Search Results (19,053)

Accurate and rapid detection of Volvariella volvacea (straw mushroom) fruiting bodies at harvestable maturity is a critical prerequisite for automated industrial cultivation. However, existing detection methods often yield high false-negative and false-positive rates when processing a small-scale, densely distributed, and heavily occluded targets against complex straw substrate backgrounds. Furthermore, these methods frequently struggle to balance the competing requirements of architectural efficiency (such as parameter volume and computational complexity) and real-time performance for edge computing. To address these challenges, this study proposes a YOLO11n-CPDM, a lightweight detection model based on an improved YOLO11n architecture. The model incorporates synergistic optimizations across feature extraction, fusion, and reconstruction. First, a Dual Coordinate Attention Feature Extraction mechanism is integrated into the C3k2 bottleneck blocks of the backbone network. This enhances target perception in complex, occluded environments by concurrently modeling global context and local salient features. Second, within the neck network, the standard attention module is replaced with the PnPNystraAttention module, coupled with the DySample dynamic upsampling operator. This modification strengthens contextual relationships among multi-scale features and improves spatial consistency during reconstruction while preserving linear computational complexity. Finally, the detection head is optimized using MBConv blocks based on an inverted residual structure to minimize parameter volume. Experimental results on a custom V. volvacea dataset demonstrate that the proposed YOLO11n-CPDM model achieves significant performance gains, with Precision (P), Recall (R), and Mean Average Precision (mAP50) reaching 86.8%, 87.5%, and 88.4%, respectively. These figures represent improvements of 2.7, 3.0, and 3.2 percentage points over the baseline YOLO11n model. Additionally, the model size is reduced to 4.8 MB (a 12.7% decrease), while achieving inference speeds of 42.7 FPS on Jetson AGX Orin and 21.2 FPS on Jetson Nano, outperforming the baseline model on both embedded platforms. Consequently, the proposed model effectively enhances detection performance in complex environments while maintaining excellent lightweight characteristics and deployment flexibility, providing a solid technical foundation for intelligent perception and automated harvesting of V. volvacea. Full article

The high prevalence of cardiovascular diseases and the extensive application wearable electrocardiogram (ECG) devices for long-term monitoring have posed significant challenges for the transmission, storage, and real-time processing of massive amounts of ECG data. Consequently, efficient ECG compression and reconstruction have become a research priority in remote ECG monitoring. Traditional compressed sensing is complex and has high computational overhead, while single deep learning models cannot simultaneously extract local waveforms and model temporal dependencies. To address these shortcomings in the reconstruction process, this paper presents a CNN-LSTM-Attention hybrid model. This model utilizes a convolutional neural network (CNN) to capture local ECG waveform features, employs a long short-term memory (LSTM) network to learn long-term temporal dependencies, and introduces an attention mechanism to weight and fuse key diagnostic features, enabling accurate focus on key components including the QRS complex and ST segment. Experimental results on the MIT-BIH Arrhythmia dataset demonstrate that across the full compression range of 0.1–0.9, the proposed model achieves favorable comprehensive performance. Its PRD is stabilized at 10–12%, the SNR stays above 20 dB, and the RMSE is mostly lower than 0.25 mV. In terms of reconstruction accuracy and stability, our model outperforms the single CNN and CNN-LSTM models by a large margin. Full article

