Search

In recent years, the challenge of distinguishing vehicles of the same model has prompted a shift towards leveraging both global appearances and local features, such as lighting and rearview mirrors, for vehicle re-identification (ReID). Despite advancements, accurately identifying vehicles remains complex, particularly due to the underutilization of highly discriminative text regions. This paper introduces the Text Region Attention Network (TANet), a novel approach that integrates global and local information with a specific focus on text regions for improved feature learning. TANet uniquely captures stable and distinctive features across various vehicle views, demonstrating its effectiveness through rigorous evaluation on the VeRi-776, VehicleID, and VERI-Wild datasets. TANet significantly outperforms existing methods, achieving mAP scores of 83.6% on VeRi-776, 84.4% on VehicleID (Large), and 76.6% on VERI-Wild (Large). Statistical tests further validate the superiority of TANet over the baseline, showcasing notable improvements in mAP and Top-1 through Top-15 accuracy metrics. [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]

Precise forecasting of offshore wind speeds is paramount for various applications, including offshore wind energy production, disaster prevention and mitigation, and maritime navigation. This study introduces a novel model for point and interval prediction of offshore wind speed, incorporating an innovative two-layer decomposition technique, gated recurrent unit (GRU), and kernel density estimation (KDE). Initially, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is utilized to decompose the raw series into multiple subsequences, thus alleviating the inherent data nonstationarity. Subsequently, we employ the refined composite multiscale fuzzy entropy (RCMFE) to reconstruct the subsequences into multiple components, thereby reducing the computational complexity. Variational mode decomposition (VMD) is utilized to enhance the modeling accuracy to decompose the high-frequency component, thereby generating a set of submodels. The GRU, a specialized recurrent neural network architecture, is leveraged to forecast the remaining components and submodels, producing a series of subresults. The subresults are linearly summed to obtain the final point prediction result. Finally, based on point prediction, employing KDE to gauge the probability density distribution of prediction errors culminates in the derivation of the offshore wind speed prediction interval. The experimental results substantiate the superior predictive performance of the proposed prediction model. • This paper forecasts the offshore wind speed using the ICEEMDAN-RCMFE-VMD-GRU-KDE. • Two-layer decomposition based on ICEEMDAN-RCMFE-VMD improves forecasting accuracy. • KDE (box) outperformed other methods for offshore wind speed interval prediction. • Testing is conducted using wind speed data collected from two buoy stations. • Interval prediction addresses the shortcomings of point prediction. [ABSTRACT FROM AUTHOR]

The performance of object detection networks is often limited by the depth of the feature extraction network. Increasing network parameters may yield limited improvements in the detection system's performance. Additional careful designs of network details are necessary, but they can significantly increase training difficulty. This paper introduces a novel object detection method that utilizes generative adversarial training. Our approach focuses on minimizing the EM distance (Wasserstein distance) of the feature distribution as the primary training objective. We enhance the image features so that training of GAN (Generative Adversarial Networks) yields a feature distribution that exceeds that of the original dataset, obtaining a better feature extraction network. A new loss function is also added to the adversarial training process to ensure stable improvement of the detector. A comparative experiment conducted with the original CenterNet network on MS COCO (Microsoft Common Objects in COntext) 2017 reveals that the generative adversarial training method significantly improves the average precision for most of the examined backbone networks. Among the four backbone networks employed in the experiments, the mean improvement in network AP (Average Precision) values ranged from 0.3 to 0.9, demonstrating their success with minimal training efforts. Moreover, none of the four backbone networks experienced an increase in network parameters during inference. Experimental results indicate that the proposed architecture effectively enhances the network's feature extraction capability without compromising speed during inference. [ABSTRACT FROM AUTHOR]

Physics-informed neural networks (PINNs) usually confront significant difficulties to accurately solve partial differential equations (PDEs) due to many pathologies caused by gradient failures during training process. In this paper, a gradient disease regarding the ill-conditioned loss function of the PINN methodology is intensively investigated in both theoretical and experimental aspects. Particularly, the regular PINN approaches can obtain good predictions for trivial problems but may fail to learn solutions when their PDE coefficients and/or physical domain sizes vary. Besides, the influences of neural network structure to the PINN training quality are inferred from the theoretical analyses and also confirmed by relating experiments, in which using large-width multi-layer perceptrons (MLPs) is proved to be beneficial in stabilizing PINN training process. To overcome the abovementioned restrictions, a novel PINN methodology using hierarchically normalized technique (hnPINN) motivated from the developed theory is devised. The key idea of the proposed hnPINN is, on the one hand, to transform the original PDE system into one of two proposed dimensionless forms to alleviate the negative effects of PDE coefficients and domain size; on the other hand, to use secondary output scalers to flexibly calibrate the gradient flow for training effectively and improving the solution preciseness. The determination of the secondary output scaler is formulated by a heuristic framework inspired from theoretical analyses on the hnPINN gradient flow. The obtained results from some typical PDEs and common problems in solid mechanics strongly confirm the high effectiveness of the hnPINN in terms of solution accuracy, superior convergence and performance stability in comparison to those of the vanilla PINN and the non-dimensionalized PINN (ndPINN). As a preprocessing procedure, the hnPINN method is independent on network architectures and also greatly potential to combine with other state-of-the-art PINN models for effectively solving challenged issues in practice. • Limitations of regular PINN are shed light via theoretical and experimental analyses. • Hierarchically normalized PINN (hnPINN) for solving PDEs is proposed. • A hierarchical process is devised to normalize PDEs and calibrates network output. • Heuristic framework for selecting optimal secondary scaler is designed. • Numerical results through solid mechanics problems confirm hnPINN superiority. [ABSTRACT FROM AUTHOR]

Crowdsourcing provides a cost-effective labeling solution for the acquisition of labeled training samples for machine learning by employing workers on the Internet. A common approach to improving the label quality is to employ a truth inference method to infer integrated labels for samples from their multiple noisy labels obtained from different crowd workers. Although the quality of integrated labels is significantly improved compared with that of the original noisy ones, it still cannot completely eliminate the noises inevitably existing in the integrated labels. To further improve the label quality, this paper proposes a novel label noise correction method for crowdsourcing based on dynamic resampling (DRNC). DRNC first divides the dataset with inferred labels into a clean set and a noisy set through a filter. According to a certain proportion, the clean set and the noisy set are resampled to train multiple heterogeneous classifiers, which form an ensemble classifier. Then, the dataset is divided by the ensemble classifier into a new sub-noisy set and a sub-clean set. The whole process repeats multiple rounds, generating multiple sub-clean sets. Finally, these sub-clean sets are used to train classifiers, which jointly correct the wrong labels in the dataset by voting. Experimental results on 25 simulated and 4 real-world datasets consistently show that the proposed DRNC averagely improves the quality of labels as well as the quality of learned models in the range of 1 to 10 percentage points, compared with four state-of-the-art crowdsourcing noise correction methods. [ABSTRACT FROM AUTHOR]

