Search Results (280)

Visible Light Positioning (VLP) has emerged as a pivotal technology for industrial Internet of Things (IoT) and smart logistics, offering high accuracy, immunity to electromagnetic interference, and cost-effectiveness. However, fluctuations in signal gain caused by target motion significantly degrade the positioning accuracy of current VLP systems. Conventional approaches face intrinsic limitations: propagation-model-based techniques rely on static assumptions, fingerprint-based approaches are highly sensitive to dynamic parameter variations, and although CNN/LSTM-based models achieve high accuracy under static conditions, their inability to capture long-term temporal dependencies leads to unstable performance in dynamic scenarios. To overcome these challenges, we propose a novel dynamic VLP algorithm that incorporates a Spatio-Temporal Feature Information Network (STFI-Net) for joint localization and orientation estimation of moving targets. The proposed method integrates a two-layer convolutional block for spatial feature extraction and employs modern Temporal Convolutional Networks (TCNs) with dilated convolutions to capture multi-scale temporal dependencies in dynamic environments. Experimental results demonstrate that the STFI-Net-based system enhances positioning accuracy by over 26% compared to state-of-the-art methods while maintaining robustness in the face of complex motion patterns and environmental variations. This work introduces a novel framework for deep learning-enabled dynamic VLP systems, providing more efficient, accurate, and scalable solutions for indoor positioning. Full article

Sleep staging is a crucial indicator for assessing sleep quality, which contributes to sleep monitoring and the diagnosis of sleep disorders. Although existing sleep staging methods achieve high classification performance, two major challenges remain: (1) the ability to effectively extract salient features from multi-channel sleep data remains limited; (2) excessive model parameters hinder efficiency improvements. To address these challenges, this work proposes a lightweight multi-channel sleep staging network (LMCSleepNet). LMCSleepNet is composed of four modules. The first module enhances frequency domain features through continuous wavelet transform. The second module extracts time–frequency features using multi-scale convolutions. The third module optimizes ResNet18 with depthwise separable convolutions to reduce parameters. The fourth module improves spatial correlation using the Convolutional Block Attention Module (CBAM). On the public datasets SleepEDF-20, SleepEDF-78, and LMCSleepNet, respectively, LMCSleepNet achieved classification accuracies of 88.2% (κ = 0.84, MF1 = 82.4%) and 84.1% (κ = 0.77, MF1 = 77.7%), while reducing model parameters to 1.49 M. Furthermore, experiments validated the influence of temporal sampling points in wavelet time–frequency maps on sleep classification performance (accuracy, Cohen’s kappa, and macro-average F1-score) and the influence of multi-scale dilated convolution module fusion methods on classification performance. LMCSleepNet is an efficient lightweight model for extracting and integrating multimodal features from multichannel Polysomnography (PSG) data, which facilitates its application in resource-constrained scenarios. Full article

Synthetic aperture radar (SAR) provides all-weather and all-day imaging capabilities and can penetrate clouds and fog, playing an important role in ship detection. However, small ships usually contain weak feature information in such images and are easily affected by noise, which makes detection challenging. In practical deployment, limited computing resources require lightweight models to improve real-time performance, yet achieving a lightweight design while maintaining high detection accuracy for small targets remains a key challenge in object detection. To address this issue, we propose a novel lightweight network for accurate small-ship recognition in SAR images, named S2M-Net. Specifically, the Space-to-Depth Convolution (SPD-Conv) module is introduced in the feature extraction stage to optimize convolutional structures, reducing computation and parameters while retaining rich feature information. The Mixed Local-Channel Attention (MLCA) module integrates local and channel attention mechanisms to enhance adaptation to complex backgrounds and improve small-target detection accuracy. The Multi-Scale Dilated Attention (MSDA) module employs multi-scale dilated convolutions to fuse features from different receptive fields, strengthening detection across ships of various sizes. The experimental results show that S2M-Net achieved mAP50 values of 0.989, 0.955, and 0.883 on the SSDD, HRSID, and SARDet-100k datasets, respectively. Compared with the baseline model, the F1 score increased by 1.13%, 2.71%, and 2.12%. Moreover, S2M-Net outperformed other state-of-the-art algorithms in FPS across all datasets, achieving a well-balanced trade-off between accuracy and efficiency. This work provides an effective solution for accurate ship detection in SAR images. Full article

