view learning. • The new bounds show good tightness and ability to support model selection. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) for the biomedical domain is gaining significant interest and holds considerable potential for the future of healthcare, particularly also in the context of in vitro diagnostics. The European In Vitro Diagnostic Medical Device Regulation (IVDR) explicitly includes software in its requirements. This poses major challenges for In Vitro Diagnostic devices (IVDs) that involve Machine Learning (ML) algorithms for data analysis and decision support. This can increase the difficulty of applying some of the most successful ML and Deep Learning (DL) methods to the biomedical domain, just by missing the required explanatory components from the manufacturers. In this context, trustworthy AI has to empower biomedical professionals to take responsibility for their decision-making, which clearly raises the need for explainable AI methods. Explainable AI, such as layer-wise relevance propagation, can help in highlighting the relevant parts of inputs to, and representations in, a neural network that caused a result and visualize these relevant parts. In the same way that usability encompasses measurements for the quality of use, the concept of causability encompasses measurements for the quality of explanations produced by explainable AI methods. This paper describes both concepts and gives examples of how explainability and causability are essential in order to demonstrate scientific validity as well as analytical and clinical performance for future AI-based IVDs. • Causability has to be shown for features recognized by In Vitro Diagnostic devices. • Analytical and clinical performance of AI algorithms must be monitored. • Explainability and causability have to be demonstrated for performance monitoring. • Experts need evidence of explainability/causability in order to take responsibility. • AI needs causability measures to ensure the quality of explainability. [ABSTRACT FROM AUTHOR]

Detecting anomalies in telemetry data captured on-board a spacecraft is critical to ensure its safe operation. Although there exist various techniques for automatically detecting point, contextual, and collective anomalies from time-series data, quantifying their performance remains under-researched. In this paper, we thoroughly validate our approach for the task of anomalous event detection that is built upon a two-stage technique, in which the telemetry signal is predicted using a long short-term memory network based on the historical data, and then the prediction is compared with the actual (captured) data. If the difference between those two is sufficiently large, we can infer that an anomalous event has happened. To evaluate the capabilities of such detection techniques over the simulated and benchmark time-series data, we investigate a set of commonly used metrics obtained for a range of anomaly detection approaches, and present their shortcomings, especially related to their inability of capturing the temporal aspects of the detectors. We tackle this issue by introducing new quality metrics which enable us to objectively verify if the detectors can timely spot the anomalies in sequential data. The experimental study showed that inferring the conclusions based on a subset of metrics can lead to biased observations, as the best algorithms determined based on the overlap metrics, including the Dice coefficient, do not necessarily correspond to the algorithms that offer the fastest detection. Finally, we discuss the Antelope Toolbox—our software tool for simulating nominal telemetry data of given characteristics, alongside well-defined anomalous events, and to perform the quantitative and qualitative analysis of anomaly detection algorithms over such simulated events. • We investigate the quality metrics to verify anomaly detection in telemetry data. • We introduce new measures that capture temporal aspects of anomaly detectors. • We present an end-to-end machine learning pipeline for anomaly detection. • We objectively assess 15 anomaly detection algorithms using all metrics. • Exploiting only a subset of all metrics can easily lead to biased conclusions. [ABSTRACT FROM AUTHOR]

Physics-informed neural networks (PINNs) based machine learning is an emerging framework for solving nonlinear differential equations. However, due to the implicit regularity of neural network structure, PINNs can only find the flattest solution in most cases by minimizing the loss functions. In this paper, we combine PINNs with the homotopy continuation method, a classical numerical method to compute isolated roots of polynomial systems, and propose a new deep learning framework, named homotopy physics-informed neural networks (HomPINNs), for solving multiple solutions of nonlinear elliptic differential equations. The implementation of an HomPINN is a homotopy process that is composed of the training of a fully connected neural network, named the starting neural network, and training processes of several PINNs with different tracking parameters. The starting neural network is to approximate a starting function constructed by the trivial solutions, while other PINNs are to minimize the loss functions defined by boundary condition and homotopy functions, varying with different tracking parameters. These training processes are regraded as different steps of a homotopy process, and a PINN is initialized by the well-trained neural network of the previous step, while the first starting neural network is initialized using the default initialization method. Several numerical examples are presented to show the efficiency of our proposed HomPINNs, including reaction-diffusion equations with a heart-shaped domain. [ABSTRACT FROM AUTHOR]

The development of the Internet of Things, cloud computing, and artificial intelligence has given birth to industrial artificial intelligence (IAI) technology, which enables us to obtain fine perception and in-depth understanding capabilities for the operating conditions of industrial processes, and promotes the intelligent transformation of modern industrial production processes. At the same time, modern industry is facing diversified market demand instead of ultra-large-scale demand, resulting in typical variable conditions, which enhances the nonstationary characteristics of modern industry, and brings great challenges to the monitoring of industrial processes. In this regard, this paper analyzes the complex characteristics of nonstationary industrial operation, reveals the effects on operating condition monitoring, and summarizes the difficulties faced by varying condition monitoring. Furthermore, by reviewing the recent 30 years of development of data-driven methods for industrial process monitoring, we sorted out the evolution of nonstationary monitoring methods, and analyzed the features, advantages and disadvantages of the methods at different stages. In addition, by summarizing the existing related research methods by category, we hope to provide reference for monitoring methods of nonstationary process. Finally, combined with the development trend of industrial artificial intelligence technologies, some promising research directions are given in the field of nonstationary process monitoring. [ABSTRACT FROM AUTHOR]

The control of HVAC (Heating Ventilation and Air Conditioning) systems is usually complex because its modeling in certain cases is difficult, since these systems have a large number of components. Heat exchangers, chillers, valves, sensors, and actuators, increase the non-linear characteristics of the complete model, so it is necessary to propose new control strategies that can handle the uncertainty generated by all these elements working together. On the other hand, artificial intelligence is a powerful tool that allows improving the performance of control systems with inexact models and uncertainties. This paper presents new control alternatives for HVAC systems based on LAMDA (Learning Algorithm for Multivariable Data Analysis). This algorithm has been used in the field of machine learning, however, we have taken advantage of its learning characteristics to propose different types of intelligent controllers to improve the performance of the overall control system in tasks of regulation and reference change. In order to perform a comparative analysis in the context of HVAC systems, conventional methods such as PID and Fuzzy-PID are compared with LAMDA-PID, LAMDA-Sliding Mode Control based on Z-numbers (ZLSMC), and Adaptive LAMDA. Specifically, two HVAC systems are implemented by simulations to evaluate the proposals: an MIMO (Multiple-input Multiple-output) HVAC system and an HVAC system with dead time, which are used to compare the results qualitatively and quantitatively. The results show that ZLSMC is the most robust controller, which efficiently controls HVAC systems in cases of reference changes and the presence of disturbances. • New control alternatives for HVAC systems based on fuzzy approaches. • Learning Algorithm for Multivariable Data Analysis (LAMDA) in the definition of intelligent controllers. • MIMO (Multiple-input Multiple-output) HVAC and HVAC with dead time controlled by LAMDA approaches. • Utilization of LAMDA approaches for fuzzy modelling and control of HVAC systems. [ABSTRACT FROM AUTHOR]