Imbalance is a typical characteristic of data in the field of intelligent fault diagnosis. As a data augmentation method that both balances data and extends information, the generative adversarial network has aroused widespread concern in the data imbalance problem. However, it still suffers from high difficulty in model training and poor quality of generated samples. To address this issue, this paper proposes a progressive generative adversarial network, which is a strategy able to gradually generate complex signals from low-frequency signals to wide-frequency signals. In the developed network, on the one hand, decomposing signals into different frequency bands explicitly reduces the difficulty of directly generating high-dimensional and wide-frequency signals. On the other hand, different generative models can focus on different frequency bands, avoiding the interference of high-energy signals on the fault feature frequencies. In order to achieve good generative performance, the generators and training method for the progressive generative adversarial network are elaborately designed. The correlation shortcut avoids information suppression due to the poor selection of noise amplitudes, and the focusing shortcut forces the body of the generator to focus on key feature bands. Ultimately, the superiority of the progressive generative network is verified by evaluating the quality of the generated samples on three datasets and applying the generated samples to solve the data imbalance problem. • A progressive generation framework is proposed to improve the quality of the generated signal. • The proposed generator retains the correlation between low and high frequencies. • The proposed generator can focus on specific frequency bands. • Model at each level is trained independently to avoid the accumulation of errors. [ABSTRACT FROM AUTHOR]

This paper delves into enhancing underwater images to improve human observation of underwater scenes. To this end, a reinforcement learning-based human visual perception-driven image enhancement paradigm for underwater scenes is proposed, referred to as INSPIRATION. This paradigm is so named because it constructs rewards for guiding model training by incorporating metrics inspired by human visual perception, eliminating the need for reference images. It overcomes the limitations of deep models, which often result in poor performance in dynamic and diverse underwater scenes due to the scarcity of underwater images with enhancement references. Specifically, a residual-enhancement network, composed of residual modules and a channel-attention module, is utilized to extract features as a state. An extensible collection encompassing diverse image enhancement algorithms is utilized to provide an image enhancement algorithm as an action. A multi-non-reference human visual perception metric increment is utilized as a reward, and proximal policy optimization (PPO) is utilized to conduct reinforcement learning. This paradigm treats underwater images as sole inputs during both training and implementation, learning and organizing a sequence of image enhancement algorithms to explicitly achieve a step-wise image enhancement process, aligning the enhanced images with human visual perception. Extensive qualitative and quantitative evaluations conclusively demonstrate that our paradigm outperforms nine state-of-the-art underwater image enhancement methods in terms of visual quality and achieves better performance on five underwater image quality assessment measures across three underwater image datasets. Additionally, the potential advantages of our paradigm as a pre-processing step in other underwater computer vision applications are demonstrated. The code has been released publicly for reproducibility and evaluations at https://gitee.com/wanghaoupc/uie_inspiration. [ABSTRACT FROM AUTHOR]

Continuously growing demands due to the predictable faults or abnormal events of the flexible production line are becoming a challenge to easily cause the energy waste, which needs to accurately predict the real-time energy consumption of the actual production process. By reviewing the related works about prediction model approach and energy consumption analysis in the actual production application, it is necessary to overcome two main challenges: optimal prediction selection and internal relation mining of energy consumption under different equipment working conditions. To deal with the existing challenges, the paper proposes a novel attention-based Long and Short-Term Memory (LSTM) approach to predict energy consumption with temporal series under various equipment working conditions. This method offers forecasting support to form a complete prediction framework for the automatic Miniature Circuit Breaker (MCB) production line, which can be used to predict the specific working condition based on attention-based LSTM approach. By comparing various prediction approaches for energy consumption under the working condition prediction with various equipment of different production line, the Fully Connected Neutral (FCN) network approach can achieve a high accuracy and effectiveness based on MAE, R2 and MSE evaluations. [ABSTRACT FROM AUTHOR]

Image steganography is a technique of hiding secret information inside another image, so that the secret is not visible to human eyes and can be recovered when needed. Most of the existing image steganography methods have low hiding robustness when the container images affected by distortion. Such as Gaussian noise and lossy compression. This paper proposed a practical robust invertible network for image steganography (PRIS) to improve the robustness of image steganography, it based on invertible neural networks, and put two enhance modules before and after the extraction process with a 3-step training strategy. Moreover, rounding error is considered which is always ignored by existing methods, but actually it is unavoidable in practical. A gradient approximate function (GAF) is also proposed to overcome the undifferentiable issue of rounding distortion. Experimental results show that our method outperforms the state-of-the-art robust image steganography method in both robustness and practicability, achieved an average Peak Signal to Noise Ratio value of 34.28/32.96 on container/secret pairs under 5 different attacks. Codes are available at https://github.com/yanghangAI/PRIS , demonstration of our model in practical at http://yanghang.site/hide/. [ABSTRACT FROM AUTHOR]

Group activity recognition aims to recognize holistic activity in multi-person scene, necessitating consideration of the interactions between actors and their surroundings. It has various applications, such as public surveillance, video analysis. Nonetheless, existing works merely extract scene features as a supplementary component of activity features, failing to adequately explore the interplay between the scene and actors. To address this limitation, this paper proposes a Local–Global Context-Aware Graph Reasoning Model (LG-CAGR), which leverages and reasons through local and global context features to gain deeper insights into group activity within the scene. In particular, we present an innovative feature extraction strategy to harness local location features and global scene attributes, effectively complementing actor features by capturing spatial group topology and determining relative positions between actors. Subsequently, we delve into these features by devising a local–global group reasoning module that deduces pair-wise interactions between actors and scenes within Graph Convolutional Network, comprehensively elucidating correlations between overall scene and local individuals to construct group-level features. Multi-graphs are constructed considering actor's features, scene features as nodes, and interactions as edges. A self-attention graph pooling network is introduced to automatically integrate key actor features and form rich group-level features to recognize group activity. The results on Collective Activity Dataset, Collective Activity Extended Dataset, Volleyball Dataset and Public Life in Public Space dataset have reached 94.0%, 97.7%, 92.7% and 56.1%. Compared with existing methods using the same backbone, we exceeded 1%, 2.1%, 0.3%, and 14.9% respectively, affirming the superiority of the proposed method compared with state-of-the-art methods. • A novel progressive network structure for group activity recognition. • Context feature extraction strategy for the exploration of group activity. • Capturing temporal and spatial dynamics by reasoning local–global GCN. [ABSTRACT FROM AUTHOR]

