Search Results (1,809)

This paper proposes a low-complexity signal detection method for orthogonal time frequency space (OTFS) communication systems, based on a separable convolutional neural network (SeCNN), termed SeCNN-OTFS. A novel SeparableBlock architecture is introduced, which integrates residual connections and a channel attention mechanism to enhance feature discrimination and training stability under high Doppler conditions. By decomposing standard convolutions into depthwise and pointwise operations, the model achieves a substantial reduction in computational complexity. To validate its effectiveness, simulations are conducted under a standard OTFS configuration with 64-QAM modulation, comparing the proposed SeCNN-OTFS with conventional CNN-based models and classical linear estimators, such as least squares (LS) and minimum mean square error (MMSE). The results show that SeCNN-OTFS consistently outperforms LS and MMSE, and when the signal-to-noise ratio (SNR) exceeds 12.5 dB, its bit error rate (BER) performance becomes nearly identical to that of 2D-CNN. Notably, SeCNN-OTFS requires only 19% of the parameters compared to 2D-CNN, making it highly suitable for resource-constrained environments such as satellite and IoT communication systems. For scenarios where higher accuracy is required and computational resources are sufficient, the CNN-OTFS model—with conventional convolutional layers replacing the separable convolutional layers—can be adopted as a more precise alternative. Full article

This study proposes an improved YOLO11n-seg instance segmentation model to address the limitations of existing models in accurately identifying mature blueberries in complex greenhouse environments. Current methods often lack sufficient accuracy when dealing with complex scenarios, such as fruit occlusion, lighting variations, and target overlap. To overcome these challenges, we developed a novel approach that integrates a Spatial–Channel Adaptive (SCA) attention mechanism and a Dual Attention Balancing (DAB) module. The SCA mechanism dynamically adjusts the receptive field through deformable convolutions and fuses multi-scale color features. This enhances the model’s ability to recognize occluded targets and improves its adaptability to variations in lighting. The DAB module combines channel–spatial attention and structural reparameterization techniques. This optimizes the YOLO11n structure and effectively suppresses background interference. Consequently, the model’s accuracy in recognizing fruit contours improves. Additionally, we introduce Normalized Wasserstein Distance (NWD) to replace the traditional intersection over union (IoU) metric and address bias issues that arise in dense small object matching. Experimental results demonstrate that the improved model significantly improves target detection accuracy, recall rate, and mAP@0.5, achieving increases of 1.8%, 1.5%, and 0.5%, respectively, over the baseline model. On our self-built greenhouse blueberry dataset, the mask segmentation accuracy, recall rate, and mAP@0.5 increased by 0.8%, 1.2%, and 0.1%, respectively. In tests across six complex scenarios, the improved model demonstrated greater robustness than mainstream models such as YOLOv8n-seg, YOLOv8n-seg-p6, and YOLOv9c-seg, especially in scenes with dense occlusions. The improvement in mAP@0.5 and F1 scores validates the effectiveness of combining attention mechanisms and multiple metric optimizations, for instance, segmentation tasks in complex agricultural scenes. Full article

Precise recognition of individual ovine specimens plays a pivotal role in implementing smart agricultural platforms and optimizing herd management systems. With the development of deep learning technology, sheep face recognition provides an efficient and contactless solution for individual sheep identification. However, with the growth of sheep, their facial features keep changing, which poses challenges for existing sheep face recognition models to maintain accuracy across the dynamic changes in facial features over time, making it difficult to meet practical needs. To address this limitation, we propose the lifelong biometric learning of the sheep face network (LBL-SheepNet), a feature decoupling network designed for continuous adaptation to ovine facial changes, and constructed a dataset of 31,200 images from 55 sheep tracked monthly from 1 to 12 months of age. The LBL-SheepNet model addresses dynamic variations in facial features during sheep growth through a multi-module architectural framework. Firstly, a Squeeze-and-Excitation (SE) module enhances discriminative feature representation through adaptive channel-wise recalibration. Then, a nonlinear feature decoupling module employs a hybrid channel-batch attention mechanism to separate age-related features from identity-specific characteristics. Finally, a correlation analysis module utilizes adversarial learning to suppress age-biased feature interference, ensuring focus on age-invariant identifiers. Experimental results demonstrate that LBL-SheepNet achieves 95.5% identification accuracy and 95.3% average precision on the sheep face dataset. This study introduces a lifelong biometric learning (LBL) mechanism to mitigate recognition accuracy degradation caused by dynamic facial feature variations in growing sheep. By designing a feature decoupling network integrated with adversarial age-invariant learning, the proposed method addresses the performance limitations of existing models in long-term individual identification. Full article

