Search Results (449)

Poultry feces, a critical biomarker for health assessment, requires timely and accurate pathological identification for food safety. Conventional visual-only methods face limitations due to environmental sensitivity and high visual similarity among feces from different diseases. To address this, we propose MMCD (Multimodal Chicken-feces Diagnosis), a ResNet50-based multimodal fusion model leveraging semantic complementarity between images and descriptive text to enhance diagnostic precision. Key innovations include the following: (1) Integrating MASA(Manhattan self-attention)and DSconv (Depthwise Separable convolution) into the backbone network to mitigate feature confusion. (2) Utilizing a pre-trained BERT to extract textual semantic features, reducing annotation dependency and cost. (3) Designing a lightweight Gated Cross-Attention (GCA) module for dynamic multimodal fusion, achieving a 41% parameter reduction versus cross-modal transformers. Experiments demonstrate that MMCD significantly outperforms single-modal baselines in Accuracy (+8.69%), Recall (+8.72%), Precision (+8.67%), and F1 score (+8.72%). It surpasses simple feature concatenation by 2.51–2.82% and reduces parameters by 7.5M and computations by 1.62 GFLOPs versus the base ResNet50. This work validates multimodal fusion’s efficacy in pathological fecal detection, providing a theoretical and technical foundation for agricultural health monitoring systems. Full article

This paper provides a comparative study of unsupervised Deep Learning (DL) methods for anomaly detection in Flight Data Monitoring (FDM). The paper applies Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), Convolutional Neural Network (CNN), classic Transformer architecture, and LSTM combined with a self-attention mechanism to real-world flight data and compares the results to the current state-of-the-art flight data analysis techniques applied in the industry. The paper finds that LSTM, when integrated with a self-attention mechanism, offers notable benefits over other deep learning methods as it effectively handles lengthy time series like those present in flight data, establishes a generalized model applicable across various airports and facilitates the detection of trends across the entire fleet. The results were validated by industrial experts. The paper additionally investigates a range of methods for feeding flight data (lengthy time series) to a neural network. The innovation of this paper involves utilizing Transformer architecture and LSTM with self-attention mechanism for the first time in the realm of aviation data, exploring the optimal method for inputting flight data into a model and evaluating all deep learning techniques for anomaly detection against the ground truth determined by human experts. The paper puts forth a compelling case for shifting from the existing method, which relies on examining events through threshold exceedances, to a deep learning-based approach that offers a more proactive style of data analysis. This not only enhances the generalization of the FDM process but also has the potential to improve air transport safety and optimize aviation operations. Full article

Gallium nitride high-electron-mobility transistors (GaN HEMTs) are critical for high-power applications like AI power supplies and robotics but face reliability challenges due to increased dynamic ON-resistance (R_{DS_ON}) from electrical and thermomechanical stresses. This paper presents a novel self-calibrating temperature-sensitive electrical parameter (TSEP) model that uses gate leakage current (I_G) to estimate junction temperature with high accuracy, uniquely addressing aging effects overlooked in prior studies. By integrating I_G, aging-induced degradation, and failure-in-time (FIT) models, the approach achieves a junction temperature estimation error of less than 1%. Long-term hard-switching tests confirm its effectiveness, with calibrated R_{DS_ON} measurements enabling precise remaining useful life (RUL) predictions. This methodology significantly improves GaN HEMT reliability assessment, enhancing their performance in resilient power electronics systems. Full article

Special vehicle detection in intelligent surveillance, emergency rescue, and reconnaissance faces significant challenges in accuracy and robustness under complex environments, necessitating advanced detection algorithms for critical applications. This paper proposes HSF-DETR (Hypergraph Spatial Feature DETR), integrating four innovative modules: a Cascaded Spatial Feature Network (CSFNet) backbone with Cross-Efficient Convolutional Gating (CECG) for enhanced long-range detection through hybrid state-space modeling; a Hypergraph-Enhanced Spatial Feature Modulation (HyperSFM) network utilizing hypergraph structures for high-order feature correlations and adaptive multi-scale fusion; a Dual-Domain Feature Encoder (DDFE) combining Bipolar Efficient Attention (BEA) and Frequency-Enhanced Feed-Forward Network (FEFFN) for precise feature weight allocation; and a Spatial-Channel Fusion Upsampling Block (SCFUB) improving feature fidelity through depth-wise separable convolution and channel shift mixing. Experiments conducted on a self-built special vehicle dataset containing 2388 images demonstrate that HSF-DETR achieves mAP50 and mAP50-95 of 96.6% and 70.6%, respectively, representing improvements of 3.1% and 4.6% over baseline RT-DETR while maintaining computational efficiency at 59.7 GFLOPs and 18.07 M parameters. Cross-domain validation on VisDrone2019 and BDD100K datasets confirms the method’s generalization capability and robustness across diverse scenarios, establishing HSF-DETR as an effective solution for special vehicle detection in complex environments. Full article