The selection of a reliable and competent transportation company is a typical multi-criteria group decision-making (MCGDM) challenge in supply chain management. MCGDM has been widely used for decision support under ambiguity and uncertainty. This paper considers this problem in the setting of interval-valued q-rung orthopair fuzzy soft sets (IVq-ROFSS), a novel extension of fuzzy sets that presents an integrated approach to interpreting imperfect and ambiguous data. This study explores the novel Einstein aggregation operators (AOs) for this model, specifically the interval-valued q-rung orthopair fuzzy soft Einstein weighted average (IVq-ROFSEWA) and interval-valued q-rung orthopair fuzzy soft Einstein weighted geometric (IVq-ROFSEWG). These operators can consider large amounts of data that include all connections among parameters. Their fundamental properties (such as idempotency, boundedness, homogeneity, monotonicity, and shift invariance) are presented and proven. With the assistance of the new Einstein AOs, we design a novel MCGDM approach. A case study is presented to choose the most reliable transportation company that endorses the rationality and credibility of the proposed decision-making technique in supply chain management. Hence, this research helps with an innovative decision-support structure for assessing transport corporations. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) signals are essential, as they are used to measure muscular activity in different parts of the human body. The measurement and analysis of EMG signal lead to various applications of muscle disorders such as muscular dystrophy, myopathy, hand movements, etc. In this paper, an improved and effective hand movement classification model is developed for amputee subjects. It includes: (1) EMG feature extraction using Discrete Wavelet Transform (DWT), (2) EMG feature selection using binary Global Best Guided Gaussian Artificial Bee Colony (BGGABC), (3) Hand movements classification using Optimized k-nearest neighbors (OKNN) classifier. The EMG signal is taken from the DB3 of NinaPro dataset comprising 17 different prosthetic hand movements recorded from 11 amputee subjects. Thereafter, DWT is applied to decompose the EMG signal for extracting features. An improved wrapper-based feature selection technique (BGGABC) is used to select the optimal feature subset for effective classification. The two variants of KNN, i.e. Smallest Modified KNN and Largest Modified KNN are taken in which item strength to a class is optimized for efficient classification. The strength of an item to a class depends on distance and weight of an item to a class. Therefore, a multi-objective Non-dominated sorting genetic algorithm-II (NSGA-II) is used for optimizing these two contradictory parameters (distance and weight) simultaneously to have optimized variants, namely: Optimized Smallest KNN (OSKNN) and Optimized Largest KNN (OLKNN). Extensive results show that the proposed method OKNN achieved the highest classification accuracy of 93.07% (OLKNN) and 89.43% (OSKNN) compared with KNN variants and competitors. • An Optimized K-Nearest Neighbor classifier is proposed based on the Modified KNN. • DWT is applied for feature extraction to obtain key features from the raw EMG dataset. • BGGABC based wrapper FS is used to enhance the performance of EMG feature selection. • NSGA-II is used to optimize the parameters of MKNN to get enhanced performance. • OKNN is compared with KNN variants and competitors for hand movement classification. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the most serious threats to human health among skin lesions. Computer-aided diagnosis methods can assist patients in identifying and detecting skin lesion types early, thereby enabling corresponding treatments. In this paper, we propose a dual-branch neural network model Conformer with Residual Cosine Similarity Attention and Bidirectional Convolutional fusion strategy, named RCSABC-Conformer. The core of this network structure comprises three parts: a Convolutional Neural Network (CNN) branch with Residual Cosine Similarity Attention (RCSA), a Transformer branch, and a Feature Couple Unit with Bidirectional Convolutional strategy (BC-FCU). The RCSA module calculates the cosine similarity value between the feature map generated by the convolutional operation and the feature map of the residual edge to assess whether their semantic information is similar. The semantic information of similar parts is weighted by exponential normalization to enhance the network's memory of similar features of the same type of skin lesion. The BC-FCU module interactively fuses local features and global representations of skin lesion images with different resolutions in the two branches. Specifically, when the global representations is integrated into local features, we introduce a new bidirectional convolution strategy to extract the feature map from both forward and backward directions, and then select the element with the smaller feature value from the two directions to fuse into local features. In this way, we can minimize the interference of the artifact features extracted by the Transformer branch on the CNN branch. In addition, taking advantage of the Transformer branch's capacity to construct global representations, our model can learn contextual semantic information of normal skin and lesion areas to enhance model robustness. We conducted experiments on three datasets, consisting of clinical and dermoscopic skin lesion images, as well as a hybrid of both. The experimental results show that RCSABC-Conformer outperforms both advanced and classical classification methods in terms of classification accuracy across all three datasets, without requiring an increase in the number of parameters and computational complexity. Compared with the baseline model, the classification accuracy of our proposed method improves by 2.40%, 5.39%, and 4.44% on the three datasets, respectively. To the best of our knowledge, this is the first study to apply an interactive fusion dual-branch network for multi-disease classification on different modalities of skin lesion databases. Code will be available at https://github.com/AlenLi817/RCSABC-Conformer. [ABSTRACT FROM AUTHOR]

In this paper, we propose the use of deep learning-based image super-resolution to accelerate structural topology optimization. Topology optimization suffers from iterative computation and a time cost that increases with the number of elements. Recently, there have been attempts to accelerate topology optimization using deep learning-based models, but they often do not address a wide range of physical conditions or require extensive training data. This highlights the need for an approach that can effectively solve different problem conditions with less training data. Our approach first starts topology optimization at a low resolution to quickly obtain an optimized structure. It is converted to the structure at a higher resolution by using an image super-resolution model. Then, the final structure is obtained by performing topology optimization at this high resolution by using the converted structure as the starting configuration. The super-resolution model learns how to transform low-resolution structural features into high-resolution ones regardless of optimization conditions. As a result, it can be applied to any problems different from the problem used to generate the data for training the model. The proposed approach's excellent acceleration and generalization performance is demonstrated for three representative problems in structural topology optimization with a small number of training datasets. Furthermore, it has been shown to be effective in the deck arch bridge problem and the natural frequency maximization problem. Finally, the proposed approach is also found to be effective on the three-dimensional cantilever beam problem. [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]