In mechanical field, tool state seriously affects the production quality and efficiency. Recently, machine learning is an important technique to realize tool state recognition. Extracting and selecting features from the raw input data of the machine learning model can effectively eliminate useless information and improve the model accuracy. Therefore, a two-stage feature selection method is proposed in this paper. We first qualitatively propose the non-discreteness and separability of signal features. For these two properties, quantitative calculation methods are then developed in two stages. The proposed two-stage feature selection method is applied to machine learning models for tool state recognition. In engineering application verification, the proposed method achieves an average recognition accuracy of 84.4% in hob wear recognition, and an average recognition accuracy of 99.8% and 94.4% for two data sets in hob fault recognition, which is significantly higher than other feature selection methods. The verification results indicate that the proposed method has good generalization and engineering application value. [ABSTRACT FROM AUTHOR]

Tube bending is a widely used process in marine, automotive, construction and other industries. Different methods are available for this process during which various problems and defects are encountered. This paper aims to develop the most relevant model for bending the tubes using a computer numerical controlled (CNC) bending machine on the first attempt without any defects. To achieve this goal, the parameters affecting the tube bending process on the bending machine are defined. Based on these parameters, 150 bending experiments are conducted in an industrial plant to collect data and their results are used as dataset for machine learning (ML) algorithms. Seven different state-of-the-art ML algorithms –logistic regression, decision tree, k-nearest neighbor, random forest, Naïve Bayes, support vector machine and eXtreme gradient boosting (XGBoost)– are implemented using Python's Scikit-Learn library. Their performance is compared using confusion matrix and classification metrics such as accuracy, precision, recall, F1-score, receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) value. Considering all the performance metrics, logistic regression performed best in terms of prediction on our dataset. XGBoost and support vector machine were quiet successful based on F1 score and AUC, respectively. Overall, logistic regression, Naïve Bayes, Support Vector Machine, and XGBoost showed performances above 90% across all metrics. Decision tree, k-nearest neighbor and random forest performed poorly compared to other algorithms for our data. The proposed ML method is expected to save costs by reducing material waste and labor time and to increase the process efficiency and the product quality. [ABSTRACT FROM AUTHOR]

Audio classification and source separation are two important components in the music industry and for audio engineering as well. The Indian classical music industry is filled with a lot of similar-sounding instruments. The application of these in the field of music composition, audio signal processing and voice recognition can be a huge boon for the music industry. This research paper proposes an improvised method for audio source separation followed by a novel method for classification of the separated sources using a unique as well as novel dataset consisting of classical Indian musical instruments. The method entails decoupling the conglomerate of audio signals and categorising the resulting sources according to their unique traits using Indian Musical Instrument Classification models, CNN (Convolutional Neural Networks) and SVM (Support Vector Machine) models. The proposed novel dataset Indian Musical Instrument Dataset(IMID) is an important contribution to the area because there are not any unique organised datasets for classical Indian instruments. The IMIDataset includes ten Indian instruments — Flute, Veena, Sitar, Sarod, Tabla, Violin, Guitar, Piano, Bass and Drums. To evaluate and compare the efficacy of the proposed model, comparison was made with the different datasets based on their accuracy and loss metrics. Link to the dataset. [ABSTRACT FROM AUTHOR]

Accurate electricity consumption forecasting, especially monthly electricity consumption forecasting, plays an essential role in the stable and efficient operation of power systems. To improve forecasting performance and practicality, we propose a dynamic decomposition-denoising-ensemble model to predict monthly electricity consumption in this paper. Firstly, seasonal-trend decomposition procedure based on loess (STL) incorporated with a dynamic mechanism is used to decompose the original monthly electricity consumption series into trend component, seasonal component and residual component. Secondly, empirical wavelet transform (EWT) is introduced to denoise the residual component and obtain the denoised residual component. Thirdly, autoregressive integrated moving average (ARIMA), Holt-Winters (HW) and extreme learning machine (ELM) are used to predict the trend component, the seasonal component and the denoised residual components, respectively. Finally, the forecasting results of each component are added to obtain the final forecasting results. Furthermore, we take two real datasets from China as examples to verify the performance of our proposed model. The empirical results show that the proposed model performs better than the benchmark models and denoising the residual component can enhance the forecasting performance. Specifically, compared with benchmark models, the mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean squared error (RMSE) values of the proposed model decrease by 5.81%–46.02% (12.15%–51.03%), 4.80%–42.24% (12.75%–53.53%) and 1.98%–41.02% (10.44%–55.27%). [ABSTRACT FROM AUTHOR]

The lighting requirements are subjective and one light setting cannot work for all. However, there is little work on developing smart lighting algorithms that can adapt to user preferences. To address this gap, this paper uses fuzzy logic and reinforcement learning to develop an adaptive lighting algorithm. In particular, we develop a baseline fuzzy inference system (FIS) using the domain knowledge, generating light recommendation based on a set of intuitive rules. These rules, derived from existing literature, are based on environmental conditions i.e. daily glare index, and user information including age, activity, and chronotype. Through a feedback mechanism, the user interacts with the algorithm, correcting the algorithm output to their preferences. We interpret these corrections as rewards to a Q-learning algorithm, which tunes the FIS parameters online to match the user preferences. The Q-learning is a model-free learning algorithm that learns to act optimally by interacting with the user and the rewards it receives. This allows the proposed algorithm to work in a model-free manner, effectively handling the uncertainties that might arise from the individualistic preferences of users. To the authors' best knowledge, this algorithm is pioneering work in designing intelligent algorithms for personalized lighting control, featuring several elements of novelty, including the number of environmental and user-related inputs, the continuous control of light intensity as opposed to common on/off control, and the ability to learn user preferences. The algorithm is implemented in a real aircraft cabin and is evaluated in an extensive user study. The implementation results demonstrate that the developed algorithm possesses the capability to learn user preferences while successfully adapting to a wide range of environmental conditions and user characteristics. This underscores its viability as a potent solution for intelligent light management, featuring advanced learning capabilities. • Intelligent lighting algorithm with the ability to learn from and adapt to user preferences. • A fuzzy inference system tunes lighting based on environment and user traits. • The developed algorithm is tested and verified via an in-depth user study. [ABSTRACT FROM AUTHOR]