Detecting surface defects in steel products is essential for maintaining manufacturing quality. However, existing methods struggle with significant challenges, including substantial defect size variations, diverse defect types, and complex backgrounds, leading to suboptimal detection accuracy. This work introduces ELS-YOLO, an advanced YOLOv11n-based algorithm designed to tackle these limitations. A C3k2_THK module is first introduced that combines a partial convolution, heterogeneous kernel selection protocoland the SCSA attention mechanism to improve feature extraction while reducing computational overhead. Additionally, the Staged-Slim-Neck module is developed that employs dual and dilated convolutions at different stages while integrating GMLCA attention to enhance feature representation and reduce computational complexity. Furthermore, an MSDetect detection head is designed to boost multi-scale detection performance. Experimental validation shows that ELS-YOLO outperforms YOLOv11n in detection accuracy while achieving 8.5% and 11.1% reductions in the number of parameters and computational cost, respectively, demonstrating strong potential for real-world industrial applications. Full article

Underwater target detection is a critical technology for marine resource management and ecological protection, but its performance is often limited by complex underwater environments, including optical attenuation, scattering, and dense distributions of small targets. Existing methods have significant limitations in feature extraction efficiency, robustness in class-imbalanced scenarios, and computational complexity. To address these challenges, this study proposes a lightweight adaptive detection model, YOLOv11-MSE, which optimizes underwater detection performance through three core innovations. First, a multi-scale dilated attention (MSDA) mechanism is embedded into the backbone network to dynamically capture multi-scale contextual features while suppressing background noise. Second, a Slim-Neck architecture based on GSConv and VoV-GSCSPC modules is designed to achieve efficient feature fusion via hybrid convolution strategies, significantly reducing model complexity. Finally, an efficient multi-scale attention (EMA) module is introduced in the detection head to reinforce key feature representations and suppress environmental noise through cross-dimensional interactions. Experiments on the underwater detection dataset (UDD) demonstrate that YOLOv11-MSE outperforms the baseline model YOLOv11, achieving a 9.67% improvement in detection precision and a 3.45% increase in mean average precision (mAP50) while reducing computational complexity by 6.57%. Ablation studies further validate the synergistic optimization effects of each module, particularly in class-imbalanced scenarios where detection precision for rare categories (e.g., scallops) is significantly enhanced, with precision and mAP50 improving by 60.62% and 10.16%, respectively. This model provides an efficient solution for edge computing scenarios, such as underwater robots and ecological monitoring, through its lightweight design and high underwater target detection capability. Full article

Defect detection in lithium-ion battery (LIB) welding presents unique challenges, including scale heterogeneity, subtle texture variations, and severe class imbalance. We propose a multi-scale convolutional framework that integrates EfficientNet-B0 for lightweight representation learning, PANet for cross-scale feature aggregation, and a YOLOv8 detection head augmented with multi-head attention. Parallel dilated convolutions are employed to approximate self-similar receptive fields, enabling simultaneous sensitivity to fine-grained microstructural anomalies and large-scale geometric irregularities. The approach is validated on three datasets including RIAWELC, GC10-DET, and an industrial LIB defects dataset, where it consistently outperforms competitive baselines, achieving 8–10% improvements in recall and F1-score while preserving real-time inference on GPU. Ablation experiments and statistical significance tests isolate the contributions of attention and multi-scale design, confirming their role in reducing false negatives. Attention-based visualizations further enhance interpretability by exposing spatial regions driving predictions. Limitations remain regarding fixed imaging conditions and partial reliance on synthetic augmentation, but the framework establishes a principled direction toward efficient, interpretable, and scalable defect inspection in industrial manufacturing. Full article

