Safety monitoring of power operations in substations is crucial for accident prevention. However, traditional methods such as wearable devices and video surveillance suffer from limitations including high costs and reliance on lighting conditions. A solution that integrates millimeter-wave radar with deep learning ensures operational compliance by high precision gesture detection. This paper proposes RoPEHAR, a human activity recognition system based on millimeter-wave radar, which combines traditional transformer architecture with rotary positional encoding, specifically designed for human posture recognition in indoor industrial environments. To reduce interference from the coupling of human and instrument signals and noise in electrical scenarios, RoPEHAR introduces a hybrid filtering pipeline that combines hierarchical SNR denoising with enhanced DBSCAN clustering to accurately segment the point cloud data of limbs and instruments. The core innovation lies in the introduction of a spatiotemporal Informer, Roformer. It enhances the 3D-space vector information about data points through dynamic rotary positional encoding. This system effectively models limb motion trajectories. Experiments demonstrate that RoPEHAR achieves high-precision performance, reaching an accuracy of 95.8%, enabling real-time and reliable activity recognition for substation safety monitoring.

Accurate and scalable indoor localization for unmanned aerial vehicles (UAVs) is essential for Internet of Things (IoT) applications such as autonomous logistics, infrastructure inspection, and emergency response in GPS-denied environments. However, traditional methods often struggle with cost, deployment complexity, and sensitivity to environmental dynamics, limiting their practicality for large-scale IoT scenarios. This paper presents a method in which Channel State Information (CSI) from low-cost IoT sensors enables robust, device-free 3D UAV localization while optimizing accuracy, sensor adaptability, and data efficiency. We propose CiUAV, leveraging CSI captured by ESP32-S3 sensors, with a Robust CSI Signal Enhancement (RCSE) framework integrating Dynamic AGC Compensation (DAC) and Adaptive Noise Suppression and Outlier Removal (ANSOR), alongside a Sensor-in-Sample (SiS) multi-objective optimization model for adaptive multi-sensor fusion. Experimental evaluations in realistic indoor settings achieve a 3D root mean squared error (RMSE) of 0.2659 meters, outperforming baselines by up to 35% in accuracy and 50% in data efficiency. CiUAV offers a lightweight, scalable, and infrastructure-compatible solution for future IoT-enabled UAV systems.

Ensuring personnel safety during power station inspections is a critical yet challenging task due to inherent hazards in such environments. Traditional monitoring methods, including wearable devices and video surveillance, suffer from user discomfort, limited visibility, and high deployment costs. To overcome these limitations, this article proposes PowerHAR, a device-free framework for recognizing power inspection activities based on WiFi channel state information (CSI) acquired from custom-designed ESP32 internet of things (IoT) sensors. PowerHAR introduces a spatio-temporal feature distribution-based power operation recognition network, comprising a transformer-based preprocessing module capable of effectively handling variable-length CSI sequences, and a spatio-temporal extraction module that integrates convolutional operations with multihead self-attention mechanisms for comprehensive feature fusion. By leveraging mutual CSI sensing among distributed sensors, PowerHAR provides robust and accurate recognition of power inspection activities without requiring additional hardware infrastructure. Experimental validation demonstrates that PowerHAR significantly surpasses existing baseline methods, confirming its high reliability and practicality in safety-critical industrial scenarios.

WiFi Indoor localization plays a crucial role in an emerging application domain for tracking indoor people, however, the serious issue is that the WiFi signals from access points (APs) vary greatly over time and the deployment structure of APs may be changed, for example, some APs are replaced or removed over time, which cause localization accuracy reduced. To solve this problem, this paper presents WiLoc, a Long-term WiFi localization with Lightweight Siamese Neural Network. This method introduces a Siamese neural encoder-based framework to learn the similarity between three inputs, where the Siamese network only consists of three linear layers without any convolutional layer or transformer. The triplet loss function is utilized to supervise the training of the feature encoder. Then, the encodings from this encoder are input to K-Nearest Neighbors (KNN) to predict the user’s positions. Extensive experiments on the UJI dataset, show the proposed WiLoc can effectively relieve the degradation of localization accuracy over time compared to the state-of-the-art algorithms, the degradation is reduced from 51% to 12.1%, and the average localization error is 2.06 m.

Safety monitoring of power operations in power stations is crucial for preventing accidents and ensuring stable power supply. However, conventional methods such as wearable devices and video surveillance have limitations such as high cost, dependence on light, and visual blind spots. WiFi-based human pose estimation is a suitable method for monitoring power operations due to its low cost, device-free, and robustness to various illumination conditions. In this paper, a novel Channel State Information (CSI)-based pose estimation framework, namely PowerSkel, is developed to address these challenges. PowerSkel utilizes self-developed CSI sensors to form a mutual sensing network and constructs a CSI acquisition scheme specialized for power scenarios. It significantly reduces the deployment cost and complexity compared to the existing solutions. To reduce interference with CSI in the electricity scenario, a sparse adaptive filtering algorithm is designed to preprocess the CSI. CKDformer, a knowledge distillation network based on collaborative learning and self-attention, is proposed to extract the features from CSI and establish the mapping relationship between CSI and keypoints. The experiments are conducted in a real-world power station, and the results show that the PowerSkel achieves high performance with a PCK@50 of 96.27%, and realizes a significant visualization on pose estimation, even in dark environments. Our work provides a novel low-cost and high-precision pose estimation solution for power operation.

The concentration of dissolved gases in transformer oil can be utilized to diagnose faults in transformers. However, substandard online monitoring data may lead to inaccurate fault diagnosis outcomes, resulting in severe repercussions. Hence, this study presents a novel approach for anomaly detection in dissolved gas online monitoring data in transformer oil using stacking ensemble learning. Firstly, a sliding time window is employed to preprocess the monitoring data and generate a dataset consisting of time series monitoring data. Subsequently, evaluation metrics and diversity measures are applied to select distinct base learners and a meta-learner for the stacking model. This approach amalgamates the strengths and disparities of various learners. Lastly, comparative analysis of case studies demonstrates the effectiveness of the proposed method in distinguishing different types of anomalies in dissolved gas online monitoring data, exhibiting superior performance in terms of accuracy, F1 score, and area under curve(AUC).

Low-resolution infrared-based human activity recognition (HAR) attracted enormous interests due to its low cost and private. In this article, a novel semi-supervised cross-domain neural network (SCDNN) based on$8\times8$low-resolution infrared sensor is proposed for accurately identifying human activity despite changes in the environment at a low cost. The SCDNN consists of feature extractor, domain discriminator, and label classifier. In the feature extractor, the unlabeled and minimal labeled target domain data are trained for domain adaptation to achieve a mapping of the source domain and target domain data. The domain discriminator employs the unsupervised learning to migrate data from the source domain to the target domain. The label classifier obtained from training the source domain data improves the recognition of target domain activities due to the semi-supervised learning utilized in training the target domain data. Experimental results show that the proposed method achieves 92.12% accuracy for recognition of activities in the target domain by migrating the source and target domains. The proposed approach adapts superior to cross-domain scenarios compared to the existing deep learning methods, and it provides a low cost yet highly adaptable solution for cross-domain scenarios.