Executing various production tasks is critical to the safe operation and efficient production of industrial processes. As one of them, the detection task of key quality variables directly affects the operation optimization and decision-making of industrial processes, but it is severely limited by the harsh environment and detection instruments. Therefore, the real-time prediction task of key quality variables becomes the basis for optimal control of industrial processes. To address this issue, this paper proposes a task-oriented deep learning framework based on a target-related transformer (TR-Former) network for industrial quality prediction tasks. Specifically, a new target-related self-attention (TR-SA) mechanism is developed to guide feature learning by adding attention scores between task-related target variables and other variables. As a result, the learned features in this instance will be guaranteed to be relevant to the target variable and useful for the quality prediction task. Moreover, the long-range dynamics of industrial process data can also be captured, which can further improve the prediction performance of the model. Finally, extensive experiments were conducted on two industrial processes to validate the superiority of the proposed method in terms of quality prediction tasks. The experimental results demonstrate that the proposed TR-Former method exhibits an improvement ranging from 3% to 13% in the mean absolute error indicator compared to the traditional transformer and other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper proposes a novel control strategy for uncertain magnetic levitation (UML) systems. Our method is fundamentally based on terminal sliding mode (TSM) and prescribed performance (PP) control theory. In contrast to conventional TSM and PP methods, which heavily rely on a precise model of the dynamics, our approach breaks free from the constraint of requiring such precision. It employs a neural network (NN) to approximate unknown functions and the components that may cause singularities in the control input. Additionally, the dual PP functions designed in this novel approach not only effectively manage maximum overshoot but also ensure symmetric steady-state tracking error (SSTE) boundaries, rapidly minimizing errors to zero within a fixed time. Moreover, this approach reduces chattering. On the other hand, to mitigate the adverse impact of input saturation, a fixed-time auxiliary system (FTAS) is introduced into the control design. As a result of these proposals, the approach enables the attainment of multiple desired performance indicators within a predetermined domain and a fixed time, particularly under conditions of uncertainties and input saturation. These indicators include convergence, SSTE, and maximum overshoot. The stability of the proposed scheme has been rigorously established by applying the stable principles of Lyapunov theory and fixed-time control (FTC) theory. Experiments serve to validate the exceptional performance of the proposed strategy under a range of diverse operating conditions. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the semi-supervised person re-identification (Re-ID) task. Under the semi-supervised setting, only a subset of individuals in large-scale datasets need to be labeled for training to reduce the manual annotation cost. To enhance recognition performance under this setting, we propose a novel three-stage, two-branch semi-supervised Re-ID framework. Within this framework, we implement a progressive training process that integrates three methods for training unlabeled data: identification learning based on the pseudo-label estimation technique, metric learning based on mining positive or negative pairwise relationships between samples, and feature consistency learning between views generated through various data augmentations. To make full use of the unlabeled data, the above three methods are gradually added in each training stage, and the defects of these methods are avoided. Moreover, to further improve the reliability of training samples, we design two modules for selecting reliable samples to determine which method to adopt for each unlabeled sample to reduce model performance deterioration due to incorrect pseudo-labels or incorrect sample pairs. Our framework can be combined with existing supervised methods and has less performance cost. Moreover, different components in our proposed framework can be used as plug-ins to integrate into existing semi-supervised Re-ID methods and improve their performance. Extensive experiments were conducted on two public Re-ID benchmarks that demonstrate the effectiveness of our proposed framework. [ABSTRACT FROM AUTHOR]

As the important decomposition components of insulating gas sulfur hexafluoride, the accurate quantification of SO 2 , CS 2 and H 2 S is important to determine the type and severity of internal faults in the insulating equipment. In this paper, a method combining symmetry dot pattern and deep learning is proposed for quantitative detection of multi-component gas mixtures on the ultraviolet absorption spectroscopy platform. The method is based on symmetry dot pattern analysis to fuse the local ultraviolet spectral information which is useful for identifying trace gas mixtures with overlapping absorption peaks. A deep network based on transfer learning is established to recognize the symmetry dot pattern diagrams, achieving feature representation from different scales. The outstanding performance of this method is demonstrated and compared to the existing models by receiver operating characteristic curve. Experimental results on the platform show that the proposed method can quantitatively detect the concentrations of SO 2 , H 2 S and CS 2 ternary gas mixture online. [ABSTRACT FROM AUTHOR]

The development of intelligent traffic coordination and smart mobility under the digital economy has increased the need for effective traffic sub-area division. The traditional division methods rely on predefined urban administrative units, failing to adapt to the varying traffic conditions. Therefore, data-driven approaches have been developed to divide traffic sub-areas, considering both the frequency of data updates and a balance between accuracy and traffic characteristics within the selected data. However, these approaches are affected by unsatisfactory zone boundaries, and the relevant clustering algorithms cannot efficiently support traffic sub-area division. To address these issues, this paper proposes a two-layer traffic sub-area division (TL-TSD) framework that considers factors such as traffic density, road structure, and spatiotemporal characteristics inherent in the overall trajectory. Specifically, in the first layer, we introduce a specific equation based on dynamic time warping to adaptively perform trajectory cutting and record matching information while maintaining the shape features of the overall trajectory. Subsequently, we design a modified density based spatial clustering of applications with noise algorithm to obtain initial clusters. In the second layer, based on the matching information, we introduce two trajectory refinement algorithms. Each is designed for final clusters and well-defined boundaries. Extensive experimental results and statistical analysis on two real-world datasets indicate that the proposed framework can effectively address the aforementioned technical challenges and outperform the comparison algorithms in terms of the overall dunn metric. Moreover, the visualization results show that the final clusters with well-defined boundaries are more effective for dividing traffic sub-areas. [ABSTRACT FROM AUTHOR]

Power transmission lines play very important roles in power systems. When a fault occurs, a fast process of identification, localization and isolation of the fault is required. To one of the most popular solutions for fault detection and localization belong the distance relays using the impedance based algorithms. This paper will present a new approach using the modified Takagi-Sugeno-Kang neuro-fuzzy network trained on the signals generated by hardware simulator to estimate the shortage fault locations and fault resistances. The solution will base only on the voltage and current signals measured at the beginning of the lines. To compare the simulation results with the real field relay, the simulated lines' signals are regenerated into a relay tester Omicron CMC-356 to test with a real Siemens 7SA522 relay. The numerical results will show that the proposed neuro-fuzzy network can offer very accurate estimation of fault resistances with the coefficient of determination equal 0.9986 and higher accuracy in fault location comparing with the real 7SA522 relay in both relative mean squared errors and maximum errors. [ABSTRACT FROM AUTHOR]

The current landscape of medical diagnostics grapples with a critical challenge posed by the limitations of existing meta-learning techniques in interpreting complex representations from limited labeled data, particularly evident in COVID-19 datasets. In response to this gap, our paper introduces a groundbreaking Turning Point (TP) methodology designed to enhance the interpretability of machine learning diagnostics, specifically addressing the shortcomings highlighted in conventional meta-learning approaches. Our Turning Point-based Few-Shot Learning (TPFSL) model goes beyond traditional FSL methods by embracing structured knowledge representation, departing from unstructured metric spaces. We found that our TPFSL model outperformed the state-of-the-art models by an average of 4.50% in 1-shot learning and 4.43% in 5-shot learning after conducting extensive benchmarking on the COVCT, SARSCOV2, and SIRM datasets. Across all datasets studied, TPFSL outperforms the ProtoNet benchmark in 1-shot classification by 12.966% and in 5-shot classification by 11.033%. The importance of TP density, the structure of the network, and placement in improving model performance have been shown by a thorough set of ablation investigations; with its revolutionary TPFSL model, which tackles the shortcomings of current meta-learning methods head-on, COVID-19 diagnostic procedures can be made more accurate and valid in clinical situations. [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]