Guided wave propagation (GWP) is commonly employed for the design of SHM systems. However, GWP is sensitive to variations in the material properties, often leading to false alarms. To address this issue, uncertainty quantification (UQ) is employed to improve the reliability of the predictions. Computational structural mechanics is a useful tool for the simulation of GWP. Even so, the application of UQ methods requires numerous solutions, while large-scale, transient GWP simulations increase the computational cost. In this paper, we propose a machine learning (ML)-based reduced order model (ROM), annotated as BO-ML-ROM , to decrease the computational time of the GWP simulation. The ROM is integrated with a Bayesian optimization (BO) framework to adaptively sample the data for the ROM training. The results showed that BO outperforms one-shot sampling methods, both in terms of accuracy and speed. The developed ROM, which is orders of magnitude faster than the original solver, is then applied for forward uncertainty quantification of the GWP in an aluminum plate and a composite panel under varying material properties. The UQ analysis reveals the higher impact of the uncertainties in the wave reflections. Furthermore, to compute the influence of the material properties on the predictions, a sensitivity analysis (SA) is performed using the variance-based Sobol' indices and the Shapley additive explanations, where it is shown that the uncertainties in the elastic properties have a varying influence across time. The predicted results reveal the efficiency of BO-ML-ROM for the simulation of the GWP and demonstrate its utility for UQ and SA. [ABSTRACT FROM AUTHOR]

In practical engineering scenarios with limited labeled samples, conventional semi-supervised diagnostic methods face challenges in achieving satisfactory identification outcomes. To address the aforementioned issues, this paper introduces an incremental semi-supervised learning (ISL) approach based on boosting efficient attention (BEA) assisted cyclic adversarial auto-encoder (CAAE), referred to as BEA-CAAE. The CAAE enhances unsupervised feature representation by simultaneously constraining the distribution of encoded features and aligning elements of the reconstructed samples through a cyclic encoding strategy. The BEA improves classical attention weights' activation strength to better capture vital information, thereby boosting the feature extraction capabilities of both CAAE and the classifier. The ISL employs a stepwise pseudo-label propagation strategy to incrementally filter high-confidence samples, enhancing sample and label utilization, and improving diagnostic accuracy under low label rate conditions. Experiments conducted on multiple test rigs with simple structures as well as large-scale rotating components test rigs that mimic real-world engineering conditions have demonstrated that the proposed method exhibits a significant advantage over existing semi-supervised fault diagnosis approaches in terms of fault diagnosis accuracy and generalization capability, especially under low label rate conditions. [ABSTRACT FROM AUTHOR]

Grid-interactive building control poses a critical challenge in the context of grid modernization and decarbonization. Recently, various artificial intelligence-based optimal control approaches have been proposed, providing innovative solutions to optimal building control problems. However, researchers and practitioners are now confronted with a dilemma when selecting appropriate control strategies, ranging from model-based (knowledge-incorporating) to learning-based (data-driven) approaches, and hybrid methods combining them. Although each algorithm in existing literature claims superiority over specific baselines, their performance has never been systematically compared and analyzed, owing to the absence of a unified platform for comprehensive evaluation. To fill this knowledge gap, we identify and implement all state-of-the-art approaches within a modular training and evaluation framework, assessing their efficacy in a grid-interactive building control problem. In this paper, we also introduce a streamlined hybrid method that complements existing hybrid approaches. Our comparative study reveals and quantifies the advantages of hybrid methods: on average, they achieve near-optimal control while requiring less than 14% of the online computation of traditional model-based methods. To achieve this performance, they need as few as 2% of the training samples of purely learning-based methods. Finally, we provide insights into the merits, limitations, and implementation of each method to help researchers better understand the state of the art and future directions. The software framework implemented in this study is open-sourced to facilitate future research. [ABSTRACT FROM AUTHOR]

Longitudinal impulse, as a common dynamic problem of heavy haul trains, could induce the lateral instability of the coupler and the separation of the locomotive and wagon connection and thus seriously hinder the train running safety. The coupler force undergoes complex changes during longitudinal impulse transmission and exhibits strong nonlinear characteristics, which poses significant challenges to the identification of the coupler force. To address these issues, this paper reports a novel quantitative method for the coupler force identification of heavy haul locomotives. Firstly, the moving average filtering method is used to preprocess the signal of longitudinal relative displacement between the coupler and carbody (LRDCC), and the approximate relative velocity (ARV) feature is also extracted from the preprocessed signal. Then, a Convolutional Neural Network (CNN) model is constructed to extract high-level features from LRDCC and ARV. The model with randomly initialized weight parameters does not require additional training and thus reduces the computational cost. Finally, an Extreme Learning Machine (ELM) is used as the regression layer to process the extracted high-level features and further improve the identification performance. Additionally, the dung beetle algorithm is used to obtain the optimal model parameters to improve the coupler force identification performance. Not only a dynamics simulation but a field test is carried out to show that the proposed method could accurately detect the coupler force of heavy haul locomotives. Furthermore, the proposed method shows promising prospects in replacing the traditional monitoring method under the actual long-term working conditions of trains. • An indirect measurement scheme is proposed for coupler force dynamic identification. • The proposed network model presents high identification Accuracy and efficiency. • Method showcases strong generalization under complex, long-term train operations. [ABSTRACT FROM AUTHOR]

A product recognition system recognizes all products on the shelf images and determines their positions. A business equipped with an automatic product recognition system has a convenient follow-up of many human-powered activities while increasing customer satisfaction. That is, product recognition stands out with its benefits such as tracking shelf layouts and stocking their status, and improving the shopping experience for customers, especially the visually impaired ones. However, product recognition is a challenging problem of computer vision in terms of the difficulty of obtaining and updating datasets and the breadth of the product scale. On the other hand, the number of studies on product recognition is constantly increasing by using various computer vision and machine learning methods, and effective solutions are offered to this problem. This paper provide a comprehensive review in the field of researches of product recognition on grocery store shelves. In this article, data sets and approaches used in the literature for the development of an automatic product recognition system are examined and compared, and their benefits and limitations are commented. Finally, a guideline is provided for future researchers and new perspectives for future studies are presented. [Display omitted] [ABSTRACT FROM AUTHOR]

Long short-term memory (LSTM) is a recurrent neural network (RNN) framework designed to solve the gradient disappearance and explosion problems of traditional RNNs. In recent years, LSTM has become a state-of-the-art model for solving various machine-learning problems. This paper propose a novel regularized LSTM based on the batch gradient method. Specifically, the L 2 regularization is appended to the objective function as a systematic external force, effectively controlling the excessive growth of weights in the network and preventing the overfitting phenomenon. In addition, a rigorous convergence analysis of the proposed method is carried out, i.e., monotonicity, weak convergence, and strong convergence results are obtained. Finally, comparative simulations are conducted on the benchmark data set for regression and classification problems, and the simulation results verify the effectiveness of the method. [ABSTRACT FROM AUTHOR]