Mangroves play a crucial role in ecosystems, and the accurate classification and real-time monitoring of mangrove species are essential for their protection and restoration. To improve the segmentation performance of mangrove UAV remote sensing images, this study performs species segmentation after the super-resolution (SR) reconstruction of images. Therefore, we propose SwinNET, an SR reconstruction network. We design a convolutional enhanced channel attention (CEA) module within a network to enhance feature reconstruction through channel attention. Additionally, the Neighborhood Attention Transformer (NAT) is introduced to help the model better focus on domain features, aiming to improve the reconstruction of leaf details. These two attention mechanisms are symmetrically integrated within the network to jointly capture complementary information from spatial and channel dimensions. The experimental results demonstrate that SwinNET not only achieves superior performance in SR tasks but also significantly enhances the segmentation accuracy of mangrove species. Full article

Non-invasive ultrasound diagnosis, combined with deep learning, is frequently used for detecting thyroid diseases. However, real-time detection on portable devices faces limitations due to constrained computational resources, and existing models often lack sufficient capability for small object detection of thyroid nodules. To address this, this paper proposes an improved lightweight small object detection network framework called LISA-YOLO, which enhances the lightweight multi-scale collaborative fusion algorithm. The proposed framework exploits the inherent symmetrical characteristics of ultrasound images and the symmetrical architecture of the detection network to better capture and represent features of thyroid nodules. Specifically, an improved depthwise separable convolution algorithm replaces traditional convolution to construct a lightweight network (DG-FNet). Through symmetrical cross-scale fusion operations via FPN, detection accuracy is maintained while reducing computational overhead. Additionally, an improved bidirectional feature network (IMS F-NET) fully integrates the semantic and detailed information of high- and low-level features symmetrically, enhancing the representation capability for multi-scale features and improving the accuracy of small object detection. Finally, a collaborative attention mechanism (SAF-NET) uses a dual-channel and spatial attention mechanism to adaptively calibrate channel and spatial weights in a symmetric manner, effectively suppressing background noise and enabling the model to focus on small target areas in thyroid ultrasound images. Extensive experiments on two image datasets demonstrate that the proposed method achieves improvements of 2.3% in F1 score, 4.5% in mAP, and 9.0% in FPS, while maintaining only 2.6 M parameters and reducing GFLOPs from 6.1 to 5.8. The proposed framework provides significant advancements in lightweight real-time detection and demonstrates the important role of symmetry in enhancing the performance of ultrasound-based thyroid diagnosis. Full article

Despite advances in Convolutional Neural Networks (CNNs) for intelligent fault diagnosis in CNC machine tools, bearing fault diagnosis in CNC feed systems remains challenging, particularly in multi-scale feature extraction and generalization across operating conditions. This study introduces an enhanced multi-scale feature network (MSFN) that addresses these limitations through three integrated modules designed to extract critical fault features from vibration signals. First, a Soft-Scale Denoising (S2D) module forms the backbone of the MSFN, capturing multi-scale fault features from input signals. Second, a Multi-Scale Adaptive Feature Enhancement (MS-AFE) module based on long-range weighting mechanisms is developed to enhance the extraction of periodic fault features. Third, a Dynamic Sequence–Channel Attention (DSCA) module is incorporated to improve feature representation across channel and sequence dimensions. Experimental results on two datasets demonstrate that the proposed MSFN achieves high diagnostic accuracy and exhibits robust generalization across diverse operating conditions. Moreover, ablation studies validate the effectiveness and contributions of each module. Full article

Automatic component recognition plays a crucial role in intelligent ship manufacturing, but existing methods suffer from low recognition accuracy and high computational cost in industrial scenarios involving small samples, component stacking, and diverse categories. To address the requirements of shipbuilding industrial applications, a Triplet Spatial Reconstruction Attention (TSA) mechanism that combines threshold-based feature separation with triplet parallel processing is proposed, and a lightweight You Only Look Once Ship (YOLO-Ship) detection network is constructed. Unlike existing attention mechanisms that focus on either spatial reconstruction or channel attention independently, the proposed TSA integrates triplet parallel processing with spatial feature separation–reconstruction techniques to achieve enhanced target feature representation while significantly reducing parameter count and computational overhead. Experimental validation on a small-scale actual ship component dataset demonstrates that the improved network achieves 88.7% mean Average Precision (mAP), 84.2% precision, and 87.1% recall, representing improvements of 3.5%, 2.2%, and 3.8%, respectively, compared to the original YOLOv8n algorithm, requiring only 2.6 M parameters and 7.5 Giga Floating-point Operations per Second (GFLOPs) computational cost, achieving a good balance between detection accuracy and lightweight model design. Future research directions include developing adaptive threshold learning mechanisms for varying industrial conditions and integration with surface defect detection capabilities to enhance comprehensive quality control in intelligent manufacturing systems. Full article