The existing deep learning-based image dehazing algorithms commonly employ an encoder–decoder structure to learn a direct mapping from hazy images to haze-free images. However, these state-of-the-art methods often fail to consider the varying contents of hazy images across different scenes, resulting in unsatisfactory dehazing outcomes. To address this issue, this paper attempts to integrate a novel instance-aware subnet into the classic encoder–decoder structure in order to achieve a clear separation between figure and background, conducting the selective incorporation of instance features into the dehazing network. Specifically, we introduce a novel architecture called the hybrid residual attention network, which is capable of separately extracting full-image features and instance-level features. This architecture incorporates attention mechanisms and a multi-scale dilated convolution structure, enabling adaptive perception of haze density in different scenes. Additionally, we introduce a global feature fusion subnet that employs a pixel attention structure to fuse features from the entire image and multiple individual instances, thus being aware of instance features. Compared to existing methods, our approach offers a major advantage in accurately estimating the haze density of individual instances, reducing color distortion, and mitigating noise amplification in the output images. Experimental results demonstrate that our method outperforms existing methods across different evaluation metrics and testing benchmarks. Therefore, we believe that our method will serve as a valuable addition to the current collection of artificial intelligence models and will benefit engineering applications in video surveillance and high-level computer vision tasks. [ABSTRACT FROM AUTHOR]

Neural network is beneficial for obtaining weight, which is a crucial parameter for vehicle in operation. However, the high demand of neural network for real data, and the lack of in-depth research on multi-vehicle weight prediction scenarios, have limited the development of weight prediction. In this paper, relying on the genetic algorithm-optimized BP neural network (GA-BP neural network), a commercial vehicle weight prediction method based on driving simulation data was proposed. The driving data of multiple commercial vehicle types were collected and used to study the weight prediction effect of the proposed method in single-vehicle and multi-vehicle scenarios. The fuzzy processing method of driving simulation data was proposed to process simulation data instead of real data to train the model, which effectively solves the problem of high demand for real data in neural network method. The study shows that proposed method can achieve weight prediction deviation of 2.87% for single-vehicle model and 4.63% for multi-vehicle model. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (Re-ID) is a challenging task due to the complexity of the camera view and the variability introduced by pedestrian pose. The irrelevant samples in sample-based contrastive learning pose a potential risk of overfitting which reduces the ability to identify similar features. Therefore, the feature representation relies on the local feature to perceive global content and overfits negative samples. This paper proposes an innovative approach: Attention-Boosted Contrastive Learning (ABC-Learning), which increases region awareness and regularizes in-memory samples. In ABC-Learning, the adjacent content aware (ACA) module is designed to enhance regional feature recognition. It enables local regions of feature maps to re-balance their output by perceiving the informative features of neighboring regions. Additionally, cluster-oriented self-attention (COS) is proposed to regularize the influence of different clusters on the contrastive learning process. The structure of COS reduces the influence of irrelevant clusters through memory data distribution. Finally, a new distance-weighted (DW) memory updating strategy is deployed to keep memory and encoder coherent. DW ensures updating consistency and knowledge transfer through relative distance detection. Our results evaluated on person Re-ID benchmarks demonstrate the promising ability of ABC-Learning to capture the regional feature information and sample weights adjustment. [ABSTRACT FROM AUTHOR]

The Active Disturbance Rejection Control (ADRC) has been employed in many industrial applications in recent year. One of the key issues when applying ADRC to industrial process control is determining controller parameters. This paper presents a new robust optimal tuning rule for first order reduced ADRC for the industrial processes which can be approximated to First Order Plus Dead Time (FOPDT) model. The tuning rule is derived to achieve a good control performance and robustness of the closed loop system by minimizing the Integrated Absolute Error (IAE) or Integrated Time-weighted Absolute Error (ITAE) under robustness constraints. It is formulated as an optimization problem with the strong nonlinear inequality constraints such as stability margin and maximum sensitivity function constraint. It is difficult to solve these optimization problems analytically. From this, the optimization problem is effectively solved by using the Particle Swarm Optimization - Differential Evolution (PSO-DE) hybrid intelligence algorithm, which is one of the swarm intelligent optimization techniques. The validity of the proposed tuning rule is verified via simulations for the benchmark processes and the temperature control for yeast culture process. [ABSTRACT FROM AUTHOR]

Automatic classification methods widely used for diagnosing and analyzing COVID-19 cases. These methods assume known labels and rely on a single view of the dataset. Given the prevalence of COVID-19 cases and the extensive volume of patient records lacking labels, this communication underscores our unique approach—conducting the first study on COVID-19 case diagnosis in an unsupervised manner. Our work operates under the assumption of prior knowledge regarding the number of classes, such as COVID-19, pneumonia, and normal, in a case study. By adopting an unsupervised learning paradigm, we leverage the wealth of unlabeled data, reducing dependence on human experts for annotating numerous images. This paper introduces an enhanced version of a recent direct method where non-negative cluster indices and spectral embeddings are jointly estimated. Beyond the inherent advantages of this method, our proposed model introduces improvements through two additional types of constraints: (i) ensuring consistent smoothing of cluster labels across all views and (ii) imposing an orthogonality constraint on the matrix of cluster assignments. The efficacy of the proposed method is demonstrated using the public COVIDx dataset with three classes, showcasing promising results in categorizing radiographs. The proposed approach is tested on other public image datasets to assess its effectiveness. [ABSTRACT FROM AUTHOR]

Determining the mining sequence is one of the main objectives in mine planning. However, depending on the size of the analyzed instances, such activity might become an extremely difficult task, despite current computational capacity. In addition, determining a feasible and operational mining sequence is also challenging, so practitioners usually employ strategies to segment and simplify the main problem, such as splitting it into distinct time horizons and aggregating blocks into clusters. This paper aims to perform a critical review about the different clustering methodologies and algorithms used for mining-block aggregation, with the purpose of understanding the proposed solutions and identifying the gaps found in the current literature. The reviewed aggregation strategies encompass the modelling of tabular deposits as sets of layers and grouping of blocks in benches, bench-phases, and mining cuts. Among the optimization techniques evaluated, one may find heuristics, artificial intelligence, and exact approaches, relying on deterministic or uncertainty-based methodologies, considering approximately six decades of studies and covering fifty-eight works published in journals and proceedings from 1967 to 2022. In addition to what is seen within the literature analyzed, we also propose future research directions, such as approaches and algorithms not yet implemented to solve the block aggregation problem, thus presenting opportunities for further research in this field. [ABSTRACT FROM AUTHOR]

Failure modes and effects analysis is a proactive reliability-management engineering technique, it has been applied to improve reliability of processes, products, and services. Traditional failure modes and effects analysis method manifests three deficiencies with regard to form of risk assessments, determination of risk factor weights, and exploitation of failure modes' risk levels. Although numerous studies have contributed to surmount these deficiencies, existing failure modes and effects analysis methods still face such issues. Moreover, a novel drawback has raised when failure modes and effects analysis participants adopt linguistic terms as risk assessments of failure modes, the reliability of linguistic distribution assessments as well as failure modes and effects analysis groups (participants with similar knowledge background are previously classified into a failure modes and effects analysis group) is overlooked. Therefore, this paper introduces the transformation of linguistic distribution assessments into fuzzy preference relations, as more effective modeling for investigating consistency, by using the newly defined possibility degrees of linguistic distribution assessments will be applied to devise four algorithms for enhancing reliability of assessments. Hence, the three deficiencies of traditional failure modes and effects analysis method are solved by means of a novel failure modes and effects analysis framework. Finally, a real example with respect to ranking failure modes of worm wheel grinding machine is developed to verify the performance and advantages of the proposed method, in which ten failure modes are ranked and the one with the highest risk level is selected, and consistency of risk assessments is improved to be acceptable. • Possibility preference relations are built for FMEA risk assessments. • Four consistency improving algorithms are devised for reliability. • Two weighting determination models are built for risk factors and FMEA groups. • A FMEA model is developed to enhance reliability and handle existing issues. [ABSTRACT FROM AUTHOR]