This paper focuses on the hypothesis of optimizing time series predictions using fractal interpolation techniques. In general, the accuracy of machine learning model predictions is closely related to the quality and quantitative aspects of the data used, following the principle of garbage-in, garbage-out. In order to quantitatively and qualitatively augment datasets, one of the most prevalent concerns of data scientists is to generate synthetic data, which should follow as closely as possible the actual pattern of the original data. This study proposes three different data augmentation strategies based on fractal interpolation, namely the Closest Hurst Strategy , Closest Values Strategy and Formula Strategy. To validate the strategies, we used four public datasets from the literature, as well as a private dataset obtained from meteorological records in the city of Braşov, Romania. The prediction results obtained with the LSTM model using the presented interpolation strategies showed a significant accuracy improvement compared to the raw datasets, thus providing a possible answer to practical problems in the field of remote sensing and sensor sensitivity. Moreover, our methodologies answer some optimization-related open questions for the fractal interpolation step using Optuna framework. [ABSTRACT FROM AUTHOR]

The critical heat flux (CHF) is an important parameter determining the heat transfer capability of nuclear reactors. Therefore, prediction of CHF with accuracy and correct understanding is essential for the design and safety analysis of nuclear power plants (NPPs) and industrial boiling systems. This paper focuses on the CHF prediction using the Gaussian process regression (GPR), a machine learning (ML) technique for modeling nonlinear systems. The covariance kernel is a critical component of GPR modeling because it contains assumptions about the function we want to know and defines the dependence and similarity between the data. In this study, the prediction of CHF is investigated during training and prediction in two different approaches: isotropic and anisotropic covariance kernels. Besides, we evaluate the influence of various isotropic and anisotropic kernels on the accuracy of CHF prediction and quantification of uncertainty encoded in the posterior variances in each of the approaches. The use of anisotropic kernels, considering different shape parameters in line with different data dimensions, results in higher accuracy and better generalization. In addition, compared to other ML tools such as support vector regression (SVR) and artificial neural networks (ANNs), the GPR with anisotropic kernels has much better performance. The evaluation criteria involving root mean square error (RMSE) and mean absolute percentage error (MAPE) in anisotropic kernels are significantly improved compared to isotropic kernels. For example, in squared exponential and rational quadratic kernels, RMSE and MAPE values improved by {65.81%, 67.28%} and {61.97%, 60.12%} values, respectively. The results of the GPR method with the anisotropic kernels show the relative superiority of this method compared to SVR and ANN. The lowest RMSE and MAPE values of all three methods were compared, and these values have improved in GPR compared to SVR by 96.01% and 94.25% and compared to ANN by 84.40% and 85.51%, respectively. Finally, some valuable ideas and practical findings will be offered based on numerical simulations and comparisons between isotropic and anisotropic kernel assumptions. Since the approach of using anisotropic kernels has high computational time despite its high flexibility, we will address this issue in future studies and also use this approach for other nuclear engineering problems. [Display omitted] • A flexible GPR structure is presented. • We compared isotropic & anisotropic kernels for critical heat flux prediction. • Anisotropic model outperforms isotropic in critical heat flux prediction. • Anisotropic GPR outperforms SVR & ANN for critical heat flux prediction. • Broader applicability to other CHF predictions in nuclear engineering applications. [ABSTRACT FROM AUTHOR]

Complex-valued neural networks (CVNNs) have become a powerful modelling tool for complex-valued data processing. Because most of the critical points of CVNNs are saddle points, the gradient-based learning algorithms for CVNNs enjoy more chances to reach the global minima while suffering from slow convergence. To this end, we propose a hybrid complex spectral conjugate gradient learning algorithm for fast training CVNNs in this paper. The proposed algorithm combines the scaled negative gradient with a Barzilai–Borwein stepsize and an optimized conjugate term to define a new training direction, thus providing an accurate approximation of the second-order curvature of the objective function. The complex Wolfe conditions are employed to adaptively determine the optimal training stepsize. Under mild conditions, the descent property of the training direction and the convergence of the proposed algorithm are theoretically established. Simulation results on a number of benchmark complex-valued data processing problems demonstrate the efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In the paper, we present a new transfer subspace learning algorithm termed discriminative transfer regression (DTR) for cross-domain image recognition, in which low-rank representation (LRR), discriminative regression, local geometry preserving, and different norm minimization are integrated in to a united framework for transfer learning. Firstly, both the global structure and the local geometry information of the original data are preserved by imposing low-rank and sparse constraints on the reconstruction coefficient matrix. Secondly, DTR algorithm can overcome the disturbance of outliers and noises. Thirdly, the local manifold structure of the observed samples with the same semantics from the source and target domains is captured by the adaptive weight graph. Fourthly, the discriminative information of the samples from the source domain is encoded to the target domain based on ridge regression (RR). Meanwhile, the small-class problem confronted by RR and its extensions, that the obtained projection matrix is limited by the number of classes, can be effectively solved. In addition, the convergence and computational complexity of DTR algorithm is analyzed. An extensive range of experiments on several cross-domain image databases demonstrate the superiority of the DTR algorithm. [ABSTRACT FROM AUTHOR]

Modernizing traditional power grids into smart grids represents a significant advancement in improving efficiency and sustainability within the energy sector. However, integrating renewable energy sources and the intricate network of interconnected devices has presented new challenges, especially in grid stability. Anticipating and maintaining grid stability ensures a continuous energy supply and prevents potential disruptions. This research paper explores the smart grid stability issue through machine learning. Two distinct scenarios are examined. In the first scenario, the problem is approached as a binary classification task, where grid states are categorized as stable or unstable, a well-established method for addressing grid stability. In the second scenario, an effort is made to predict continuous values that reflect the degree of grid stability. These continuous values are subsequently mapped to a conditional function, facilitating stability detection based on a predefined threshold. To address data imbalance, two balancing strategies, specifically the Synthetic Minority Over-sampling Technique (SMOTE) and K-means SMOTE, are employed in each scenario. The analysis covers a range of regressors and classifiers, focusing on tree-based models, boosting algorithms, ensemble learners, and Multilayer Perceptrons (MLP). The investigation results demonstrate that combining the K-means SMOTE strategy with the CatBoost Classifier in the first scenario achieves the highest accuracy, reaching an impressive 99.6%, and an exceptional ability to detect grid instability, achieving 100% accuracy. Furthermore, the results of the second scenario are promising, with accuracy rates reaching 99.4%, thanks to the utilization of a stacking ensemble learner. Notably, this study introduces Explainable AI, a groundbreaking initiative in this field, to delve into the inner workings of the proposed models and enhance their transparency. This pioneering effort marks a significant step forward in understanding and optimizing the predictive capabilities of machine learning models applied to smart grid stability. [Display omitted] • Reframing the smart grid stability problem as a regression task. • Underscoring the significance of predicting the grid stability value. • Assessing the impact of data balancing strategies on the prediction results. • Evaluating several classifiers and regressors for smart grid stability. • Achieving 100% instability detection accuracy using K-means SMOTE and CatBoost. • Pioneering eXplainable AI (XAI) techniques to enhance model transparency. [ABSTRACT FROM AUTHOR]