Sign language is a complex and dynamic visual language that requires the coordinated movement of various body parts, such as the hands, arms, and limbs—making it an ideal application domain for sensor networks to capture and interpret human gestures accurately. To address the intricate task of precise and expedient SLR from raw videos, this study introduces a novel deep learning approach by devising a multimodal framework for SLR. Specifically, feature extraction models are built based on two modalities: skeleton and RGB images. In this paper, we firstly propose a Multi-Stream Spatio-Temporal Graph Convolutional Network (MSGCN) that relies on three modules: a decoupling graph convolutional network, a self-emphasizing temporal convolutional network, and a spatio-temporal joint attention module. These modules are combined to capture the spatio-temporal information in multi-stream skeleton features. Secondly, we propose a 3D ResNet model based on deformable convolution (D-ResNet) to model complex spatial and temporal sequences in the original raw images. Finally, a gating mechanism-based Multi-Stream Fusion Module (MFM) is employed to merge the results of the two modalities. Extensive experiments are conducted on the public datasets AUTSL and WLASL, achieving competitive results compared to state-of-the-art systems. Full article

Deep learning-based hyperspectral target detection (HTD) methods often face the challenge of insufficient prior information and difficulty in distinguishing local and global spectral differences. To address these problems, we propose a self-supervised framework that leverages contrastive learning to reduce dependence on prior knowledge, called the Gated Dual-Path Network with Contrastive Learning (GDPNCL). In this work, we introduce a novel sample augmentation strategy for deep network training, in which each pixel in the scene is processed using a dual concentric window to generate positive and negative samples. In addition, a Gated Dual-Path Network (GDPN) is proposed to effectively extract and discriminate local and global information from the spectra. Moreover, to mitigate the issue of false negative samples within the same class and to enhance the contrast between negative samples, we design a Weight Information Noise contrastive estimation (WIN) loss. The loss leverages the relationship between samples to further help the model learn representations that effectively distinguish targets from diverse backgrounds. Finally, the trained encoder is subsequently employed to extract features from the prior spectrum and test pixels, and the cosine similarity between them serves as the detection metric. Comprehensive experiments on four challenging hyperspectral datasets demonstrate that the GDPNCL outperforms state-of-the-art methods, highlighting its effectiveness and robustness in HTD. Full article

Diuron (DU) is a widely used phenylurea herbicide designed to inhibit weed growth, but its high toxicity and prolonged half-life contribute significantly to environmental contamination. The majority of electrochemical (EC) sensors typically rely on a single response signal for the detection of DU, rendering them highly susceptible to interference from variable background noise in complex environments, thereby reducing the selectivity and robustness. By integrating molecularly imprinted polymer (MIP) with a ratiometric strategy, the aforementioned issues could be solved. In this study, a novel signal on-off ratiometric MIP-EC sensor was developed based on the MXene/PEI-MWCNTs nanocomposite for the detection of DU. Positively charged PEI-MWCNTs was used as an interlayer spacer and embedded into negatively charged MXene by a simple electrostatic self-assembly method. This effectively prevented the agglomeration of MXene and enhanced its electrocatalytic performance. The MIP was synthesized via electropolymerization with DU serving as the template molecule and the selectivity was enhanced by leveraging the gate effect of MIP. Subsequently, a ratiometric MIP-EC sensor was designed by introducing [Fe(CN)₆]^3−/4− into the electrolyte solution as an internal reference. Additionally, the current ratio signal (I_DU/I_[Fe(CN)6]^3−/4−) and DU concentration exhibited a good linear relationship within the range of 0.1 to 100 µM, with a limit of detection (LOD) of 30 nM (S/N = 3). In comparison with conventional single-signal MIP-EC sensing, the developed ratiometric MIP-EC sensing demonstrates superior reproducibility and accuracy. At the same time, the proposed sensor was successfully applied to the quantitative analysis of DU residues in soil samples, yielding highly satisfactory results. Full article