In previous studies, based on picture fuzzy sets, full implication algorithm and quintuple implication principle have been studied. The problem is, full implication algorithm did not consider the relationship between the input and antecedent of rule, while quintuple implication principle only considered the inclusion relationship between the rule's antecedent and input. Both algorithms did not consider the similarity of rule's antecedent and input. This leads to unreasonable calculation results in some cases. Therefore, we study fuzzy reasoning methods based on picture similarity measure for generalized modus ponens and generalized modus tollens in this paper. First of all, based on picture biresiduation, a new picture similarity measure between picture fuzzy sets is constructed. Then, representations of solutions of fuzzy reasoning methods based on picture similarity measure are given. Moreover, reducibility and robustness of fuzzy reasoning methods based on picture similarity measure are studied. Finally, two issues related to medical diagnosis are addressed by the proposed methods, demonstrate the rationality and effectiveness of our suggested methods. [ABSTRACT FROM AUTHOR]

To decrease the impact of ambiguity, fuzzy sets are frequently used to decide if an element belongs to a set. Various fuzzy set extensions differ from others in how uncertainty is expressed in the definition of membership functions. This paper presents a novel extension named Fermatean fuzzy Z-numbers, introducing fuzzy restriction and fuzzy reliability functions with Fermatean fuzzy membership functions. By utilizing fuzzy Z-numbers to delineate membership degrees, considering both restriction and its reliability, in tandem with Fermatean membership functions offering an expanded value spectrum, the assessment of linguistic evaluations using Fermatean fuzzy Z-numbers can yield more pragmatic outcomes in decision evaluations amidst high uncertainty. Moreover, the interval-valued Fermatean fuzzy-Z-analytic hierarchy process is developed to explore the impact of proposed interval-valued Fermatean fuzzy-Z numbers on the multi-criteria decision-making process, demonstrated in the context of third-party logistics provider selection. Adding fuzzy reliability functions to the decision-making process improves how uncertainty is represented by considering variations in confidence levels associated with each decision, thus aiding in the clearer expression of decisions. Additionally, the proposed method's outcomes are compared with the outcomes of the current approaches. [ABSTRACT FROM AUTHOR]

Pedestrian trajectory prediction in dynamic and strongly interactive scenes has become one of the most challenging problems in fields such as automated driving. In this paper, we propose Goal-CurveNet, a multimodal trajectory prediction network combining heterogeneous graph attention goal prediction and curve fitting. The model addresses the problems of pedestrian interaction modeling, multimodal trajectory prediction, and performance of predicted trajectories in pedestrian trajectory prediction. Goal-CurveNet can better model the historical trajectories and interaction behaviors in the scene systematically based on heterogeneous graph attention. It predicts the complete trajectories by curve fitting, which effectively improves the quality of predicted trajectories. The model architecture of "goal first and then trajectory" and targeted training paradigm also enhance the final performance. Through detailed training and testing on ETH & UCY datasets, we validate the effectiveness of each contribution of Goal-CurveNet. Compared to many state-of-the-art models, Goal-CurveNet achieves performance improvements in key metrics and effective prediction of pedestrian trajectories. [ABSTRACT FROM AUTHOR]

Accurate stock movement prediction is essential to profit from the stock market. However, this task is challenging due to the complexity and non-stationary nature of the market. Deep learning methods have obtained more attention and success in mining price movement patterns.However, some limitations affect their performances. In general, the stock market is ever-changing, and many factors affect stock movement, so capturing the stock movement patterns is hard without enough prior information. To tackle it, we consider employing economic facts to help improve the deep learning method. In this paper, we propose a novel Hierarchical Deep learning Model that fuses Economic Facts (HDMEF) to predict stock movement from the micro to the macro tiers: the individual, industry, and whole market tiers. Specifically, we present three well-designed modules to separately model them based on the Capital Asset Pricing Model (CAPM), the herding effects, and the holiday effects in the stock market. Experiments on the A-share CSI300 and CSI500 indexes demonstrate that our proposed method performs best on all test phases compared with previous competitive baselines, even an absolute improvement of 2%–3% on some test phases where all the baselines act poor, proving our method is more efficient and robust in different market conditions. In addition, we do an ablation study to analyze the role of various economic effects used in our model, and the results prove that each module is helpful for prediction. [ABSTRACT FROM AUTHOR]

Sustainable development has become a worldwide consensus in recent years. It has become increasingly important to study how to make effective management decisions in rural areas to achieve sustainable development. In this paper, we develop a new approach to strategic responses for sustainable rural development by using case-based reasoning (CBR), the bi-direction Choquet integral (BDCI), and the Shapley index (SI). First, to deal with the complexity of sustainable rural development, we develop an ontology-based sustainable rural development domain model. Second, we propose a case retrieval algorithm based on BDCI to improve the case retrieval method used in CBR to solve the problem of the relationship between the features. Third, we propose a case reuse method that is inspired by SI, in which each solution is evaluated relative to its value, and the implementation step for the response strategy is determined based on its priority. The proposed strategy response method for sustainable rural development is demonstrated through a case study and its effectiveness is demonstrated empirically. • A CBR-based approach for sustainable rural development strategy response is innovatively developed. • Using ontology method to build a sustainable rural development domain model. • A BDCI-based case retrieval algorithm is proposed to solve the relationship between attributes. • A Shapley-based case reuse method is proposed to provide order for solutions. [ABSTRACT FROM AUTHOR]

An energy functional describes the equilibrium state of a system. In this work, we present a novel technique, Functional Optimization using Neural Networks (FONN), for minimizing the system's energy. FONN utilizes neural networks to process information at discrete grid points, considering their interactions with neighboring grid points, to update the state of the system. The training process involves formulating a loss function based on the system's energy, and with the help of multiple fine-tuning steps, the method employs a progressive energy reduction technique that decreases the energy in multiple steps. FONN's effectiveness is demonstrated across various problems, including the minimization of the heat and Lyapunov energy. Moreover, the paper explores the minimization of the elastic bending energy with an area constraint. [ABSTRACT FROM AUTHOR]