With the widespread application of wearable sensors in health monitoring and human–computer interaction, deep learning-based human activity recognition (HAR) research faces challenges such as the effective extraction of multi-scale temporal features and the enhancement of robustness against noise in multi-source data. This study proposes the TGA-HAR (TCN-GRU-Attention-HAR) model. The TGA-HAR model integrates Temporal Convolutional Neural Networks and Recurrent Neural Networks by constructing a hierarchical feature abstraction architecture through cascading Temporal Convolutional Network (TCN) and Bidirectional Gated Recurrent Unit (BiGRU) layers for complex activity recognition. This study utilizes TCN layers with dilated convolution kernels to extract multi-order temporal features. This study utilizes BiGRU layers to capture bidirectional temporal contextual correlation information. To further optimize feature representation, the TGA-HAR model introduces residual connections to enhance the stability of gradient propagation and employs an adaptive weighted attention mechanism to strengthen feature representation. The experimental results of this study demonstrate that the model achieved test accuracies of 99.37% on the WISDM dataset, 95.36% on the USC-HAD dataset, and 96.96% on the PAMAP2 dataset. Furthermore, we conducted tests on datasets collected in real-world scenarios. This method provides a highly robust solution for complex human activity recognition tasks. Full article

Cow behavior recognition constitutes a fundamental element of effective cow health monitoring and intelligent farming systems. Within large-scale cow farming environments, several critical challenges persist, including the difficulty in accurately capturing behavioral feature information, substantial variations in multi-scale features, and high inter-class similarity among different cow behaviors. To address these limitations, this study introduces an enhanced target detection algorithm for cow behavior recognition, termed RFR-YOLO, which is developed upon the YOLOv11n framework. A well-structured dataset encompassing nine distinct cow behaviors—namely, lying, standing, walking, eating, drinking, licking, grooming, estrus, and limping—is constructed, comprising a total of 13,224 labeled samples. The proposed algorithm incorporates three major technical improvements: First, an Inverted Dilated Convolution module (Region Semantic Inverted Convolution, RsiConv) is designed and seamlessly integrated with the C3K2 module to form the C3K2_Rsi module, which effectively reduces computational overhead while enhancing feature representation. Second, a Four-branch Multi-scale Dilated Attention mechanism (Four Multi-Scale Dilated Attention, FMSDA) is incorporated into the network architecture, enabling the scale-specific features to align with the corresponding receptive fields, thereby improving the model’s capacity to capture multi-scale characteristics. Third, a Reparameterized Generalized Residual Feature Pyramid Network (Reparameterized Generalized Residual-FPN, RepGRFPN) is introduced as the Neck component, allowing for the features to propagate through differentiated pathways and enabling flexible control over multi-scale feature expression, thereby facilitating efficient feature fusion and mitigating the impact of behavioral similarity. The experimental results demonstrate that RFR-YOLO achieves precision, recall, mAP50, and mAP50:95 values of 95.9%, 91.2%, 94.9%, and 85.2%, respectively, representing performance gains of 5.5%, 5%, 5.6%, and 3.5% over the baseline model. Despite a marginal increase in computational complexity of 1.4G, the algorithm retains a high detection speed of 147.6 frames per second. The proposed RFR-YOLO algorithm significantly improves the accuracy and robustness of target detection in group cow farming scenarios. Full article

Leaves are the key organs in photosynthesis and nutrient production, and leaf counting is an important indicator of banana plant health and growth rate. However, in complex orchard environments, leaves often overlap, the background is cluttered, and illumination varies, making accurate segmentation and detection challenging. To address these issues, we propose a lightweight banana leaf detection and counting method deployable on embedded devices, which integrates a space–depth-collaborative reasoning strategy with multi-scale feature enhancement to achieve efficient and precise leaf identification and counting. For complex background interference and occlusion, we design a multi-scale attention guided feature enhancement mechanism that employs a Mixed Local Channel Attention (MLCA) module and a Self-Ensembling Attention Mechanism (SEAM) to strengthen local salient feature representation, suppress background noise, and improve discriminability under occlusion. To mitigate feature drift caused by environmental changes, we introduce a task-aware dynamic scale adaptive detection head (DyHead) combined with multi-rate depthwise separable dilated convolutions (DWR_Conv) to enhance multi-scale contextual awareness and adaptive feature recognition. Furthermore, to tackle instance differentiation and counting under occlusion and overlap, we develop a detection-guided space–depth position modeling method that, based on object detection, effectively models the distribution of occluded instances through space–depth feature description, outlier removal, and adaptive clustering analysis. Experimental results demonstrate that our YOLOv8n MDSD model outperforms the baseline by 2.08% in mAP50-95, and achieves a mean absolute error (MAE) of 0.67 and a root mean square error (RMSE) of 1.01 in leaf counting, exhibiting excellent accuracy and robustness for automated banana leaf statistics. Full article

