Energy recharging is one of the most important issues in wireless rechargeable sensor networks (WRSNs). Many energy-recharging algorithms have been proposed using multiple mobile chargers. However, the number of mobile chargers that significantly impact the network lifetime of the given WRSNs still can be improved. This paper proposes an energy recharging algorithm, called PLPR , which uses the mobile charger to recharge the sensors and uses the super mobile charger to recharge the mobile chargers, aiming at minimizing the number of mobile chargers and super mobile chargers while achieving the purpose of sustainable survival of all sensors. Initially, the proposed PLPR determines the number of mobile chargers, clusters the sensors into several groups, and constructs the initial path for each mobile charger in each cluster. Based on these paths, the proposed PLPR further reduces the path length in each cluster and improves the recharging efficiency of the mobile charger. To satisfy the perpetual lifetime of the mobile chargers, the PLPR further constructs an initial path, reduces the path length, and schedules the recharging task of super mobile chargers. Performance evaluations reveal that the proposed PLPR outperforms existing energy recharging algorithms in terms of average energy consumption, total recharging time, charging efficiency, traveling distance of mobile charger, fairness indices, SD of recharging efficiency and average waiting time for a given WRSN.

In the manufacturing process involving grinding wheels, challenges in fine-tuning grinding machines are typically addressed by craftsmen through subjective observations of sparks and sounds. However, most current anomaly detection methods mainly aim at a single modality, whereas existing multimodal methods cannot effectively cope with a common issue. To address this, this paper introduces an innovative mechanism, AI-Based Multimodal Anomaly Detection (AMAD), designed to optimize the efficiency and accuracy of grinding wheel production lines. The proposed AMAD includes data preprocessing and multimodal anomaly detection, accurately identifying anomalies in grinding wheel operation videos. In the data preprocessing phase, the proposed AMAD utilizes Mel Frequency Cepstral Coefficients (MFCC) and AutoEncoder for audio processing and segmentation for video processing. In the multimodal anomaly detection phase, the proposed AMAD employs Convolutional Neural Networks (CNN) for audio analysis and Convolutional Long Short-Term Memory (ConvLSTM) for video analysis. By combining both audio and video modalities, the proposed AMAD effectively predicts whether the input video represents normal or abnormal grinding wheel operations. This multimodal approach not only improves the accuracy of anomaly detection but also enhances the robustness of the system. Simulation results demonstrate that the proposed AMAD significantly improves performance in anomaly detection in terms of precision, recall, and F1-Score.

As the elderly population continues to grow, timely health monitoring and emergency response for the elderly become particularly crucial. However, traditional wireless sensor networks face challenges such as transmission delays, high energy consumption, network congestion, and packet collisions during emergencies, which impact the health and safety of the elderly. To address these issues, this paper proposes a novel multi-layer topology control mechanism, called Improving Emergent Events Transmission (IEET), which integrates tree and mesh topologies while applying channel selection and subrated connection strategies. The tree topology effectively constructs a distinct path for emergent transmission, filtering out channels susceptible to contentions and collisions. It employs a subrated connection scheme to adjust the connection interval for transmitting emergency messages, thus reducing transmission delay and energy consumption. Additionally, the mesh topology addresses traffic congestion near the gateway, reducing packet collisions and improving the reliability of packet transmission. As a result, emergent information can be swiftly transmitted to the gateway, mitigating the impact of emergencies on the elderly. Simulation results demonstrate that the proposed IEET outperforms existing mechanisms in terms of average packet latency, network lifetime, and energy consumption for sensors in Bluetooth Low Energy (BLE) networks.