Accurate positioning of curtain wall frames is crucial for the automated installation of curtain wall modules. However, the current robot-based installation methods overly depend on visual guidance from operators, resulting in high costs and limiting construction efficiency. The development of deep learning has introduced an image segmentation approach that offers a new solution for the visual positioning of curtain wall frames. This paper proposes a context collaboration pyramid network to automatically segment curtain wall frames by incorporating context interaction and channel guided pyramid structure. The model adopts an "encoder-decoder" architecture with a feature interaction block strategically inserted between the encoder and decoder. Specifically, the encoder utilizes the pyramid pooling Transformer as a backbone to extract multi-level features from original RGB images. The decoder employs a channel guided pyramid convolution module to integrate multi-scale features and achieve finer prediction. Meanwhile, a context interaction fusion module between the features of adjacent levels was designed carefully to enhance the collaboration of the architecture. In addition, a benchmark dataset for the curtain wall frame segmentation task, consisting of 1547 images, was established. The dataset incorporates challenging scenarios, including strong lights, low contrast, and cluttered backgrounds. This method is evaluated on the collected dataset, and achieves an impressive accuracy of 97.30% and an F1-Score of 88.95%, outperforming other segmentation networks. Overall, the proposed method can extract target information accurately and efficiently and provide critical visual guidance for the robot, so as to promote the automatic installation level of the curtain wall module. [ABSTRACT FROM AUTHOR]

In the field of prognostics and health management (PHM) for industrial equipment and systems, the estimation of remaining useful life (RUL) constitutes a fundamental task. A reliable and accurate method for estimating the RUL is therefore essential. This paper proposes a dynamic self-adaptive ensemble model, aimed at improving the rolling bearing RUL prediction. This model integrates an adaptive multi-scale feature extractor, a gated convolutional unit (GCU) and temporal convolutional networks (TCN). Through a redesign of the data flow, this model directly incorporates multi-scale comprehensive feature evaluation indicators into the neural network data flow, significantly enhancing the model's feature extraction capabilities. Subsequently, the study extends the traditional TCN by incorporating the GCU module and its gating mechanisms, further strengthening the model's capacity to capture long-term dependencies in sequence tasks. Experimental results demonstrate that, compared to existing state-of-the-art (SOTA) models, our method achieves at least a 10% increase in the prediction accuracy on two public run-to-failure bearing datasets. Beyond the tested datasets, the architecture that directly maps multi-scale evaluation indicators into the structure of neural network data flows also holds potential for broader application across diverse PHM tasks, promising significant improvements in the industrial safety and efficiency. • Multi-scale evaluation module for original features. • Direct mapping from multiple evaluation metrics to feature weights. • The feature selection process is incorporated into the RUL estimation model. • Better ability to capture inherent long-term and localized dependencies. [ABSTRACT FROM AUTHOR]

The field of predictive process monitoring focuses on case-level models to predict a single specific outcome such as a particular objective, (remaining) time, or next activity/remaining sequence. Recently, a longer-horizon, model-wide approach has been proposed in the form of process model forecasting, which predicts the future state of a whole process model through the forecasting of all activity-to-activity relations at once using time series forecasting. This paper introduces the concept of predictive process model monitoring which sits in the middle of both predictive process monitoring and process model forecasting. Concretely, by modelling a process model as a set of constraints being present between activities over time, we can capture more detailed information between activities compared to process model forecasting, while being compatible with typical predictive process monitoring objectives which are often expressed in the same language as these constraints. To achieve this, Processes-As-Movies (PAM) is introduced, i.e., a novel technique capable of jointly mining and predicting declarative process constraints between activities in various windows of a process' execution. PAM predicts what declarative rules hold for a trace (objective-based), which also supports the prediction of all constraints together as a process model (model-based). Various recurrent neural network topologies inspired by video analysis tailored to temporal high-dimensional input are used to model the process model evolution with windows as time steps, including encoder–decoder long short-term memory networks, and convolutional long short-term memory networks. Results obtained over real-life event logs show that these topologies are effective in terms of predictive accuracy and precision. [ABSTRACT FROM AUTHOR]

This paper introduces an improved differential evolution algorithm based on cooperative multi-population (CMp-DE for short), which combines diverse population collaboration mechanisms and catalytic factors into an improved differential evolution framework. By harnessing various population collaboration mechanisms, the algorithm enhances the diversity of individuals within populations during initial iterations and reduces it during later iterations, thereby harmonizing the algorithm's exploratory and exploitative capabilities. Furthermore, a novel mutation operator is proposed that divides the iterative process into exploration and exploitation phases, thereby augmenting the algorithm's global exploration prowess. Lastly, a catalytic operator is introduced to generate new individuals near post-crossover individuals based on a specified rule, which enhances the algorithm's ability to escape local optima and increasing stability. The proposed CMp-DE is benchmarked against the CEC2017 benchmark test functions and compared against 13 algorithms, including five differential evolution algorithms and their variants, as well as eight state-of-the-art metaheuristic optimization algorithms. This evaluation assesses the CMp-DE's solution accuracy, convergence, stability, and scalability. Finally, the applicability of CMp-DE is validated by addressing six practical optimization problems. The experimental results show that CMp-DE surpasses other algorithms in terms of both convergence accuracy and robustness. Moreover, integrating a catalytic operator with other optimization algorithms notably boosts performance in convergence accuracy and stability. The inclusion of the catalytic operator has significantly enhanced the performance of algorithms compared to their performance before its addition. This underscores the potential of the catalytic operator in improving the performance of various algorithms, particularly in terms of convergence accuracy and robustness. [ABSTRACT FROM AUTHOR]

The harmful utilization of DeepFake technology poses a significant threat to public welfare, precipitating a crisis in public opinion. Existing detection methodologies, predominantly relying on convolutional neural networks and deep learning paradigms, focus on achieving high in-domain recognition accuracy amidst many forgery techniques. However, overseeing the intricate interplay between textures and artifacts results in compromised performance across diverse forgery scenarios. This paper introduces a groundbreaking framework, denoted as Texture and Artifact Detector (TAD), to mitigate the challenge posed by the limited generalization ability stemming from the mutual neglect of textures and artifacts. Specifically, our approach delves into the similarities among disparate forged datasets, discerning synthetic content based on the consistency of textures and the presence of artifacts. Furthermore, we use a model ensemble learning strategy to judiciously aggregate texture disparities and artifact patterns inherent in various forgery types, thereby enabling the model's generalization ability. Our comprehensive experimental analysis, encompassing extensive intra-dataset and cross-dataset validations along with evaluations on both video sequences and individual frames, confirms the effectiveness of TAD. The results from four benchmark datasets highlight the significant impact of the synergistic consideration of texture and artifact information, leading to a marked improvement in detection capabilities. • We build an artifact and texture inconsistency detector for deepfake detection. • Texture coherence is analyzed via a novel mask extraction method and an autoencoder. • The use of an ensemble training strategy improved the ability to generalize. • Extensive experiments verified the effectiveness of the model we built. [ABSTRACT FROM AUTHOR]