Rain streaks degrade the quality of optical images and seriously affect the effectiveness of subsequent vision-based algorithms. Although the applications of a convolutional neural network (CNN) and self-attention mechanism (SA) in single image deraining have shown great success, there are still unresolved issues regarding the deraining performance and the large computational load. The work in this paper fully coordinates and utilizes the advantages between CNN and SA and proposes a hybrid content-aware deraining network (CAD) to reduce complexity and generate high-quality results. Specifically, we construct the CADBlock, including the content-aware convolution and attention mixer module (CAMM) and the multi-scale double-gated feed-forward module (MDFM). In CAMM, the attention mechanism is used for intricate windows to generate abundant features and simple convolution is used for plain windows to reduce computational costs. In MDFM, multi-scale spatial features are double-gated fused to preserve local detail features and enhance image restoration capabilities. Furthermore, a four-token contextual attention module (FTCA) is introduced to explore the content information among neighbor keys to improve the representation ability. Both qualitative and quantitative validations on synthetic and real-world rain images demonstrate that the proposed CAD can achieve a competitive deraining performance. Full article

Wireless Sensor Networks (WSNs) consist of distributed sensor nodes that collect and transmit environmental data, often in resource-constrained and unsecured environments. These characteristics make WSNs highly vulnerable to various security threats. To address this, the objective of this research is to design and evaluate a deep learning-based Intrusion Detection System (IDS) that is both accurate and efficient for real-time threat detection in WSNs. This study proposes a hybrid IDS model combining one-dimensional Convolutional Neural Networks (Conv1Ds), Gated Recurrent Units (GRUs), and Self-Attention mechanisms. A Conv1D extracts spatial features from network traffic, GRU captures temporal dependencies, and Self-Attention emphasizes critical sequence components, collectively enhancing detection of subtle and complex intrusion patterns. The model was evaluated using the WSN-DS dataset and demonstrated superior performance compared to traditional machine learning and simpler deep learning models. It achieved an accuracy of 98.6%, precision of 98.63%, recall of 98.6%, F1-score of 98.6%, and an ROC-AUC of 0.9994, indicating strong predictive capability even with imbalanced data. In addition to centralized training, the model was tested under cooperative, node-based learning conditions, where each node independently detects anomalies and contributes to a collective decision-making framework. This distributed approach improves detection efficiency and robustness. The proposed IDS offers a scalable and resilient solution tailored to the unique challenges of WSN security. Full article

Aiming at the problems of leakage and misdetection caused by insufficient multi-scale feature extraction and an excessive amount of model parameters in bridge defect detection, this paper proposes the AMSF-Pyramid-YOLOv11n model. First, a Cooperative Optimization Module (COPO) is introduced, which consists of the designed multi-level dilated shared convolution (FPSharedConv) and a dual-domain attention block. Through the joint optimization of FPSharedConv and a CGLU gating mechanism, the module significantly improves feature extraction efficiency and learning capability. Second, the Unified Global-Multiscale Bottleneck (UGMB) multi-scale feature pyramid designed in this study efficiently integrates the FCGL_MANet, WFU, and HAFB modules. By leveraging the symmetry of Haar wavelet decomposition combined with local-global attention, this module effectively addresses the challenge of multi-scale feature fusion, enhancing the model’s ability to capture both symmetrical and asymmetrical bridge defect patterns. Finally, an optimized lightweight detection head (LCB_Detect) is employed, which reduces the parameter count by 6.35% through shared convolution layers and separate batch normalization. Experimental results show that the proposed model achieves a mean average precision (mAP@0.5) of 60.3% on a self-constructed bridge defect dataset, representing an improvement of 11.3% over the baseline YOLOv11n. The model effectively reduces the false positive rate while improving the detection accuracy of bridge defects. Full article

This paper investigates the short-circuit characteristics of 1.2 kV symmetrical and asymmetrical trench-gate SiC MOSFETs. Based on the self-designed short-circuit test platform, single and repetitive short-circuit tests were carried out to characterize the short-circuit capability of the devices under different electrical stresses through the short-circuit withstanding time (SCWT). Notably, the asymmetric trench structure exhibited a superior short-circuit capability under identical test conditions, achieving a longer SCWT compared to its symmetrical counterpart. Moreover, TCAD was used to model the two devices and fit the short-circuit current waveforms to study the difference in short-circuit characteristics under different conditions. For the degradation of the devices after repetitive short-circuit stresses, repetitive short-circuit pulse experiments were conducted for the two groove structures separately. The asymmetric trench devices show a positive Vth drift, increasing on-resistance, increasing C_gs and C_ds, and decreasing C_gd, while the symmetric trench devices show a negative Vth drift, decreasing on-resistance, and inverse variation in capacitance parameters. Both blocking voltages are degraded, but the gate-source leakage current remains low, indicating that the gate oxide has not yet been damaged. Full article