Existing intelligent fault diagnosis methods ignore the influence of sensors at different positions on the model fault diagnosis performance. Furthermore, the lack of interpretability leads to insufficient reliability of the model fault diagnosis results. Therefore, a physics-informed multi-sensor information fusion method for gearbox fault diagnosis is proposed. The method consists of a physics-informed shallow feature extraction module, a hierarchical multi-scale graph learning module, and an adaptive feature fusion module. The shallow feature extraction module is composed of Laplacian convolution. Multi-scale Laplacian convolution kernels are used to capture multi-frequency and multi-scale feature information, enriching fault representations. The hierarchical multi-scale graph learning module adopts graph convolutional neural networks to conduct deep multi-sensor fault feature extraction for generating high-level features. The adaptive feature fusion module realizes the weighting of important sensor data and the suppression of redundant information through attention scores. This method is validated on two gearbox datasets. The results show that when applied to the SEU dataset, the proposed method achieves a diagnosis accuracy 5.8% higher than that of the state-of-the-art method (MIFNet) under small-sample conditions. In noisy environments, the proposed method achieves an average diagnostic accuracy 1.8% higher than that of the state-of-the-art method (LiConvFormer). This indicates that the proposed method exhibits superior fault diagnosis performance and can effectively handle fault diagnosis tasks under small-sample conditions and in noisy environments. Full article

Global warming poses serious threats to plant reproduction and agricultural productivity by affecting the timing of flowering, a critical developmental transition. Although transcriptional regulation of flowering pathways has been extensively studied, posttranslational and protein-level regulatory mechanisms are gaining increasing attention as important thermosensory switches enabling rapid and reversible responses to temperature fluctuations. These mechanisms include temperature-dependent protein degradation, ubiquitination, liquid–liquid phase separation of intrinsically disordered proteins, protein sequestration, and dynamic protein–protein interactions. This review summarizes current understanding of posttranslational flowering time regulation under high-temperature conditions, focusing on the major interconnected thermosensory modules, such as the temperature-dependent proteostasis of floral repressors and the emergence of temperature-responsive liquid–liquid phase separation (LLPS) of intrinsically disordered proteins (IDPs). Recent discoveries indicate that temperature-responsive flowering relies not only on transcriptional networks but also on dynamic protein-level regulatory mechanisms, including ubiquitination, proteasomal degradation, and liquid–liquid phase separation. However, the fact that these mechanisms have not been validated in crop species leaves their translational potential an open question. Full article

Maritime search and rescue is an important component of emergency response frameworks and primarily relies on Unmanned Aerial Vehicles (UAVs) for maritime object detection. However, maritime accidents frequently occur in low-visibility environments, such as foggy or low-light conditions, which lead to low contrast, blurred object boundaries, and degraded texture representations. Most existing maritime object detection algorithms are developed for natural light scenes, and their performance deteriorates markedly when deployed directly in low-visibility environments, primarily due to reduced image quality that hinders feature extraction and semantic information aggregation. Although several studies incorporate image enhancement techniques prior to detection to improve image quality, these approaches often introduce significant additional computational overhead, limiting their practical deployment on UAV platforms. To tackle these challenges, this paper proposes a lightweight model built upon a recent YOLO framework, termed Multi-Scale Adaptive YOLO (MSA-YOLO), for maritime detection using UAVs in low-visibility environments. The proposed model systematically optimizes the backbone, neck, and detection head networks. Specifically, an improved StarNet backbone is designed by integrating Efficient Channel Attention (ECA) mechanisms and multi-scale convolutional kernels, which strengthen feature extraction capability while maintaining low computational overhead. In the neck network, a high-frequency enhanced residual block branch is inserted into the C3k2 module to capture richer detailed information, while depthwise separable convolution is utilized to further reduce computational cost. Moreover, a non-parametric attention module is incorporated into the detection head to adaptively optimize features in the classification and regression branches. Finally, a joint loss function that combines bounding box regression, classification, and distribution focal losses is utilized to improve detection accuracy and training stability. Experimental results on the constructed AFO, Zhoushan Island, and Shandong Province datasets demonstrate that, relative to YOLOv11-s, MSA-YOLO reduces model parameters and FLOPs by 52.07% and 41.36%, respectively, while achieving improvements of 1.11% and 1.33% in mAP@0.5:0.95 and mAP@0.5. These results indicate that the proposed method effectively balances computational efficiency and detection accuracy, rendering it suitable for practical maritime search and rescue applications in low-visibility environments. Full article

