Search Results (1,498)

Computer vision-based gait recognition (CVGR) is a technology that has gained considerable attention in recent years due to its non-invasive, unobtrusive, and difficult-to-conceal nature. Beyond its applications in biometrics, CVGR holds significant potential for healthcare and human–computer interaction. Current CVGR systems often transmit collected data to a cloud server for machine learning-based gait pattern recognition. While effective, this cloud-centric approach can result in increased system response times. Alternatively, the emerging paradigm of edge computing, which involves moving computational processes to local devices, offers the potential to reduce latency, enable real-time surveillance, and eliminate reliance on internet connectivity. Furthermore, recent advancements in low-cost, compact microcomputers capable of handling complex inference tasks (e.g., Jetson Nano Orin, Jetson Xavier NX, and Khadas VIM4) have created exciting opportunities for deploying CVGR systems at the edge. This paper reports the state of the art in gait data acquisition modalities, feature representations, models, and architectures for CVGR systems suitable for edge computing. Additionally, this paper addresses the general limitations and highlights new avenues for future research in the promising intersection of CVGR and edge computing. Full article

Cloud–edge–end computing architecture is crucial for large-scale edge data processing and analysis. However, the diversity of terminal nodes and task complexity in this architecture often result in non-independent and identically distributed (non-IID) data, making it challenging to balance data heterogeneity and privacy protection. To address this, we propose a privacy-preserving federated learning method based on cloud–edge–end collaboration. Our method fully considers the three-tier architecture of cloud–edge–end systems and the non-IID nature of terminal node data. It enhances model accuracy while protecting the privacy of terminal node data. The proposed method groups terminal nodes based on the similarity of their data distributions and constructs edge subnetworks for training in collaboration with edge nodes, thereby mitigating the negative impact of non-IID data. Furthermore, we enhance WGAN-GP with attention mechanism to generate balanced synthetic data while preserving key patterns from original datasets, reducing the adverse effects of non-IID data on global model accuracy while preserving data privacy. In addition, we introduce data resampling and loss function weighting strategies to mitigate model bias caused by imbalanced data distribution. Experimental results on real-world datasets demonstrate that our proposed method significantly outperforms existing approaches in terms of model accuracy, F1-score, and other metrics. Full article

Triboelectric nanogenerators (TENGs) have garnered significant attention due to their high energy conversion efficiency and extensive application potential in energy harvesting and self-powered devices. Recent advancements in electrospun nanofibers, attributed to their outstanding mechanical properties and tailored surface characteristics, have meant that they can be used as a critical material for enhancing TENGs performance. This review provides a comprehensive overview of the developments in electrospun nanofiber-based TENGs. It begins with an exploration of the fundamental principles behind electrospinning and triboelectricity, followed by a detailed examination of the application and performance of various polymer materials, including poly (vinylidene fluoride) (PVDF), polyamide (PA), thermoplastic polyurethane (TPU), polyacrylonitrile (PAN), and other significant polymers. Furthermore, this review analyzes the influence of diverse structural designs—such as fiber architectures, bionic configurations, and multilayer structures—on the performance of TENGs. Applications across self-powered devices, environmental energy harvesting, and wearable technologies are discussed. The review concludes by highlighting current challenges and outlining future research directions, offering valuable insights for researchers and engineers in the field. Full article

Paralleled buck converters have garnered significant attention for fulfilling the increasing demands of power supplies in modern applications. They have the advantages of increased current capacity and reduced current ripple. Under this architecture, applying distributed control brings the benefits of reliability and scalability. However, the interconnecting lines between the converters are required for achieving the interleaving operation, which reduces the reliability and scalability. To eliminate the interconnecting lines, this paper proposed a hysteresis current controller to achieve the symmetric interleaving operation. First, the parallel structure with a common output filter was proposed to provide the hardware basis for the proposed control method. Then, the hysteresis current controller was constructed based on the inductor voltage of each buck module to achieve the interleaving operation. The experiment of the three-module-paralleled buck converter was conducted. The experimental results show that the symmetric interleaving was achieved with a maximum phase shift error of 4.1%; the output of the parallel system can recover within 2.60 ms after the load transitions from 50% to 100%; and the parallel system can recover within 1.96 ms after one module removal. The simulation results of the six-module-paralleled buck converter show that the parallel system can recover within 1.00 ms after one module addition, which illustrates the scalability of the proposed method. Full article