Healthcare supply chain management is vital for the adequate and timely delivery of essential medical resources to healthcare facilities. In this context, a machine learning model is proposed in this paper to enhance the service of healthcare supply chains by predicting both the medical supply quantities and its timely delivery. This proposed work utilizes the multi-task learning as both of the interrelated tasks, such as the "shipped quantity" of the medical supplies and its "actual days to delivery", simultaneously optimize their performance to improve supply chain predictions significantly. The prioritized multi-task learning with task-specific regularization provides better learning for the task "actual days to delivery" over "shipped quantity" by considering its significance in healthcare. Additionally, this task-specific regularization also prevents overfitting for the training of the model. The results and its analysis show a significant advancement of 0.3522 and 0.3531 mean absolute error and mean square error for predicting both the tasks. The proposed work outperforms the existing work in terms of mean absolute error, mean square error, root mean square error and R-squared (R 2). In addition, the machine learning interpretation technique is used to assess the contribution of each feature in prediction by the proposed model. • Efficient prediction of medical supply quantities and delivery time in healthcare. • Prioritized multi task learning enhances accuracy as per significance of task. • Task-specific regularization prevents overfitting during training. • Proposed work outperforms existing approaches, enhancing performance. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative data-driven approach to uncertainty quantification (UQ) in complex engineering designs based on polynomial chaos expansion (PCE) and least-square support-vector machine (LSSVM). While PCE is a prevalent UQ method, its reliance on a predefined model form poses limitations in the model complexity, training accuracy, and efficiency in high-dimensional settings. To overcome this, we propose a nonparametric reformulation that draws equivalence with the kernel-based LSSVM. Leveraging special implicit kernels based on Hermite or Legendre polynomials, our method achieves accurate predictions with reduced training data. The model is trained through the dual space LSSVM formulation, thereby exploiting the so-called "kernel trick", while PCE coefficients up to an arbitrary order are efficiently obtained post-training. Validation encompasses a diverse range of scenarios, including standard benchmarks and real-life applications in electrical engineering involving up to 26 independent random input parameters. The proposed "PCE-LSSVM" method exhibits superior performance over traditional PCE implementations. It achieves up to 7 times smaller root-mean-square error and up to 10 times lower dispersion across various training datasets, showcasing superior performance even with a significantly reduced number of training samples. Notably, this approach is 2 to 50 times more efficient compared to alternative approaches such as ordinary least square regression or Gaussian quadratures. Overall, PCE-LSSVM emerges as a powerful and efficient tool for accurate UQ in complex engineering systems. • Nonparametric polynomial chaos expansion via least-square support-vector machines. • Link between spectral and kernel-based machine learning methods. • Novel infinite-dimensional kernels for Gaussian and uniform variability. • Higher accuracy with lower number of training samples. • Applications to the uncertainty quantification of real-life electronic designs. [ABSTRACT FROM AUTHOR]

Data-driven prognostics of systems exploit sensor measurements to predict the degradation evolution and anticipate failures, corresponding to the estimation of the remaining useful life (RUL). This task uses feature engineering to build prognostic indicators (HI) and machine learning (ML) to estimate the RUL. However, high variability in data coming from similar systems operating under different conditions negatively affects the RUL performance. Hence, this paper presents a new methodology that combines feature and ML engineering methods to provide an explainable RUL prediction. The key contributions lie in constructing efficient prognostic indicators that isolate distinct profile trajectories, enabling adaptive RUL extraction for each system. An ensemble of heterogeneous ML predictors is also trained using these indicators and RUL trajectories, effectively addressing variability issues and enhancing RUL performance. The proposed methodology is rigorously validated using NASA-provided turbofan engine data (C-MAPSS), demonstrating its performance, compared to state-of-the-art results, with improved score and accuracy of prediction. • Explainability of RUL calculation considering the variability of degradation trajectories. • Enhancing the adaptability of predictions to different operating conditions. • Handling epistemic uncertainties in RUL estimation. • High accuracy and precision of the estimated remaining useful life. [ABSTRACT FROM AUTHOR]

A fuzzy inference system consists of a machine learning concept that combines accuracy and interpretability. They are divided into two main groups: Mamdani and Takagi–Sugeno-Kang. While Mamdani models favor interpretability, Takagi–Sugeno-Kang models provide more accurate results because of their ability to approximate a nonlinear system through a collection of linear subsystems. The evolving Takagi Sugeno model inspired a new class of Takagi–Sugeno-Kang models classified as an evolving fuzzy system, which can update their structure and functionality to adapt themselves to changes in the data. However, these models may provide several rules that reduce the interpretability. Furthermore, as they usually present many hyper-parameters, it can be challenging to obtain results that satisfy specific requirements in terms of the accuracy-interpretability trade-off. To overcome such shortcomings, this paper introduces a new model in which the only hyper-parameter is the maximum number of rules. Consequently, the user can define the number of rules considering the accuracy-interpretability trade-off. The introduced models are evaluated using benchmark time series, three well-known financial series, S&P 500, NASDAQ, and TAIEX, and renewable energy datasets. The results are compared with other state-of-the-art machine learning models, such as classical models and some rule-based evolving Fuzzy Systems. The results are evaluated regarding error metrics and the number of final rules. The proposed model obtained similar or equal performance in the simulations to the compared models with increased interpretability. The code of the proposed model is available at https://github.com/kaikerochaalves/NTSK.git. • A new Takagi–Sugeno-Kang (NTSK) algorithm is proposed. • The proposed model achieves increased interpretability and simplicity. • The model is applied to financial and photovoltaic energy forecasting. • The introduced model is compared with established models in the literature, presenting superior or equal performance. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries undergo capacity loss and power fade over time. Despite indicating degradation, these changes lack internal insights. Degradation modes group various mechanisms but are challenging to quantify due to aging complexity. In this paper, a noninvasive and comprehensive diagnostic framework is proposed for the accurate estimation of the state of health (SOH) and degradation modes. A large amount of synthetic data is generated from the mechanistic model to cover many typical aging paths without using redundant experimental data. A data-driven multistep diagnosis method is developed by using incremental capacity sequences. This method analyses unique sensitivities to voltage responses from different degradation modes and identifies them sequentially to simplify complex interactions. In addition, overpotential correction is incorporated to estimate battery degradation modes under normal usage. This framework is validated through experimental data under various operating conditions, affirming the 2 % accuracy of SOH estimation and the effective automatic quantification of degradation modes. Furthermore, the method is applicable to common state-of-charge (SOC) windows ranging from 25% to 85 % (3.6 V–4.1 V for the voltage window) and a high current rate up to C/4. The diagnostic framework does not rely on any regular calibration data during model training and thus has high potential for practical application. • A novel framework without regular calibration is proposed for battery diagnosis. • Synthetic training dataset with typical aging paths is generated via mechanistic model. • Data-driven multistep diagnosis is employed to estimate SOH and degradation modes. • Common charging SOC window and high current rate enable practical aging diagnosis. [ABSTRACT FROM AUTHOR]