With the continuous increase in the capacity of grid-connected new energy sources such as wind and photovoltaic power, the issues of sub-synchronous oscillation and super-synchronous oscillation caused by the interaction between power electronic devices and the grid have become increasingly prominent. Therefore, accurately localizing online oscillation sources is of great importance for preventing the expansion of accidents. In this paper, a modal parameter identification method is first proposed. By selecting the real part of the synchrophasor as the characteristic quantity, the precise decoupling and identification of Sub/Super-SO modal parameters are realized. On this basis, a physical feature-embedded graph attention network localization method is proposed, in which the high-precision modal parameters obtained from identification are embedded as physical features into graph nodes, and the attention mechanism is used to adaptively learn the oscillation propagation patterns in the grid topology. Finally, simulation verification based on the IEEE 14-bus system demonstrates that the proposed method can effectively achieve accurate localization of oscillation sources. Full article

Synthetic aperture radar (SAR) ship detection faces three persistent challenges: coherent speckle noise that obscures target boundaries, heterogeneous background clutter in coastal and harbor scenes, and ship targets whose spatial extent varies by more than an order of magnitude within the same image. To address these issues jointly, this paper proposes MSA-DET, an improved SAR ship detection network built upon YOLOv11. In the backbone, a Multi-Scale Cross-axis Attention module (MSCAttention) runs horizontal and vertical axial attention branches in parallel across multiple receptive-field scales, sharpening feature representations for ship targets that vary widely in size and orientation. In the neck, the standard C3k2 block is redesigned as C3k2_SSA by embedding sparse self-attention, which selectively focuses on the most discriminative spatial tokens while suppressing speckle interference and reducing computational overhead. An Adaptive Spatial Feature Fusion detection head (ASFF) replaces fixed pyramid-level aggregation with learned per-pixel blending weights, resolving gradient conflicts across scales and improving localization consistency for both small and large ships. On the HRSID dataset, MSA-DET achieves an mAP@0.5:0.95 of 63.6% and mAP@0.5 of 88.1%, representing gains of 4.0% and 1.6% over the YOLOv11n baseline; on SSDD, it reaches 69.6% and 97.7%, surpassing the baseline by 7.2% and 2.1%, respectively. These results demonstrate that coordinated multi-stage redesign—rather than isolated module substitution—is an effective strategy for SAR-oriented ship detection. The accuracy gains are accompanied by a moderate increase in model size (8.9 M parameters versus 2.6 M for YOLOv11n) and computational cost (9.6 G FLOPs versus 6.3 G), a trade-off that is justified by the substantial improvement in detection quality. Full article

This paper provides a systematic synthesis of recent developments in physics-informed neural networks (PINNs) applied to aerospace engineering, with an emphasis on their role in physically consistent surrogate modeling, forward simulation, and inverse parameter estimation. Using a PRISMA-based methodology, the study surveys peer-reviewed works published between 2017 and 2025 across aviation- and space-related domains, including aerodynamics, structural mechanics, aeroelasticity, propulsion, control, structural health monitoring, satellite-orbit prediction, space-debris collision avoidance, and spacecraft radiation-impact modeling. The analysis shows that embedding governing equations, boundary conditions, and observational data into composite loss functions enables PINNs to improve predictive consistency, reduce dependence on dense simulation or experimental datasets, and support parameter identification under sparse or noisy measurements. Attention is given to architectural variants such as XPINNs, cPINNs, gPINNs, operator-learning approaches, and hybrid PINN-CFD/FEM formulations, as well as to training strategies based on adaptive sampling, domain decomposition, transfer learning, and dynamic loss weighting. Reported benefits include reduced approximation error, improved convergence in selected high-gradient or multiphysics problems, and enhanced interpretability compared with purely data-driven models. At the same time, the review identifies persistent open challenges, including scalability to large aerospace domains, sensitivity to loss-weighting and collocation strategies, limited robustness under noise and uncertainty, high computational cost, and the lack of standardized aerospace benchmarks. Overall, the review highlights PINNs as a promising but still developing framework for fast, interpretable, and physically consistent modeling of aircraft and spacecraft systems. Full article

