Insulator defects in transmission lines can threaten the safe and stable operation of the power system. Therefore, insulator defect detection plays a crucial role in the electricity sector. Currently, You Only Look Once (YOLO) algorithm is widely used in insulator fault detection. However, insulator defect detection using YOLO still faces the double challenges of detection precision and real-time performance. Therefore, we construct a lightweight model for insulator defect detection named coordinate attention mechanism (CAM) and feature channel shuffle operation (CSO) YOLO (CACS-YOLO). By introducing the CAM and CSO in the original YOLOv8m, we improve the detection precision, and reduce the parameters of model, compared with existing insulator defect detection models. Meanwhile, in order to solve the problem of insufficient data and cope with different weather conditions, we use synthetic weather algorithms for data enhancement, and construct a Synthetic Foggy and Rainy Insulator Dataset (SFRID). The experimental results show that the mean average precision of CACS-YOLO is 96.9% and the parameters of proposed model is 27.44M. These outcomes show the high-precision and lightweight of our proposed model in insulator defect detection. The source code and dataset are available on Github.

Radar-based human activity recognition (HAR) provides a non-contact method for many scenarios, such as human–computer interaction, smart security, and advanced surveillance with privacy protection. Feeding radar-preprocessed micro-Doppler signals into a deep learning (DL) network is a promising approach for HAR. Conventional DL algorithms can achieve high performance in terms of accuracy, but the complex network structure causes difficulty for their real-time embedded application. In this study, an efficient network with an attention mechanism is proposed. This network decouples the Doppler and temporal features of radar preprocessed signals according to the feature representation of human activity in the time–frequency domain. The Doppler feature representation is obtained in sequence using the one-dimensional convolutional neural network (1D CNN) following the sliding window. Then, HAR is realized by inputting the Doppler features into the attention-mechanism-based long short-term memory (LSTM) as a time sequence. Moreover, the activity features are effectively enhanced using the averaged cancellation method, which improves the clutter suppression effect under the micro-motion conditions. Compared with the traditional moving target indicator (MTI), the recognition accuracy is improved by about 3.7%. Experiments based on two human activity datasets confirm the superiority of our method compared to traditional methods in terms of expressiveness and computational efficiency. Specifically, our method achieves an accuracy close to 96.9% on both datasets and has a more lightweight network structure compared to algorithms with similar recognition accuracy. The method proposed in this article has great potential for real-time embedded applications of HAR.

In this work, using Si interface passivation layer (IPL) we present the electrical characteristics of TaN/HfO₂/GaAs both p-and n-MOSFET made on GaAs substrates with excellent electrical and reliability characteristics, thin EOT (~2.3-3.0nm), low frequency dispersion (< 5%) and high maximum mobility (1213 cm²/V-s) with high temperature PMA for n-MOSFET on undoped GaAs. Good inversion behavior with low D_it on lightly doped p-type GaAs has been obtained. P-channel GaAs high-k MOSFETs with excellent peak mobility have also been demonstrated

In the context of high-dynamic electronic warfare, improving the precision of radar active jamming recognition algorithms under small sample conditions has become a research hotspot. When confronted with scarcity of labeled data and low jamming-to-noise ratio (JNR), existing intelligent models struggle to extract sufficient discriminative features, leading to suboptimal recognition accuracy. Particularly in the current environment of diverse and variable jamming types, these models exhibit inadequate robustness in jamming differentiation. To address these issues, this paper integrates transfer learning (TL) and dual graph convolutional network (DGCN) to propose a few-shot learning (FSL) method for radar active deception jamming recognition. Firstly, this method utilizes the large mini-ImageNet dataset to assist in pre-training a basic FSL model, obtaining abundant transferable general knowledge while excavating specific information about jamming from limited annotated samples through TL, thereby enhancing the generalization capability and optimizing efficiency of model. Subsequently, to further improve the robustness of model in recognizing diverse and complex jamming types, a DGCN structure is integrated into the fine-tuning of the FSL model based on deep convolutional architecture. It models the non-local correlations among jamming using a feature graph and distribution graph, facilitating the effective propagation of inter-class knowledge interaction and label information through message aggregation and propagation, making jamming features more similar within classes and more distinguishable between classes. Finally, the features extracted by the deep convolutional structure and DGCN are fused to obtain more comprehensive and enriched feature representation for accurate jamming recognition. Experimental results on typical jamming datasets demonstrate the effectiveness and superiority of the proposed recognition method under the condition of small sample and low JNRs.

In the current fully open and highly dynamic electronic countermeasures environment, acquiring sufficient jamming label priors is particularly challenging. Especially when the labeled samples are extremely limited, existing intelligent recognition models for radar active jamming struggle to effectively learn discriminative features, resulting in inaccurate and unstable recognition results. Therefore, this letter proposes a visual-text alignment network (VTANet) that introduces the text modality to reused the label prior information, thereby leveraging labeling knowledge to enhance jamming recognition accuracy under few-shot conditions. During training, VTANet utilizes a text feature encoding module to encode text constructed based on label priors. Through a contrastive learning strategy, these obtained text features are then used to guide the visual feature encoding module to learn more discriminative visual time-frequency (TF) representations. Experimental results show that reusing label priors through the text modality significantly improves the intra-class compactness and inter-class separability of visual TF features. With the jamming-to-noise ratio of 5dB and only 2 labeled samples per jamming type, VTANet achieves a recognition accuracy of over 90%, improving by more than 5% compared to existing methods, thus demonstrating its superiority.

The Controller Area Network (CAN) is the de facto industry standard of In-Vehicle Network (IVN) for connecting Electronic Control Units (ECUs). In recent years, related researchers have proposed various in-vehicle network security schemes to protect CAN bus. By leveraging the physical characteristics of signals sent by ECUs, ECU identification methods are proposed to implement intrusion detection system at the physical transmission layer. Voltage-based physical fingerprint techniques have gained significant attention in this research field. Considering the resource-constrained embedded environments of IVN, various methods attempt to reduce the resource requirements of physical fingerprint-based ECU identification methods. In this paper, a lightweight voltage-based fingerprint intrusion detection system is proposed, which achieves an identification accuracy of over 99% under conditions of low sampling rates, short signal segments, and a small feature set through comprehensive experiments on both CAN prototypes and a rich dataset of ten actual vehicles.