Emotion analysis based on electroencephalogram (EEG) sensors is pivotal for human–machine interaction yet faces key challenges in spatio-temporal feature fusion and cross-band and brain-region integration from multi-channel sensor-derived signals. This paper proposes MB-MSTFNet, a novel framework for EEG emotion recognition. The model constructs a 3D tensor to encode band–space–time correlations of sensor data, explicitly modeling frequency-domain dynamics and spatial distributions of EEG sensors across brain regions. A multi-scale CNN-Inception module extracts hierarchical spatial features via diverse convolutional kernels and pooling operations, capturing localized sensor activations and global brain network interactions. Bi-directional GRUs (BiGRUs) model temporal dependencies in sensor time-series, adept at capturing long-range dynamic patterns. Multi-head self-attention highlights critical time windows and brain regions by assigning adaptive weights to relevant sensor channels, suppressing noise from non-contributory electrodes. Experiments on the DEAP dataset, containing multi-channel EEG sensor recordings, show that MB-MSTFNet achieves 96.80 ± 0.92% valence accuracy, 98.02 ± 0.76% arousal accuracy for binary classification tasks, and 92.85 ± 1.45% accuracy for four-class classification. Ablation studies validate that feature fusion, bidirectional temporal modeling, and multi-scale mechanisms significantly enhance performance by improving feature complementarity. This sensor-driven framework advances affective computing by integrating spatio-temporal dynamics and multi-band interactions of EEG sensor signals, enabling efficient real-time emotion recognition. Full article

Hyperspectral image (HSI) denoising is a crucial step in image preprocessing as its effectiveness has a direct impact on the accuracy of subsequent tasks such as land cover classification, target recognition, and change detection. However, existing methods suffer from limitations in effectively integrating multi-scale features and adaptively modeling complex noise distributions, making it difficult to construct effective spatial–spectral joint representations. This often leads to issues like detail loss and spectral distortion, especially when dealing with complex mixed noise. To address these challenges, this paper proposes a multi-scale differentiated denoising network based on spatial–spectral cooperative attention (MDSSANet). The network first constructs a multi-scale image pyramid using three downsampling operations and independently models the features at each scale to better capture noise characteristics at different levels. Additionally, a spatial–spectral cooperative attention module (SSCA) and a differentiated multi-scale feature fusion module (DMF) are introduced. The SSCA module effectively captures cross-spectral dependencies and spatial feature interactions through parallel spectral channel and spatial attention mechanisms. The DMF module adopts a multi-branch parallel structure with differentiated processing to dynamically fuse multi-scale spatial–spectral features and incorporates a cross-scale feature compensation strategy to improve feature representation and mitigate information loss. The experimental results show that the proposed method outperforms state-of-the-art methods across several public datasets, exhibiting greater robustness and superior visual performance in tasks such as handling complex noise and recovering small targets. Full article

Soft manipulators have garnered significant research attention in recent years due to their flexibility and adaptability. However, the inherent flexibility of these manipulators imposes limitations on their load-bearing capacity and stability. To address this, this study compares various variable stiffness technologies and proposes a novel design concept: leveraging the phase-change characteristics of low-melting-point alloys (LMPAs) with distinct melting points to fulfill the variable stiffness requirements of soft manipulators. The pneumatic structure of the manipulator is fabricated via 3D-printed molds and silicone casting. The manipulator integrates a pneumatic working chamber, variable stiffness chambers, heating devices, sensors, and a central channel, achieving multi-stage variable stiffness through controlled heating of the LMPAs. A steady-state temperature field distribution model is established based on the integral form of Fourier’s law, complemented by finite element analysis (FEA). Subsequently, the operational temperatures at which the variable stiffness mechanism activates, and the bending performance are experimentally validated. Finally, stiffness characterization and kinematic performance experiments are conducted to evaluate the manipulator’s variable stiffness capabilities and flexibility. This design enables the manipulator to switch among low, medium, and high stiffness levels, balancing flexibility and stability, and provides a new paradigm for the design of soft manipulators. Full article

Hyperspectral image (HSI) classification is an important task in the field of remote sensing, with far-reaching practical significance. Most Convolutional Neural Networks (CNNs) only focus on local spatial features and ignore global spectral dependencies, making it difficult to completely extract spectral information in HSI. In contrast, Vision Transformers (ViTs) are widely used in HSI due to their superior feature extraction capabilities. However, existing Transformer models have challenges in achieving spectral–spatial feature fusion and maintaining local structural consistency, making it difficult to strike a balance between global modeling capabilities and local representation. To this end, we propose a Prompt-Gated Transformer with a Spatial–Spectral Enhancement (PGTSEFormer) network, which includes a Channel Hybrid Positional Attention Module (CHPA) and Prompt Cross-Former (PCFormer). The CHPA module adopts a dual-branch architecture to concurrently capture spectral and spatial positional attention, thereby enhancing the model’s discriminative capacity for complex feature categories through adaptive weight fusion. PCFormer introduces a Prompt-Gated mechanism and grouping strategy to effectively model cross-regional contextual information, while maintaining local consistency, which significantly enhances the ability for long-distance dependent modeling. Experiments were conducted on five HSI datasets and the results showed that overall accuracies of 97.91%, 98.74%, 99.48%, 99.18%, and 92.57% were obtained on the Indian pines, Salians, Botswana, WHU-Hi-LongKou, and WHU-Hi-HongHu datasets. The experimental results show the effectiveness of our proposed approach. Full article