Addressing the urgent need for accurate carbon emissions forecasting to support global emissions reduction goals, this paper introduces a novel approach for carbon emissions prediction that dynamically considers the spatial–temporal correlation of carbon emissions across forecasting targets. Traditional statistical and machine learning models have limitations, such as oversimplification and inefficiency in capturing evolving dynamics among multiple forecasting targets, alongside a focus on longer forecasting horizons like monthly or yearly. To tackle these, we propose an innovative Dynamic Spatial–Temporal Graph Convolutional Recurrent Network (DSTGCRN), a blend of graph convolutional and recurrent neural network structures customized for up-to-date multi-regional spatial–temporal predictions at a daily level. Comprehensive empirical analyses on datasets from China, the US, and the EU confirm DSTGCRN's superior performance and robustness across diverse geographical contexts. It outperforms the second-best among 10 baseline models, achieving 40.6%, 24.6%, and 38.5% improvements in MAE, RMSE, and MAPE, respectively, across various horizons. The incorporation of environmental data, including temperature and Air Quality Index, as supplementary predictors in the DSTGCRN model, has demonstrated its efficacy in the context of the China dataset. The DSTGCRN model's improved accuracy and daily multi-regional forecasting deepen emission dynamics understanding, supporting the development of informed and region-specific environmental policies that can respond promptly to changes. [ABSTRACT FROM AUTHOR]

In literature, many studies try to analyze healthcare usage and generated decision support systems. In this paper, the aim is to generate a decision support system for insurance companies in the United States according to the federal dataset. The data set contains variables from the United States Healthcare Administration formal data group and they are; group of age, group of healthcare insurance, group of nationality, Corporate Social Responsibility (CSR) usage, and Advance Premium Tax Credit (APTC) usage. The best model for each state in the United States is determined with the dataset from 2014 November to 2015 February. In this study, various statistical models are attempted to generate independent and optimal models for each state. In the model selection process, three different metrics are used. Accuracy rate, f1score and precision score are used in the model selection process and models are compared to each other according to these three metrics for each state uniquely. Consequently, the proposed model is used with a decision support scheme to support customer service workers in healthcare insurance companies. The decision support system under consideration can facilitate a substantial decrease in the duration of interactions between customer service representatives and clients. Additionally, this system can generate more logically sound and efficient customer offers. [ABSTRACT FROM AUTHOR]

The progression of the fuzzy domain is propelled synergistically by the evolution of science via academic papers and the advancement of technology through technical patents. However, the intrinsic interrelationships within the science and technology (S&T) interactive landscape of this domain remain largely unknown, as few studies attempt to explore these close interrelationships. To bridge this research gap, based on 161,060 academic publications and 36,693 granted patents, we measured their mutual attribution between S&T from the perspective of textual semantics and structure information on top of a quantitative network monitoring process. The results showed that the fuzzy domain lacked technology-oriented topics in terms of semantic relations and presented an interactive pattern where science was ahead of technology; that is, science worked as an engineer to expand the knowledge boundaries of the research field, and technology existed more as a beneficiary. This article presents cutting-edge insights into the intrinsic S&T interactions of the fuzzy domain in a visual and quantitative approach for the first time and aims to aid researchers in theoretically grasping the S&T innovation laws. [ABSTRACT FROM AUTHOR]

The conventional standardized theoretical models (such as Webster, Alcelik, Indo-HCM) used for the delay estimation revolve around the mathematical hypothesis and assumptions, making them static with limitations in accommodating the dynamic traffic behaviors. Recent advances in artificial intelligence make machine learning techniques suitable for estimating vehicle control delay compared to conventional methods. This paper demonstrates the application of several machine learning models developed by focusing on the fluctuations of traffic observed at an intersection having heterogeneous traffic conditions in Ahmedabad city for delay estimation. Several parameters are extracted from on-field and video surveys. However, not all parameters are relevant for accurately estimating vehicle control delay. Hence, a feature selection process consisting of several feature-scoring techniques from filter, wrapper, and embedded methods is applied to all the parameters. This process gave insights into the most statistically relevant independent parameters, and out of all the parameters, cycle time was found to be insignificant, with a feature score of 0 from almost all techniques. Hence, it was removed, and then the prominent parameters were then used to build a vehicle control delay model using support vector regression (SVR), K-nearest neighbor (KNN), artificial neural network (ANN), random forest regression (RF), and decision tree regression (DT). Error distribution, standard deviation of errors, coefficient of Determination (R2), and Root Mean Squared Error (RMSE) are the parameters used for evaluating the performance of the machine learning models. RF outperformed them all with a standard deviation of errors, R2, and RMSE of 11.065, 0.926, and 11.081 on testing data. But ANN, KNN, and DT also performed satisfactorily. Compared with conventional standardized theoretical models, all the machine learning models except SVR performed better. [ABSTRACT FROM AUTHOR]

The past work on Information Retrieval (IR) targeting web document collections shows that incorporating a measure that measures the quality of web documents, or rather the document prior (e.g., PageRank), into an IR system improves the retrieval effectiveness. In this study, we introduce new document priors and empirically investigate their effect by employing them as features in a learning to rank (LTR) deployment. The experiments are performed on the two standard Web IR test collections: the ClueWeb09 and the ClueWeb12 datasets, which include 500 and 733 million web documents, respectively, and the associated TREC & NTCIR query sets with a total number of 1,204 queries. A strong baseline is formed by using standard features introduced in the previous works, with respect to which the effect of newly introduced features in this paper is empirically compared. We test our features by LambdaMART, which is state-of-the-art LTR technique. The results reveal that the features introduced in this work led improvement in retrieval performance on the test collections in use. The introduced features are classified into 5 groups with respect to functional properties and each group is also analyzed in detail. • Measuring the quality of a web document is a challenging task. • A web page contains various elements that indicate quality. • Document priors can be used as query-independent features in LTR deployments. • Introduced query-independent features can measure the quality of web documents. • Contribution of the new feature groups to the retrieval performance is examined. [ABSTRACT FROM AUTHOR]