Detecting anomalies in distributed systems through log analysis remains challenging due to the complex temporal dependencies between log events, the diverse manifestation of system states, and the intricate causal relationships across distributed components. This paper introduces a TLAN (Temporal Logical Attention Network), a novel deep learning framework that integrates temporal sequence modeling with logical dependency analysis for robust anomaly detection in distributed system logs. Our approach makes three key contributions: (1) a temporal logical attention mechanism that explicitly models both time-series patterns and logical dependencies between log events across distributed components, (2) a multi-scale feature extraction module that captures system behaviors at different temporal granularities while preserving causal relationships, and (3) an adaptive threshold strategy that dynamically adjusts detection sensitivity based on system load and component interactions. Extensive experiments on a large-scale synthetic distributed system log dataset show that TLAN outperforms existing methods by achieving a 9.4% improvement in F1-score and reducing false alarms by 15.3% while maintaining low latency in real-time detection. The framework demonstrates particular effectiveness in identifying complex anomalies that involve multiple interacting components and cascading failures. Through comprehensive empirical analysis and case studies, we validate that TLAN can effectively capture both temporal patterns and logical correlations in log sequences, making it especially suitable for modern distributed architectures. Our approach also shows strong generalization capability across different system scales and deployment scenarios, supported by thorough ablation studies and performance evaluations. Full article

The impact of artificial intelligence (AI) on English language learning has become the center of attention in the past few decades. This study, with its potential to transform English language instruction and offer various instructional approaches, provides valuable insights and knowledge. To fully grasp the potential advantages of AI, more research is needed to improve, validate, and test AI algorithms and architectures. Grammatical notations provide a word’s information to the readers. If a word’s images are properly extracted and categorized using a CNN, it can help non-native English speakers improve their learning habits. The classification of parts of speech into different grammatical notations is the major problem that non-native English learners face. This situation stresses the need to develop a computer-based system using a machine learning algorithm to classify words into proper grammatical notations. A convolutional neural network (CNN) was applied to classify English words into nine classes: noun, pronoun, adjective, determiner, verb, adverb, preposition, conjunction, and interjection. A simulation of the selected model was performed in MATLAB. The model achieved an overall accuracy of 97.22%. The CNN showed 100% accuracy for pronouns, determiners, verbs, adverbs, and prepositions; 95% for nouns, adjectives, and conjunctions; and 90% for interjections. The significant results (p < 0.0001) of the chi-square test supported the use of the CNN by non-native English learners. The proposed approach is an important source of word classification for non-native English learners by putting the word image into the model. This not only helps beginners in English learning but also helps in setting standards for evaluating documents. Full article

