Bolts are important components on transmission lines, and the timely detection and exclusion of their abnormal conditions are imperative to ensure the stable operation of transmission lines. To accurately identify bolt defects, we propose a bolt defect identification method incorporating an attention mechanism and wide residual networks. Firstly, the spatial dimension of the feature map is compressed by the spatial compression network to obtain the global features of the channel dimension and enhance the attention of the network to the vital information in a weighted way. After that, the enhanced feature map is decomposed into two one-dimensional feature vectors by embedding a cooperative attention mechanism to establish long-term dependencies in one spatial direction and preserve precise location information in the other direction. During this process, the prior knowledge of the bolts is utilized to help the network extract critical feature information more accurately, thus improving the accuracy of recognition. The test results show that the bolt recognition accuracy of this method is improved to 94.57% compared with that before embedding the attention mechanism, which verifies the validity of the proposed method.

Cooperative spectrum sensing (CSS) has been considered as a powerful approach to improve the utilization of scarce radio spectrum resources. However, spectrum sensing data falsification (SSDF) can hugely degrade the achievable detection accuracy of the primary user (PU) channel status in cognitive radio (CR) networks and thus requires learning from past CR network environments. Using the supervised learning (SL) method, a large number of labels about the real state of the channel availability need to be acquired. In a practical setting, however, obtaining off-the-shelf label data is a challenging undertaking because it necessitates cooperation among PUs and secondary users (SUs) and increases communication overhead in CR networks. Motivated by this, we solve the issue of label data scarcity in CR networks in this paper, and propose a semi-supervised learning-enabled two-stage framework for CSS against SSDF attack, in which combines the superior performance of semi-supervised support vector machine (S3VM) and the fast convergence of K-means. At last, simulation results demonstrate that S3VM is equipped with a greater detection performance than support vector data description (SVDD), and the same detection performance as support vector machine (SVM), especially it also the robustness and excellent performance using a small amount of labeled data.

Bird's nest defect is an important cause of transmission line faults. To achieve accurate detection of bird nest defects in complex scenarios, a bird nest defect detection model for transmission lines was proposed that combines domain knowledge and occlusion reasoning networks. On the one hand, the model utilized the domain knowledge of the location of the bird's nest, using edge detection to obtain tower area information to constrain the location of candidate frames. This helps to reduce the false detection caused by complex backgrounds. On the other hand, on the basis of analyzing the occlusion characteristics of bird nests, the model employed occlusion reasoning networks that randomly erase features at the feature level to simulate the occlusion of bird nests in real scenes and improve the model's detection capability for occluded targets. Additionally, a multi‐scale feature fusion algorithm was designed in this paper to adapt the model to the scale variations of bird nests in aerial images. Experimental results demonstrate that the model outperforms advanced target detection models and other bird nest defect detection methods, with an AP50 of 78.8% and an AR10 of 72.4% for defect detection.

To precisely delineate the contours of insulators in complex transmission line images obtained from Unmanned Aerial Vehicle (UAV) inspections and thereby facilitate subsequent defect analysis, this study proposes an instance segmentation framework predicated upon an enhanced SOLOv2 model. The proposed framework integrates a preprocessed edge channel, generated through the Non-Subsampled Contourlet Transform (NSCT), which augments the model’s capability to accurately capture the edges of insulators. Moreover, the input image resolution to the network is heightened to 1200 × 1600, permitting more detailed extraction of edges. Rather than the original ResNet + FPN architecture, the improved HRNet is utilized as the backbone to effectively harness multi-scale feature information, thereby enhancing the model’s overall efficacy. In response to the increased input size, there is a reduction in the network’s channel count, concurrent with an increase in the number of layers, ensuring an adequate receptive field without substantially escalating network parameters. Additionally, a Convolutional Block Attention Module (CBAM) is incorporated to refine mask quality and augment object detection precision. Furthermore, to bolster the model’s robustness and minimize annotation demands, a virtual dataset is crafted utilizing the fourth-generation Unreal Engine (UE4). Empirical results reveal that the proposed framework exhibits superior performance, with AP0.50 (90.21%), AP0.75 (83.34%), and AP[0.50:0.95] (67.26%) on a test set consisting of images supplied by the power grid. This framework surpasses existing methodologies and contributes significantly to the advancement of intelligent transmission line inspection.

The widespread use of virtual reality (VR) technology is transforming the field of education and training. This study explores the potential of VR in education, with a special focus on immersion, presence and immersion, and the critical role of first-person perspective when interaction is absent and viewing position is fixed. The experimental results show that VR can improve students' concentration and enthusiasm for learning, and is crucial for developing hands-on skills and knowledge construction. In addition, we propose a model based on Spearman's correlation analysis to evaluate the influencing factors of VR experience. In order to improve the quality of teaching and learning, this study introduces a predictive model for evaluating VR experience based on the mechanism of multi-head attention, and the performance effect of the proposed model is verified by the collected experimental data. This study provides strong support for further utilizing VR to improve education. Finally, this study proposes the design and application scenarios of an immersive content recording device for educational content based on the research, to build and test functional prototypes, and to try new ideas for the production and tradition of VR educational content.