While local explanations for AI models can offer insights into individual predictions, such as feature importance, they are plagued by issues like instability. The unreliability of feature weights, often skewed due to poorly calibrated ML models, deepens these challenges. Moreover, the critical aspect of feature importance uncertainty remains mostly unaddressed in Explainable AI (XAI). The novel feature importance explanation method presented in this paper, called Calibrated Explanations (CE), is designed to tackle these issues head-on. Built on the foundation of Venn-Abers, CE not only calibrates the underlying model but also delivers reliable feature importance explanations with an exact definition of the feature weights. CE goes beyond conventional solutions by addressing output uncertainty. It accomplishes this by providing uncertainty quantification for both feature weights and the model's probability estimates. Additionally, CE is model-agnostic, featuring easily comprehensible conditional rules and the ability to generate counterfactual explanations with embedded uncertainty quantification. Results from an evaluation with 25 benchmark datasets underscore the efficacy of CE, making it stand as a fast, reliable, stable, and robust solution. [ABSTRACT FROM AUTHOR]

The long-tailed distribution data poses many challenges for machine learning because the tail classes are extremely scarce. Long-tailed data augmentation is a powerful technique for enriching the tail class diversity. However, existing methods often treat each class independently, assuming that classes are isolated from each other. These approaches overlook the presence of easily confused tail classes, making it challenging for models to distinguish between them accurately. In this paper, we propose a long-tailed classification method based on data augmentation, which utilizes multi-granularity knowledge to select and combine easily confused tail samples, thereby enhancing the classification performance of these samples. First, we utilize multi-granularity knowledge and semantic relation trees to build a class relation matrix. This matrix records the relationship between classes and helps the model search for easily confused classes from bilateral branch samplers. Second, we crop and combine the easily confused head and tail class samples in a foreground–background manner to generate new samples, thereby augmenting the model training. The extensive head class knowledge is transferred to the scarce tail class samples through the combination of fore-background, and the discriminative and generalized abilities of the model are improved. The experimental results affirm the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

• The global and multi-scale local causal features are extracted to interpret the model and improve diagnosis accuracy. • The performance of the initial model can be improved by adopting an extensible framework to add enhancement nodes. • The sample incremental learning is developed to update incrementally based on the previous models without retraining. • Two experiments on bearing components validate the effectiveness and superiority of the proposed method. Intelligent fault diagnosis (IFD) plays a significant function in ensuring the reliable operation of mechanical equipment. However, most existing IFD methods are trained in batch learning way and the feature extraction process is unexplainable and it is challenging to satisfy the complex diagnosis requirements. Thus, this paper proposes a causal broad learning model (CBLM) guided by global and multi-scale local causal features for incremental machinery fault diagnosis. Firstly, rich global and multi-scale local causal features are extracted for training CBLM. Then, incremental learning capability is developed to update model by expanding or modifying the original weights, considerably reducing the time consumption and greatly improving the computational efficiency. When the initial model has inadequate nodes for feature learning, CBLM performs structural incremental learning by adding extra nodes to improve the diagnostic performance. As new samples with various fault degrees are entered, sample incremental learning is built to rapidly update based on previous model without retraining. Finally, two experimental results on bearings indicate that CBLM improves the testing accuracy of the initial model by 0.13% to 52.22% and 1.95% to 57.64%, respectively, and remains above 97.22% and 99.77% for the updated models. The training time consumption is reduced by 25.06 s to 133.0 s, 20.78 s and 141.9 s, respectively, and the subsequent models update time are only about 12 s and 10 s. Consequently, the proposed CBLM is an effective online IFD method because it is obviously superior to the existing IFD methods in regards to time consumption and diagnosis accuracy. [ABSTRACT FROM AUTHOR]

This paper addresses the stochastic discrete lot-sizing problem on parallel machines, which is a computationally challenging problem also for relatively small instances. We propose two heuristics to deal with it by leveraging reinforcement learning. In particular, we propose a technique based on approximate value iteration around post-decision state variables and one based on multi-agent reinforcement learning. We compare these two approaches with other reinforcement learning methods and more classical solution techniques, showing their effectiveness in addressing realistic size instances. • Addressing the Stochastic Discrete Lot-Sizing Problem (SDLSP). • Open-source environment for SDLSP Reinforcement Learning (RL). • Presenting LSCMA as our multi-agent RL-based proposed method for SDLSP. • Introducing Branch and Bound ADP as another proposed method for the SDLSP. • A performance comparison via out-of-sample simulations under different conditions. [ABSTRACT FROM AUTHOR]

Radio Frequency (RF) energy harvesting has been used to power wireless and low-powered devices. However, RF energy harvesting has limitations in terms of the amount of power that can be collected based on signal availability. Hence, energy prediction is essential to improve energy harvesting circuits' performance. Previous research has mainly focused on improving power harvesting policies or theoretically estimating the harvested energy. Very few works have considered the prediction of the RF signal as time series data using real RF measurements. Moreover, challenges such as the power consumed by the circuit's harvesting decisions and the impact of outliers on the model performance haven't been addressed yet. This paper presents a complete pipeline for developing the best predictive model for RF energy in cellular frequency bands. Real-time measurements are taken in different frequency bands using software-defined radio technology. We use four artificial intelligence techniques to model the RF energy signal. Additionally, we propose an optimized model with an enhanced loss function, which makes the model more resilient to anomalies, saving computational power and time consumed in cleaning the data. The four algorithms are investigated, and their prediction accuracies are compared. The average power of a period of 5 min is accurately forecasted. Numerical results in the 1960 MHz band show that long short-term memory has the best performance, followed by the DeepAR algorithm with prediction accuracies of 95.76% and 95.02%, respectively. Moreover, the proposed optimized model showed a 32.2% lower prediction error than the traditional models. [ABSTRACT FROM AUTHOR]

Inverse heat transfer problems are ill-posed problems and their solution is challenging. Conventional (hard computing) solution methods were developed for this purpose in the past, but they are not well applicable in cases including phase change, which contain strong non-linearity and bring additional computational difficulties. Soft computing methods, which currently experience very rapid development, are a promising tool for the solution of such problems. This paper addresses an inverse heat transfer problem with phase change, in which the boundary heat flux is estimated. Four methods based on distinct mathematical principles are applied to this problem and thoroughly compared. These methods include a conventional Levenberg–Marquardt method (LMM), a predictive fuzzy logic (PFL)-based method, a population-based meta-heuristic method called LSHADE (a state-of-the-art differential evolution variant), and a recently developed surrogate-assisted method coupled with differential evolution, referred to as LSADE method. Furthermore, a reformulation of the problem was developed, utilising a dimension reduction scheme and a decomposition scheme that led to sub-problems with different time frames. This reformulation brought extensive computational improvements. Results of the comparison of the methods then showed that the LMM and the PFL behave well in case without phase change but their performance deteriorates substantially in case with phase change. The LSHADE and the LSADE showed superior performance in the solution of the inverse problem with the phase change. Moreover, their performance was rather stable and insensitive to the location of the temperature sensor, which was the source of data for the estimation. • Inverse heat transfer problem with and without phase change was addressed. • Boundary heat flux was inversely identified from temperature readings. • Four solution methods were investigated and compared to each other. • Levenberg–Marquardt method (LMM) suffered from low performance due to non-linearity. • LSHADE and LSADE methods significantly outperformed LMM and fuzzy logic. [ABSTRACT FROM AUTHOR]