To satisfy the obstacle avoidance requirements of unmanned agricultural machinery during autonomous operation and address the challenge of rapid obstacle detection in complex field environments, an improved field obstacle detection model based on YOLOv8 was proposed. This model enabled the fast detection and recognition of obstacles such as people, tractors, and electric power pylons in the field. This detection model was built upon the YOLOv8 architecture with three main improvements. First, to adapt to different tasks and complex environments in the field, improve the sensitivity of the detector to various target sizes and positions, and enhance detection accuracy, the CBAM (Convolutional Block Attention Module) was integrated into the backbone layer of the benchmark model. Secondly, a BiFPN (Bi-directional Feature Pyramid Network) architecture took the place of the original PANet to enhance the fusion of features across multiple scales, thereby increasing the model’s capacity to distinguish between the background and obstacles. Third, WIoU v3 (Wise Intersection over Union v3) optimized the target boundary loss function, assigning greater focus to medium-quality anchor boxes and enhancing the detector’s overall performance. A dataset comprising 5963 images of people, electric power pylons, telegraph poles, tractors, and harvesters in a farmland environment was constructed. The training set comprised 4771 images, while the validation and test sets each consisted of 596 images. The results from the experiments indicated that the enhanced model attained precision, recall, and average precision scores of 85.5%, 75.1%, and 82.5%, respectively, on the custom dataset. This reflected increases of 1.3, 1.2, and 1.9 percentage points when compared to the baseline YOLOv8 model. Furthermore, the model reached 52 detection frames per second, thereby significantly enhancing the detection performance for common obstacles in the field. The model enhanced by the previously mentioned techniques guarantees a high level of detection accuracy while meeting the criteria for real-time obstacle identification in unmanned agricultural equipment during fieldwork. Full article

The Internet of Things (IoT) is gaining increasing attention in healthcare due to its potential to enable continuous monitoring of patients, both at home and in controlled medical environments. In this paper, we explore the integration of IoT with human-robotics in the context of motor rehabilitation for groups of patients performing moderate physical routines, focused on balance, stretching, and posture. Specifically, we propose the I-TROPHYTS framework, which introduces a step-change in motor rehabilitation by advancing towards more sustainable medical services and personalized diagnostics. Our framework leverages wearable sensors to monitor patients’ vital signs and edge computing to detect and estimate motor routines. In addition, it incorporates a humanoid robot that mimics the actions of a physiotherapist, adapting motor routines in real-time based on the patient’s condition. All data from physiotherapy sessions are modeled using an ontology, enabling automatic reasoning and planning of robot actions. In this paper, we present the architecture of the proposed framework, which spans four layers, and discuss its enabling components. Furthermore, we detail the current deployment of the IoT system for patient monitoring and automatic identification of motor routines via Machine Learning techniques. Our experimental results, collected from a group of volunteers performing balance and stretching exercises, demonstrate that we can achieve nearly 100% accuracy in distinguishing between shoulder abduction and shoulder flexion, using Inertial Measurement Unit data from wearable IoT devices placed on the wrist and elbow of the test subjects. Full article

In the current competition process of e-commerce platforms, the technical and algorithmic wars that can quickly grasp user needs and accurately recommend target commodities are the core tools of platform competition. At the same time, the existing online purchase behavior prediction models lack consideration of time series features. This paper combines the Recurrent Neural Network, which is more suitable for the commodity recommendation scenario of the e-commerce platform, with Naive Bayes, which is simple in logic and efficient in operation and constructs the online purchase behavior prediction model RNN-NB, which can consider the features of time series. The RNN-NB model is trained and tested using 3 million time series data with purchase behavior provided by the Ali Tianchi big data platform. The prediction effect of the RNN-NB model and Naive Bayes model is evaluated and compared respectively under the same experimental conditions. The results show that the overall prediction effect of the RNN-NB model is better and more stable. In addition, through the analysis of user time series features, it can be found that the possibility of user purchase is negatively correlated with the length of time series, and merchants should pay more attention to those users with shorter time series in commodity recommendation and targeted offers. The contributions of this paper are as follows: (1) By constructing an online purchasing behavior model RNN-NB, which integrates the N vs 1 structure Recurrent Neural Network and naive Bayesian model, the validity limitations of some single-architecture recommendation algorithms are solved. (2) Based on the existing naive Bayesian model, the prediction accuracy of online purchasing behavior is further improved. (3) The analysis based on the features of the time series provides new ideas for the research of later scholars and new guidance for the marketing of platform merchants. Full article