Person re-identification (re-ID) aims to match pedestrian images across disjoint camera views. Existing multi-source unsupervised domain adaptation (UDA) re-ID methods still face two critical issues: they fail to effectively balance domain-invariant feature learning and domain-specific style preservation and cannot adequately model the implicit correlations among diverse source domains, resulting in limited cross-domain generalization performance. To address these challenges, this paper proposes a novel multi-source UDA re-ID framework equipped with a Mixture of Experts feature extraction (MEFE) network and a Graph-Based Relation (GBR) module. Specifically, the MEFE network integrates mixed Instance and Batch Normalization (MIBN) to extract robust domain-invariant features, while the embedded domain-specific style information (DSI) module compensates for lost domain-specific style details at the feature level. Furthermore, the cascaded Graph Attention and Graph Convolution Networks (GATs/GCNs) in the GBR module adaptively explore implicit feature correlations and achieve effective multi-source feature fusion. Center maximum mean discrepancy loss is adopted to further reduce cross-domain distribution discrepancies. Extensive experiments on large-scale datasets demonstrate that the proposed method achieves state-of-the-art performance and substantially outperforms mainstream UDA re-ID approaches. Full article

Visual inspection of apple leaf diseases is inefficient and subjective, limiting large-scale orchard applications. To realize rapid and accurate disease identification, this paper proposes an improved YOLOv11 model integrated with a Dual Sparse Selection Attention (DSSA) module. By embedding the DSSA module into the key layers of the YOLOv11 backbone network, the model enhances fine-grained feature extraction for small and complex lesions while suppressing background interference. A tailored training strategy with an optimized learning rate and optimizer is designed to ensure stable convergence. Experiments are conducted on a dataset consisting of 7594 images covering four categories: black rot, rust, scab, and healthy leaves. The proposed model achieves precision of 0.973, recall of 0.978, mAP50 of 0.991, and 0.949 mAP50–95, outperforming YOLOv8, YOLOv9, YOLOv10, and the vanilla YOLOv11. Furthermore, a Qt-based visualization system is developed for practical orchard deployment. This method provides a reliable solution for intelligent apple leaf disease detection and smart orchard management. Full article

Chinese cloze question generation for educational assessments requires identifying gap phrases that accurately reflect key knowledge points, posing significant challenges to automated systems. We observe that the syntactic boundaries revealed by part-of-speech (POS) tags closely align with the semantic boundaries of target gap phrases. Motivated by this observation, we propose a multi-task learning framework in which gap phrase identification serves as the primary task and POS tagging as a complementary auxiliary task. The two tasks share a common BERT-BiLSTM encoder, enabling mutual reinforcement of both syntactic and semantic representations through joint training. To further capture the interaction between label semantics and contextual word representations, we introduce a label-attention mechanism that models dependencies between the global word sequence and candidate label embeddings. Additionally, we construct a refined POS tag subset by excluding categories whose boundaries show no alignment with gap phrase boundaries, thereby strengthening the correspondence between the two tasks. Evaluated on a real-world dataset of 20.5K questions spanning five academic disciplines, our method achieves an F1 score of 65.85%, with a Recall of 67.79%, representing improvements of 2.12% and 4.35% over the prior state-of-the-art, respectively. These results demonstrate that exploiting the alignment between syntactic and semantic structures through joint learning is effective for generating educationally meaningful fill-in-the-blank questions. Full article