Dempster-Shafer theory (DST) and multi-criteria decision-making are widely applied mathematical tools in decision-making, though DST has some limitations in evidence fusion rule. The issues in evidence fusion are addressed through the development of combination rules, pre-processing of evidence, and generalization of evidence into interval-valued or intuitionistic belief degree. In this paper, a more flexible belief degree called the q-rung evidence set is introduced to solve the issues of standard belief degrees. Moreover, fusion of group decision-maker's belief degrees using a single fusion rule is a possible case of conflict among them. In this regard, we have employed the convex combination of two rules with different weights to generate a consensus among the decision-makers. A new aggregation method is devised to integrate the assessment of decision-maker based on the q-rung evidence set, convex combination rule, and a new score function. We have used a hypothetical case study in multi-criteria group decision-making problem for solving the patient's treatment preference problem in medical diagnosis to validate the proposed technique. The suggested technique successfully ranks the four alternatives with the comparison to the former aggregation method. [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]

In this paper, a global probability distribution structure-sparsity filter pruning is proposed to address the problem of difficult deployment of diagnostic models in resource constrained wireless sensor networks (WSNs) for edge fault diagnosis. Firstly, local and global weight distributions are analyzed. A global probability distribution weight sparsity method is proposed to obtain the global sparse boundary and the important features of the model. Secondly, according to the distribution of weight amplitude, the problem of uneven weight distribution is disclosed. A computational acceleration sensing method is proposed to reduce the high computational cost caused by small weight amplitude with low importance estimation. Moreover, a novel layer filter clustering pruning scheme is proposed. The intra-layer filters are classified and redundant filters are removed by using the clustering idea according to the predetermined pruning rate. Thus, the structure-sparsity filter pruning is realized. Compared with other advanced filter pruning methods, the proposed method analyzes the global and local model weight distribution and the influence of weight importance on the computational complexity of the model. The proposed method then performs filter pruning on the importance of overall filters for each network layer rather than individual filters. The accuracy of the proposed method on experimental dataset for pruned ResNet8 model under pruning rate at 0.95 is 99.12% with 3.668K parameters and 3.636MFLOPs. The experimental results elucidate that the proposed method is more suitable for deployment in resource-constrained WSNs for fault diagnosis of rotating machinery. This provides a potential solution for practical engineering applications. • A global probability distribution weight sparsity is proposed. Sparse boundary is derived to identify unimportant weights. • The computational acceleration sensing is proposed to tackle that low-importance estimates consume unnecessary computations. • A novel layer filter clustering pruning is proposed to remove redundant filters and retain the overall important feature. • The results show that compared with other methods, the proposed method obtains tradeoff in accuracy, parameters and FLOPs. [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]

Automatic and accurate medical image segmentation is a crucial step for clinical diagnosis and treatment planning of diseases. The advanced convolutional neural network (CNN) approaches based on the encoder–decoder structure have achieved state-of-the-art performances in many different medical image segmentation tasks. However, existing networks have insufficient capability of extracting the context information in each encoding stage, so they cannot effectively perceive multi-scale objects in images. In addition, the continuous down-sampling and convolution operations in the encoding stage lead to much loss of the detailed information, resulting in poor segmentation performance. In this paper, we propose a Multi-path Multi-scale Context Feature MixUp and Aggregation Network (named MpMsCFMA-Net) which fuses and aggregates multi-path features with multi-scale context information to address these issues. Based on the encoder–decoder structure, we first design the encoder to encode the semantic and detailed information of input images and introduce multi-scale context extraction module in each encoding stage. Furthermore, we design multiple features mixup module between the encoder and the decoder, aiming at providing different levels of global context information for the decoder by reconstructing skip-connection. Finally, we introduce the decoder with deeper features aggregation to better fuse multi-scale context information across layers. Experimental results on four public medical image datasets confirm that our proposed network achieves promising results and outperforms other state-of-the-art methods in most of evaluation metrics. The source code will be publicly available at https://github.com/tricksterANDthug/MpMsCFMA-Net. [ABSTRACT FROM AUTHOR]

In this paper, we propose an effective composite descriptor combining contour and appearance features for plant species identification. The composite descriptor uses two different fusion schemes: the first is a method based on the fusion of low-level local contour and appearance features; that is, we use local triangle features and local speeded-up robust features (SURF) to describe leaf images, respectively. Then, we utilize the Hausdorff distance to measure the leaf discrepancy to complete the plant identification task. The second is a method of global feature fusion based on high-level shape and appearance features. Specifically, the Fisher vector encodes the local triangle, and SURF features into high-level shape and appearance features. Then, the Euclidean distance is used to compute the dissimilarity of leaves to realize plant leaf recognition. The composite descriptor based on these two fusion schemes can well describe the characteristics of leaf images and improve the ability to identify plant leaves. This composite descriptor is extensively tested on several standard plant databases, including simple, compound, and natural scene plant leaf datasets. Experimental results demonstrate that the composite descriptor achieves high recognition accuracy, outperforming existing state-of-the-art benchmarks. In addition, we further applied our method directly to shape recognition and achieved good recognition results, demonstrating the wide range of applications of our method. • We present an effective contour representation named local triangle feature. • We propose two fusion schemes to effectively combine the contour and appearance characteristics for plant identification. • The experimental results show that our method outperforms the state-of-the-art plant identification approaches. [ABSTRACT FROM AUTHOR]

Semantic segmentation is a well-studied topic and one of the most challenging tasks in computer vision applications, such as autonomous driving. Deep learning approaches based on convolutional neural networks (CNN) have demonstrated exceptional success on this task in recent years. Despite this success, existing approaches are plagued by higher-order inconsistencies between the ground truth images and the ones predicted by the segmentation model. This paper proposes a novel post-processing scheme based on adversarial learning to counter these inconsistencies. Such a scheme can be combined with a variety of existing CNN-based semantic segmentation networks to improve their segmentation performances. The proposed scheme is a Two-Stream Conditional Generative Adversarial Network (TScGAN), with one stream having initial semantic segmentation masks predicted by an existing CNN, while the other stream utilizes scene images to retain high-level information under a supervised residual network structure. In addition, TScGAN incorporates a novel dynamic weighting mechanism, which leads to significant and consistent gains in segmentation performance. Several comparative tests on public benchmark driving databases, including Cityscapes, Mapillary, and Berkeley DeepDrive100K, demonstrate the effectiveness of the proposed method when used with state-of-the-art CNN-based semantic segmentation models. Furthermore, the ablation experiment proved the structural rationality of our two-stream structure. The code for TScGAN could be found at https://github.com/epan-utbm/TScGAN-for-Improving-Semantic-Predictions • Explores various post-processing techniques for enhancing semantic segmentation. • Novel Two-Stream Conditional GAN enhances urban drive scene segmentation. • Enhances feature extraction by implementing dynamic weighting within streams. • Evaluates the model against existing semantic segmentation methodologies. • Tests on Cityscapes, Mapillary, BDD100K reveal major IoU gains with proposed model. [ABSTRACT FROM AUTHOR]