This study systematically investigates the mechanism by which total ionizing dose (TID) affects the lifetime degradation of NMOS devices induced by hot-carrier injection (HCI). Experiments involved Cobalt-60 (Co-60) gamma-ray irradiation to a cumulative dose of 500 krad (Si), followed by 168 h annealing at 100 °C to simulate long-term stability. However, under HCI stress conditions (V_D = 2.7 V, V_G = 1.8 V), irradiated devices show a 6.93% increase in threshold voltage shift (ΔV_th) compared to non-irradiated counterparts. According to the IEC 62416 standard, the lifetime degradation of irradiated devices induced by HCI stress is only 65% of that of non-irradiated devices. Conversely, when the saturation drain current (I_Dsat) degrades by 10%, the lifetime doubles compared to non-irradiated counterparts. Mechanistic analysis demonstrates that partial neutralization of E’ center positive charges at the gate oxide interface by hot electrons weakens the electric field shielding effect, accelerating ΔV_th drift, while interface trap charges contribute minimally to degradation due to annealing-induced self-healing. The saturation drain current shift degradation primarily correlates with electron mobility variations. This work elucidates the multi-physics mechanisms through which TID impacts device reliability and provides critical insights for radiation-hardened design optimization. Full article

Three-dimensional semantic segmentation plays a crucial role in accurately identifying terrain features and objects by effectively extracting 3D spatial information from the environment. However, the inherent sparsity of point clouds and unclear terrain boundaries in outdoor mining environments significantly complicate the recognition process. To address these challenges, we propose a novel 3D semantic segmentation network that incorporates spatiotemporal feature aggregation. Specifically, we introduced the Gated Spatiotemporal Clue Encoder, which extracts spatiotemporal context from historical multi-frame point cloud data and combines it with the current scan frame to enhance feature representation. Additionally, the Spatiotemporal Feature State Space Module is proposed to efficiently model long-term spatiotemporal features while minimizing computational and memory overhead. Experimental results show that the proposed method outperforms the baseline model, achieving a 2.1% improvement in mIoU on the self-constructed TZMD_NUC outdoor mining dataset and a 1.9% avg improvement on the public SemanticKITTI dataset. Moreover, the method simultaneously improves computational efficiency, making it more suitable for real-time applications in complex, real-world mining environments. These results validate the effectiveness of the proposed method, offering a promising solution for 3D semantic segmentation in complex, real-world mining environments, where computational efficiency and accuracy are both critical. Full article

Data complexity directly affects the dynamics of complex systems, which in turn influences the accuracy and robustness of forecasting models. However, the load data exhibit complex features such as self-similarity, long-term memory, randomness, and chaos. This study aims to quantify and evaluate the complexity features of natural gas loads and to develop a multi-step-ahead forecasting model that integrates data decomposition and ensemble deep learning while considering these complexity features. Firstly, the complexity features of the series are quantified by rolling the fractal dimension, Hurst exponent, sample entropy, and maximum Lyapunov exponent. The analysis contributes to understanding data characteristics and provides information on complex features. Secondly, the ensemble learning eXtreme Gradient Boosting (XGBoost) can effectively screen complexity features and meteorological factors. Concurrently, variational mode decomposition (VMD) provides frequency-domain decomposition capability, while the gated recurrent unit (GRU) captures long-term dependencies. This synergy enables effective learning of local features and long-term temporal patterns, resulting in precise predictions. The results indicate that compared to other models, the proposed method (XGBoost-VMD-GRU considering complex features) demonstrates superior performance in forecasting, with R² of 0.9922, 0.9860, and 0.9679 for one-step, three-step, and six-step prediction, respectively. This study aims to bring innovative ideas to load forecasting by integrating complex features into the decomposition forecasting framework. Full article

Stepper motors are used in satellites for various drive operations that are achieved by custom designs. This paper presents a stepper motor driver for satellite systems. It takes rotor position and phase current as inputs and employs a current subdivision method with back-propagation neural network (BPNN) to achieve constant current control of the motor. The driver can ensure the smooth operation and the positioning accuracy of the motor with a filter wheel that is 0.1944 $\mathrm{kg}·{\mathrm{m}}^2$ in the moment of inertia and satisfy self-adaption of the load without system parameter identification. Compared to the previous scheme, the proposed scheme can reduce the power consumption by about $21.15\%$ when the motor runs at 2 $\mathrm{r}/\mathrm{s}$, which is beneficial to the reduction in the size and the mass of some power supply modules. The performances of the developed driver are implemented on a field programmable gate array (FPGA) circuit board. The experimental results are conducted to verify the claims presented. The proposed scheme can be extended to other stepper motor systems with large moment of inertia loads within spacecraft. Full article