Hyperspectral image (HSI) and LiDAR data fusion is valuable for land-cover classification in complex surface scenes. Existing methods typically extract features from each modality independently and then consider how to fuse them, ignoring the semantic consistency between features of different modalities and across different hierarchical levels. Moreover, fully mining and exploiting the complementary information between multimodal remote sensing data remains a critical issue. To address these challenges, this paper proposes a hierarchical semantic consistency constraint (HSCC) framework for HSI and LiDAR data joint classification. The framework is co-constructed by a progressive interactive fusion network (PIFNet) and a semantic consistency constraint (SCC) strategy. Specifically, PIFNet progressively calibrates the semantic representations of multimodal features at different abstraction levels through Cross-Modal Shared Attention and Symmetric Cross-Attention mechanisms, promoting information parity in deep interactions. The SCC strategy establishes multi-level semantic associations and employs a semantic consistency constraint loss to guide the network to autonomously maintain the consistency of the same land-cover object across heterogeneous feature representations, thereby further enhancing the discriminative power of the fused features. Experiments on three public datasets, MUUFL, Houston2013, and Augsburg, demonstrate that HSCC outperforms current state-of-the-art methods, validating its effectiveness in multi-source remote sensing data fusion classification tasks. Full article

Safety signs in innovative manufacturing environments fail to match dynamic risks due to the separation of perception, semantics, and decision-making. Existing methods lack closed-loop integration of IoT sensor streams, knowledge graph reasoning, and adaptive signage control. This paper proposes a framework that fuses dynamic graph attention networks with hierarchical temporal knowledge graphs and reinforcement learning optimization. The framework extracts spatiotemporal dependencies from multi-source sensors, traces risk propagation paths on an industrial knowledge graph, and generates adaptive signage actions. Experimental results demonstrate that the proposed method achieves 96.7% risk identification accuracy, a 91.3% risk propagation F1 score, a 94.2 semantic matching score, and 43.65 milliseconds response latency. Real-world validation on an aerospace workshop confirms the method’s effectiveness. This work provides a closed-loop solution from physical perception to adaptive semantic expression for intelligent manufacturing safety. Full article

Immunohistochemistry (IHC) is a widely used method for detecting specific proteins in tissue samples, helping diagnose diseases such as cancer. Traditional analysis methods rely heavily on human interpretation, which can lead to inconsistencies. In this study, we propose DeepFlare, a weakly supervised deep learning framework for cross-modality translation and segmentation of immunofluorescence and immunohistochemistry images. The proposed method utilizes multiplex immunofluorescence (mpIF) and co-registered IHC images, combined with preprocessing techniques such as affine transformation, stain normalization, noise reduction, and artifact removal. Multiple imaging channels, including hematoxylin, DAPI, Lap2, and nuclear envelope signals, are leveraged to generate segmentation masks using a U-Net++ architecture. The final segmentation mask is obtained through weighted fusion of modality-specific outputs. A generative adversarial network (GAN) is employed to measure translation fidelity between generated and real images. Weakly supervised learning techniques, including image-level supervision and consistency constraints, are applied to enhance performance under limited annotation scenarios. Pretrained pathology foundation encoders such as UNI and Virchow are integrated to extract multi-scale morphological and contextual features. Explainable AI techniques are incorporated to highlight critical regions and refine model attention. Experimental results demonstrate strong performance, achieving an SSIM of 0.7077 for image translation and a Dice score of 0.7424 for segmentation. The integration of the UNI encoder provides marginal improvement over the baseline (0.72 Dice score), indicating limited domain adaptation without fine-tuning on the dataset of 1264 training samples. Full article

Leakage detection in water distribution networks is a core component of smart water management. Addressing the limitations of traditional acoustic detection methods, which heavily rely on manual expertise, and the inadequate feature extraction and low recognition rates for minor leaks of existing deep learning models in complex noise environments, this study proposes a novel hybrid architecture CNN model named Incep-ResNet. The model innovatively integrates multi-scale feature extraction and deep residual learning, incorporating an SE attention mechanism to achieve adaptive recalibration of feature channels. Experimental results demonstrate that the model achieves a leakage identification accuracy of 96.6%, representing improvements of 6.7% and 7% compared to ResNet18 and GoogLeNet, respectively. It exhibits excellent noise resistance and feature extraction capabilities, providing a new technical solution for intelligent leakage detection. Full article