Plant disease classification is critical for effective crop management. Recent advances in deep learning, especially Vision Transformers (ViTs), have shown promise due to their strong global feature modeling capabilities. However, ViTs often overlook local features and suffer from feature extraction degradation during patch merging as channels increase. To address these issues, we propose PLTransformer, a hybrid model designed to symmetrically capture both global and local features. We design a symmetric multi-scale convolutional module that combines two different-scale receptive fields to simultaneously extract global and local features so that the model can better perceive multi-scale disease morphologies. Additionally, we propose an overlap-attentive channel downsampler that utilizes inter-channel attention mechanisms during spatial downsampling, effectively preserving local structural information and mitigating semantic loss caused by feature compression. On the PlantVillage dataset, PLTransformer achieves 99.95% accuracy, outperforming DeiT (96.33%), Twins (98.92%), and DilateFormer (98.84%). These results demonstrate its superiority in handling multi-scale disease features. Full article

The accelerated evolution of remote sensing technology has intensified the demand for real-time tile map generation, highlighting the limitations of conventional mapping approaches that rely on manual cartography and field surveys. To address the critical need for rapid cartographic updates, this study presents a novel multi-stage generative framework that synergistically integrates Generative Adversarial Networks (GANs) with Diffusion Denoising Models (DMs) for high-fidelity map generation from remote sensing imagery. Specifically, our proposed architecture first employs GANs for rapid preliminary map generation, followed by a cascaded diffusion process that progressively refines topological details and spatial accuracy through iterative denoising. Furthermore, we propose a hybrid attention mechanism that strategically combines channel-wise feature recalibration with coordinate-aware spatial modulation, enabling the enhanced discrimination of geographic features under challenging conditions involving edge ambiguity and environmental noise. Quantitative evaluations demonstrate that our method significantly surpasses established baselines in both structural consistency and geometric fidelity. This framework establishes an operational paradigm for automated, rapid-response cartography, demonstrating a particular utility in time-sensitive applications including disaster impact assessment, unmapped terrain documentation, and dynamic environmental surveillance. Full article

Fault diagnosis is of great significance for the maintenance of rotating machinery. Deep learning is an intelligent diagnostic technique that is receiving increasing attention. To address the issues of industrial data with small samples and varying working conditions, a residual convolutional neural network based on the attention mechanism is put forward for the fault diagnosis of rotating machinery. The method incorporates channel attention and spatial attention simultaneously, implementing channel-wise recalibration for frequency-dependent feature adjustment and performing spatial context aggregation across receptive fields. Subsequently, a residual module is introduced to address the vanishing gradient problem of the model in deep network structures. In addition, LSTM is used to realize spatiotemporal feature fusion. Finally, label smoothing regularization (LSR) is proposed to balance the distributional disparities among labeled samples. The effectiveness of the method is evaluated by its application to the vibration signal data from the safe injection pump and the Case Western Reserve University (CWRU). The results show that the method has superb diagnostic accuracy and strong robustness. Full article

To address the limitations of the existing cotton seedling growth prediction methods in field environments, specifically, poor representation of spatiotemporal features and low visual fidelity in texture rendering, this paper proposes an algorithm for the prediction of cotton seedling growth from images based on FCA-STNet. The model leverages historical sequences of cotton seedling RGB images to generate an image of the predicted growth at time t + 1 and extracts 37 phenotypic traits from the predicted image. A novel STNet structure is designed to enhance the representation of spatiotemporal dependencies, while an Adaptive Fine-Grained Channel Attention (FCA) module is integrated to capture both global and local feature information. This attention mechanism focuses on individual cotton plants and their textural characteristics, effectively reducing the interference from common field-related challenges such as insufficient lighting, leaf fluttering, and wind disturbances. The experimental results demonstrate that the predicted images achieved an MSE of 0.0086, MAE of 0.0321, SSIM of 0.8339, and PSNR of 20.7011 on the test set, representing improvements of 2.27%, 0.31%, 4.73%, and 11.20%, respectively, over the baseline STNet. The method outperforms several mainstream spatiotemporal prediction models. Furthermore, the majority of the predicted phenotypic traits exhibited correlations with actual measurements with coefficients above 0.8, indicating high prediction accuracy. The proposed FCA-STNet model enables visually realistic prediction of cotton seedling growth in open-field conditions, offering a new perspective for research in growth prediction. Full article