Gesture detection based on radio frequency signals has gained increasing popularity in recent years due to several benefits it has brought, such as eliminating the need to carry additional devices and providing better privacy. In traditional methods, significant breakthroughs have been made to improve recognition accuracy and scene robustness, but the limited computing power of edge devices (the first-level equipment to receive signals) and the requirement of fast response for detection have not been adequately addressed. In this article, we propose a lightweight Wi-Fi gesture recognition system, referred to as WiFine, which is designed and implemented for deployment on low-end edge devices without the use of any additional high-performance services in the process. Toward these goals, we first design algorithms for phase difference selection and amplitude enhancement, respectively, to tackle the problem of data drift caused by user change. Then, we design a cross-dimension fusion method to extract features of finer granularity from information of different dimensions, thus solving the precision problem of feature granularity. Finally, we design a lightweight neural network architecture by leveraging redundancy to reduce computational cost while ensuring satisfactory recognition accuracy. Extensive experimental results show that the proposed system achieves fast recognition of various actions with an accuracy up to 96.03% in 0.19 seconds.

Power fault monitoring based on acoustic waves has gained a great deal of attention in industry. Existing methods for fault diagnosis typically collect sound signals on site and transmit them to a back-end server for analysis, which may fail to provide a real-time response due to transmission packet loss and latency. However, the limited computing power of edge devices and the existing methods for feature extraction pose a significant challenge to performing diagnosis on the edge. In this paper, we propose a fast Lightweight Fault Diagnosis method for power transformers, referred to as LightFD, which integrates several technical components. Firstly, before feature extraction, we design an asymmetric Hamming-cosine window function to reduce signal spectrum leakage and ensure data integrity. Secondly, we design a multidimensional spatio-temporal feature extraction method to extract acoustic features. Finally, we design a parallel dual-layer, dual-channel lightweight neural network to realize the classification of different fault types on edge devices with limited computing power. Extensive simulation and experimental results show that the diagnostic precision and recall of LightFD reach 94.64% and 95.33%, which represent an improvement of 4% and 1.6% over the traditional SVM method, respectively.

In view of the characteristics of modern flight control system with few fault data and many fault types, it is difficult to rely on deep learning for accurate fault diagnosis. In this article, a fault diagnosis method of flight control system based on Triplet Network was proposed and applied to the bearing data set of Case Western Reserve University and the Pre-flight Built-in-test(PBIT) fault data of a certain type of aircraft. For the bearing data set, the signals are firstly transferred into the frequency domain by wavelet packet decomposition. Then, build the Triplet Network model, and the network training is carried out in the form of triplet input. The model compare the similarity of characteristics of similar faults and different faults, and optimize the parameters to achieve the optimal classification effect. The PBIT fault data of flight control system is processed and network training is carried out to realize the fault diagnosis function. Aiming at small samples, I divided experimental data sets with different number of training samples to observe the diagnostic effect of the model, and compared with traditional deep learning models respectively. The experiment verified the unique advantages of Triplet Network model in fault diagnosis under small sample conditions, and the accuracy was significantly better than the traditional deep learning method.