The feeding behavior of dairy cows constitutes a complex temporal sequence comprising actions such as head lowering, sniffing, arching, eating, head raising, and chewing. Its precise recognition is crucial for refined livestock management. While existing 2D convolution-based models effectively extract features from individual frames, they lack temporal modeling capabilities. Conversely, due to their high computational complexity, 3D convolutional networks suffer from significantly limited recognition accuracy in high-density feeding scenarios. To address this, this paper proposes a Spatio-Temporal Fusion Network (DAS-Net): it designs a collaborative architecture featuring a 2D branch with a triple-attention module to enhance spatial key feature extraction, constructs a 3D branch based on multi-branch dilated convolution and integrates a 3D multi-scale attention mechanism to achieve efficient long-term temporal modeling. On our Spatio-Temporal Dairy Feeding Dataset (STDF Dataset), which contains 403 video clips and 10,478 annotated frames across seven behavior categories, the model achieves an average recognition accuracy of 56.83% for all action types. This result marks a significant improvement of 3.61 percentage points over the original model. Among them, the recognition accuracy of the eating action has been increased to 94.78%. This method provides a new idea for recognizing dairy cow feeding behavior and can provide technical support for developing intelligent feeding systems in real dairy farms. Full article

To address the limitations of CNNs and RNNs in handling complex operating conditions, multi-scale degradation patterns, and long-term dependencies—with attention mechanisms often failing to highlight key degradation features—this paper proposes a remaining useful life (RUL) prediction framework based on a multi-scale dilated fusion attention (MDFA) module. The MDFA leverages parallel dilated convolutions with varying dilation rates to expand receptive fields, while a global-pooling branch captures sequence-level degradation trends. Additionally, integrated channel and spatial attention mechanisms enhance the model’s ability to emphasize informative features and suppress noise, thereby improving overall prediction robustness. The proposed method is evaluated on NASA’s C-MAPSS and N-CMAPSS datasets, achieving MAE values of 0.018–0.026, RMSE values of 0.021–0.032, and R² scores above 0.987, demonstrating superior accuracy and stability compared to existing baselines. Furthermore, to verify generalization across domains, experiments on the PHM2012 bearing dataset show similar performance (MAE: 0.023–0.026, RMSE: 0.031–0.032, R²: 0.987–0.995), confirming the model’s effectiveness under diverse operating conditions and its adaptability to different degradation behaviors. This study provides a practical and interpretable deep-learning solution for RUL prediction, with broad applicability to aero-engine prognostics and other industrial health-monitoring tasks. Full article

The increasing demand for portable health monitoring has highlighted the need for automated sleep staging systems that are both accurate and computationally efficient. However, most existing deep learning models for electroencephalogram (EEG)-based sleep staging suffer from parameter redundancy, fixed dilation rates, and limited generalization, restricting their applicability in real-time and resource-constrained scenarios. In this paper, we propose ADG-SleepNet, a novel lightweight symmetry-aware multi-scale dilation-gated temporal convolutional network enhanced with adaptive attention mechanisms for EEG-based sleep staging. ADG-SleepNet features a structurally symmetric, parallel multi-branch architecture utilizing various dilation rates to comprehensively capture multi-scale temporal patterns in EEG signals. The integration of adaptive gating and channel attention mechanisms enables the network to dynamically adjust the contribution of each branch based on input characteristics, effectively breaking architectural symmetry when necessary to prioritize the most discriminative features. Experimental results on the Sleep-EDF-20 and Sleep-EDF-78 datasets demonstrate that ADG-SleepNet achieves accuracy rates of 87.1% and 85.1%, and macro F1 scores of 84.0% and 81.1%, respectively, outperforming several state-of-the-art lightweight models. These findings highlight the strong generalization ability and practical potential of ADG-SleepNet for EEG-based health monitoring applications. Full article