Over the last few years, neural architecture search (NAS) technology has achieved good results in hyperspectral image classification. Nevertheless, existing NAS-based classification methods have not specifically focused on the complex connection between spectral and spatial data. Strengthening the integration of spatial and spectral features is crucial to boosting the overall classification efficacy of hyperspectral images. In this paper, a triple-unit hyperspectral NAS network (TUH-NAS) aimed at hyperspectral image classification is introduced, where the fusion unit emphasizes the enhancement of the intrinsic relationship between spatial and spectral information. We designed a new hyperspectral image attention mechanism module to increase the focus on critical regions and enhance sensitivity to priority areas. We also adopted a composite loss function to enhance the model’s focus on hard-to-classify samples. Experimental evaluations on three publicly accessible hyperspectral datasets demonstrated that, despite utilizing a limited number of samples, TUH-NAS outperforms existing NAS classification methods in recognizing object boundaries. Full article

Background/Objectives: Chest disease identification for Tuberculosis and Pneumonia diseases presents diagnostic challenges due to overlapping radiographic features and the limited availability of expert radiologists, especially in developing countries. The present study aims to address these challenges by developing a Computer-Aided Diagnosis (CAD) system to provide consistent and objective analyses of chest X-ray images, thereby reducing potential human error. By leveraging the complementary strengths of convolutional neural networks (CNNs) and vision transformers (ViTs), we propose a hybrid model for the accurate detection of Tuberculosis and for distinguishing between Tuberculosis and Pneumonia. Methods: We designed a two-step hybrid model that integrates the ResNet-50 CNN with the ViT-b16 architecture. It uses the transfer learning on datasets from Guangzhou Women’s and Children’s Medical Center for Pneumonia cases and datasets from Qatar and Dhaka (Bangladesh) universities for Tuberculosis cases. CNNs capture hierarchical structures in images, while ViTs, with their self-attention mechanisms, excel at identifying relationships between features. Combining these approaches enhances the model’s performance on binary and multi-class classification tasks. Results: Our hybrid CNN-ViT model achieved a binary classification accuracy of 98.97% for Tuberculosis detection. For multi-class classification, distinguishing between Tuberculosis, viral Pneumonia, and bacterial Pneumonia, the model achieved an accuracy of 96.18%. These results underscore the model’s potential in improving diagnostic accuracy and reliability for chest disease classification based on X-ray images. Conclusions: The proposed hybrid CNN-ViT model demonstrates substantial potential in advancing the accuracy and robustness of CAD systems for chest disease diagnosis. By integrating CNN and ViT architectures, our approach enhances the diagnostic precision, which may help to alleviate the burden on healthcare systems in resource-limited settings and improve patient outcomes in chest disease diagnosis. Full article

In recent years, the research on human activity recognition based on channel state information (CSI) of Wi-Fi has gradually attracted much attention in order to avoid the deployment of additional devices and reduce the risk of personal privacy leakage. In this paper, we propose a hybrid network architecture, named VBCNet, that can effectively identify human activity postures. Firstly, we extract CSI sequences from each antenna of Wi-Fi signals, and the data are preprocessed and tokenised. Then, in the encoder part of the model, we introduce a layer of long short-term memory network to further extract the temporal features in the sequences and enhance the ability of the model to capture the temporal information. Meanwhile, VBCNet employs a convolutional feed-forward network instead of the traditional feed-forward network to enhance the model’s ability to process local and multi-scale features. Finally, the model classifies the extracted features into human behaviours through a classification layer. To validate the effectiveness of VBCNet, we conducted experimental evaluations on the classical human activity recognition datasets UT-HAR and Widar3.0 and achieved an accuracy of 98.65% and 77.92%. These results show that VBCNet exhibits extremely high effectiveness and robustness in human activity recognition tasks in complex scenarios. Full article