In recent years, computational advancements have contributed to a significant increase in the volume and availability of multivariate time series data (MTSD). The ability to make use of MTSD is challenging, as it often suffers from missing values, random noise, varied sampling rates, and temporal granularities. In the modern era of machine learning, learning frameworks must accurately capture the data's temporal structure and have high generalization capabilities, as well as provide interpretability and explainability regarding its decisions. The use of temporal abstractions (TAs) and interval-based temporal patterns (TPs) has been proposed for learning from MTSD, overcoming existing challenges, and achieving state-of-the-art results on various tasks, however, improvements are needed in terms of the generalization capabilities and decision explainability. In this paper, we propose a novel interval-based method, Inter-Rel, which provides an additional layer of learning that exploits the temporal relations among the discovered interval-based TPs, enhances the feature space, and improves explanatory capabilities by shedding light on the relations between the TPs over time. To evaluate the effectiveness and additional benefits provided by Inter-Rel, we evaluate our method on various learning tasks and domains such as early sepsis detection; electroencephalogram-based (EEG-based) subject classification; and the categorization of malicious portable executables based on dynamic analysis. The experimental results demonstrate that Inter-Rel's use enhances classification performance by up to 16% in terms of area under the curve (AUC) or accuracy (depending on the task) while providing additional explanatory capabilities that can be leveraged by a domain expert. [ABSTRACT FROM AUTHOR]

In the face of uncontrolled offensive content on social media, automated detection emerges as a critical need. This paper tackles this challenge by proposing a novel approach for identifying offensive language in multilingual, code-mixed, and script-mixed settings. The study presents a novel multilingual hybrid dataset constructed by merging diverse monolingual and bilingual resources. Further, we systematically evaluate the impact of input representations (Word2Vec, Global Vectors for Word Representation (or GloVe), Bidirectional Encoder Representations from Transformers (or BERT), and uniform initialization) and deep learning models (Convolutional Neural Network (or CNN), Bidirectional Long Short Term Memory (or Bi-LSTM), Bi-LSTM-Attention, and fine-tuned BERT) on detection accuracy. Our comprehensive experiments on a dataset of 42,560 social media comments from five languages (English, Hindi, German, Tamil, and Malayalam) reveal the superiority of fine-tuned BERT. Notably, it achieves a macro average F 1 -score of 0.79 for monolingual tasks and an impressive 0.86 for code-mixed and script-mixed tasks. These findings significantly advance offensive language detection methodologies and shed light on the complex dynamics of multilingual social media, paving the way for more inclusive and safer online communities. [ABSTRACT FROM AUTHOR]

Efficient forecasting of ship order books holds immense significance in the maritime industry, enabling companies to optimize their operations, allocate resources effectively, and make informed decisions. However, volatile characteristics within historical order books pose challenges in achieving reliable, intelligent, and precise forecasts. This paper presents a novel ensemble deep random vector functional link (edRVFL) algorithm to anticipate future ship order book dynamics. The edRVFL leverages deep feature extraction and ensemble learning to enhance forecasting performance. To further elevate its capabilities, we introduce a discontinuous and parsimonious embedding strategy, which deviates from the conventional dense collection of continuous time steps used in vanilla edRVFL. This parsimonious embedding approach limits the model's complexity and boosts its generalization ability. We extensively evaluate the proposed method using ship order book data, and comparative studies demonstrate its superiority over alternative approaches. Our proposed edRVFL offers a promising solution for accurate and efficient ship order book forecasting, making it a valuable asset in the maritime industry's decision-making processes. The source codes utilized in this research are openly available on GitHub at the following link: https://github.com/crkkkaa/Ship-order-book-forecasting-by-an-ensemble-deep-parsimonious-random-vector-functional-link-network-. • A novel ensemble deep RVFL to anticipate ship order book dynamics is proposed. • We propose a parsimonious embedding algorithm to optimize temporal patterns. • The direct links ablation study is conducted for comparison. [ABSTRACT FROM AUTHOR]

Bayesian network (BN) structure learning is the basis of BN applications and plays a pivotal role in many machine learning tasks. Whereas remarkable progress in structure learning has been achieved in the past, making further improvements in the efficiency and accuracy of structure learning is a significant challenge. In this paper, we propose an efficient skeleton learning approach-based hybrid algorithm (ESLH), which consists of two phases. In the constraint-based phase, a dynamic threshold (DTH) strategy and a skeleton learning method based on triangle breaking (SLTB) are proposed to learn the skeleton of a BN structure efficiently. DTH designs a dynamic threshold to remove redundant edges in the initial skeleton with little time overhead. By the result of DTH, SLTB first finds, tests and breaks triangles in the initial skeleton to efficiently remove redundant edges and then removes the remaining redundant edges to discover the final skeleton. In the score-and-search phase, ESLH employs the hill-climbing algorithm to find the highest-scored structure. We propose a novel strategy to divide this phase into three steps, both utilizing the learned skeleton to constrain the search space and preventing the errors of the learned skeleton from reducing the quality of the final learned structure. Extensive experiments on benchmark BNs validate the effectiveness of DTH and SLTB and demonstrate that ESLH is more than five times faster than the state-of-the-art structure learning algorithms while maintaining the highest average accuracy. [ABSTRACT FROM AUTHOR]

Soil water retention curves (SWRC) are constitutive relationships that are critical for predicting the hydro-mechanical behaviour of unsaturated soil in a wide range of applications in geoenvironmental and geotechnical engineering, hydrology, and agricultural and soil science. Directly measuring SWRC can be costly and time-consuming. Recent research has shown that machine learning, especially artificial neural networks (ANNs), can effectively predict SWRC using easy-to-measure soil properties as inputs. However, significant questions remain about prediction accuracy and what are the most effective input parameters to use, and only shallow neural networks with one hidden layer have been developed in the past for this purpose. In this study, effectiveness of deep neural networks (DNNs) - ANNs with more than one hidden layer - for SWRC prediction is explored for a range of models with different combinations that require easy-to-measure input parameters. Specifically, the study investigates whether switching from a shallow neural network (SNN) to a deep neural network (DNN) can enhance the accuracy of SWRC predictions for these models. Significant differences are found in seven out of thirteen cases when shifting from SNN to DNN. It was also found that models including soil texture, augmented by either dry density or soil porosity as input parameters, perform well. Specific gravity, soil depth, and organic content, on the other hand, do not add to the predictive capability of these models. Findings of this paper can help improve SWRC prediction using machine learning and can lead to more accurate modelling of unsaturated soil behaviour. [ABSTRACT FROM AUTHOR]