X-ray security screening is a well-established technology used in public spaces. The traditional method for detecting prohibited items in X-ray images relies on manual inspection, necessitating security personnel with extensive experience and focused attention to achieve satisfactory detection accuracy. However, the high-intensity and long-duration nature of the work leads to security personnel fatigue, which in turn reduces the accuracy of prohibited items detection and results in false alarms or missed detections. In response to the challenges posed by the coexistence of multiple prohibited items, incomplete identification information due to overlapping items, variable distribution positions in typical scenarios, and the need for portable detection equipment, this study proposes a lightweight automatic detection method for prohibited items. Based on establishment the sample database for prohibited items, a new backbone network with a residual structure and attention mechanism is introduced to form a deep learning algorithm. Additionally, a dilated convolutional spatial pyramid module and a depthwise separable convolution algorithm are added to fuse multi-scale features, to improve the accuracy of prohibited items detection. This study developed a lightweight automatic detection method for prohibited items, and its highest detection rate is 95.59%, which demonstrates a 1.86% mAP improvement over the YOLOv4-tiny baseline with 122 FPS. The study achieved high accurate detection of typical prohibited items, providing support for the assurance of public safety. Full article

Precise segmentation of cell nuclei in pathological images is the foundation of cancer diagnosis and quantitative analysis, but blurred boundaries, scale variability, and staining differences have long constrained its reliability. To address this, this paper proposes AL-Net—an adaptive learning network that breaks through these bottlenecks through three innovative mechanisms: First, it integrates dilated convolutions with attention-guided skip connections to dynamically integrate multi-scale contextual information, adapting to variations in cell nucleus morphology and size. Second, it employs self-scheduling loss optimization: during the initial training phase, it focuses on region segmentation (Dice loss) and later switches to a boundary refinement stage, introducing gradient manifold constraints to sharpen edge localization. Finally, it designs an adaptive optimizer strategy, leveraging symbolic exploration (Lion) to accelerate convergence, and switches to gradient fine-tuning after reaching a dynamic threshold to stabilize parameters. On the 2018 Data Science Bowl dataset, AL-Net achieved state-of-the-art performance (Dice coefficient 92.96%, IoU 86.86%), reducing boundary error by 15% compared to U-Net/DeepLab; in cross-domain testing (ETIS/ColonDB polyp segmentation), it demonstrated over 80% improvement in generalization performance. AL-Net establishes a new adaptive learning paradigm for computational pathology, significantly enhancing diagnostic reliability. Full article

As the safety requirements of elevator systems continue to rise, the detection of loose bolts and the high-precision segmentation of anti-loosening lines have become critical challenges in elevator landing door inspection. Traditional manual inspection and conventional visual detection often fail to meet the requirements of high precision and robustness under real-world conditions such as oil contamination and low illumination. This paper proposes two improved algorithms for detecting loose bolts and segmenting anti-loosening lines in elevator landing doors. For small-bolt detection, we introduce the DS-EMA model, an enhanced YOLOv8 variant that integrates depthwise-separable convolutions and an Efficient Multi-scale Attention (EMA) module. The DS-EMA model achieves a 2.8 percentage point improvement in mAP over the YOLOv8n baseline on our self-collected dataset, while reducing parameters from 3.0 M to 2.8 M and maintaining real-time throughput at 126 FPS. For anti-loosening-line segmentation, we develop an improved DeepLabv3+ by adopting a MobileViT backbone, incorporating a Global Attention Mechanism (GAM) and optimizing the ASPP dilation rate. The revised model increases the mean IoU to 85.8% (a gain of 5.4 percentage points) while reducing parameters from 57.6 M to 38.5 M. Comparative experiments against mainstream lightweight models, including YOLOv5n, YOLOv6n, YOLOv7-tiny, and DeepLabv3, demonstrate that the proposed methods achieve superior accuracy while balancing efficiency and model complexity. Moreover, compared with recent lightweight variants such as YOLOv9-tiny and YOLOv11n, DS-EMA achieves comparable mAP while delivering notably higher recall, which is crucial for safety inspection. Overall, the enhanced YOLOv8 and DeepLabv3+ provide robust and efficient solutions for elevator landing door safety inspection, delivering clear practical application value. Full article