Convolutional neural networks (CNN) and Vision Transformers (ViT) have long been the main backbone networks for visual classification in the field of deep learning. Although ViT has recently received more attention than CNN due to its excellent fitting ability, their scalability is largely limited by the quadratic complexity of attention computation. For the determination of diabetic retinopathy, the fundus lesions as well as the width, angle, and branching pattern of retinal blood vessels are characterized, inspired by the ability of Mamba and VMamba to efficiently model long sequences, VMamba-m is proposed in this paper. This is a generalized visual skeleton model designed to reduce computational complexity to linear while retaining the advantageous features of ViTs. By modifying the cross-entropy loss function, we enhance the model’s attention to rare categories, especially in large-scale multi-category classification tasks. In order to enhance the adaptability of the VMamba-m model in processing visual data, we introduce the se channel attention mechanism, which enables the model to learn features in the channel dimension and form the importance of each channel. Finally, different weights are assigned to each channel through the incentive part. In addition to this, this paper further improves the implementation details and architectural design by introducing a novel attention mechanism implemented based on the local windowing method, which aims to optimize the model’s ability in processing long sequence data to enhance the performance of VMamba-m and improve its inference speed. Extensive experimental results show that VMamba-m performs well in the retinopathy V classification task, and it has significant advantages in terms of accuracy and computation time over existing benchmark models. Full article

Object tracking in remote sensing videos is a challenging task in computer vision. Recent advances in deep learning have sparked significant interest in tracking algorithms based on Siamese neural networks. However, many existing algorithms fail to deliver satisfactory performance in complex scenarios due to challenging conditions and limited computational resources. Thus, enhancing tracking efficiency and improving algorithm responsiveness in complex scenarios are crucial. To address tracking drift caused by similar objects and background interference in remote sensing image tracking, we propose an enhanced Siamese network based on the SiamRhic architecture, incorporating a cross-correlation and ranking head for improved object tracking. We first use convolutional neural networks for feature extraction and integrate the CBAM (Convolutional Block Attention Module) to enhance the tracker’s representational capacity, allowing it to focus more effectively on the objects. Additionally, we replace the original depth-wise cross-correlation operation with asymmetric convolution, enhancing both speed and performance. We also introduce a ranking loss to reduce the classification confidence of interference objects, addressing the mismatch between classification and regression. We validate the proposed algorithm through experiments on the OTB100, UAV123, and OOTB remote sensing datasets. Specifically, SiamRhic achieves success, normalized precision, and precision rates of 0.533, 0.786, and 0.812, respectively, on the OOTB benchmark. The OTB100 benchmark achieves a success rate of 0.670 and a precision rate of 0.892. Similarly, in the UAV123 benchmark, SiamRhic achieves a success rate of 0.621 and a precision rate of 0.823. These results demonstrate the algorithm’s high precision and success rates, highlighting its practical value. Full article

In modern knitted garment production, accurate identification of fabric texture is crucial for enabling automation and ensuring consistent quality control. Traditional manual recognition methods not only demand considerable human effort but also suffer from inefficiencies and are prone to subjective errors. Although machine learning-based approaches have made notable advancements, they typically rely on manual feature extraction. This dependency is time-consuming and often limits recognition accuracy. To address these limitations, this paper introduces a novel model, called the Differentiated Leaning Weighted DenseNet (DLW-DenseNet), which builds upon the DenseNet architecture. Specifically, DLW-DenseNet introduces a learnable weight mechanism that utilizes channel attention to enhance the selection of relevant channels. The proposed mechanism reduces information redundancy and expands the feature search space of the model. To maintain the effectiveness of channel selection in the later stages of training, DLW-DenseNet incorportes a differentiated learning strategy. By assigning distinct learning rates to the learnable weights, the model ensures continuous and efficient channel selection throughout the training process, thus facilitating effective model pruning. Furthermore, in response to the absence of publicly available datasets for fabric texture recognition, we construct a new dataset named KF9 (knitted fabric). Compared to the fabric recognition network based on the improved ResNet, the recognition accuracy has increased by five percentage points, achieving a higher recognition rate. Experimental results demonstrate that DLW-DenseNet significantly outperforms other representative methods in terms of recognition accuracy on the KF9 dataset. Full article