Fault diagnosis of insulators in aerial images is an essential task of power line inspection to maintain the reliability, safety, and sustainability of power transmission. This paper develops a novel method for intelligent diagnosis of electrical insulators based on deep learning, termed Box-Point Detector, which consists of a deep convolutional neural network followed by two parallel branches of convolutional heads. These two branches are utilized to locate the fault region and estimate insulator endpoints, which presents a new representation for insulator faults. Endpoints of the faulty insulator string can provide detailed and correlative information for enhancing the diagnosis capability of component-dependent faults that occur on component bodies. The proposed Box-Point Detector implements all predictions including region and endpoint into one network thus forms an efficient end-to-end structure, and adopts a smaller downsampling ratio to generate high resolution feature-maps in order to preserve more original information for small size faults. Experimental results indicate that Box-Point Detector can accurately diagnose high-voltage insulator faults in real-time under various conditions. Compared with some previous works using Faster R-CNN, SSD, and cascading network, our Box-Point Detector shows more competitively capabilities with high accuracy and robustness.

Sensor-based human activity recognition (HAR) has attracted enormous interests due to its wide applications in the Internet of Things (IoT), smart homes and healthcare. In this paper, a low-resolution infrared array sensor-based HAR approach is proposed using the deep learning framework. The device-free sensing system leverages the infrared array sensor of $8\times 8$ pixels to collect the infrared signals, which can ensure users’ privacy and effectively reduce the deployment cost of the network. To reduce the influence of temperature variations, a combination of the J-filter noise reduction method and the Butterworth filter is performed to preprocess the infrared signals. Long short-term memory (LSTM), a representative recurrent neural network, is utilized to automatically extract characteristics from the infrared signal and build the recognition model. In addition, the real-time HAR interface is designed by embedding the LSTM model. Experimental results show that the typical daily activities can be classified with the recognition accuracy of 98.287%. The proposed approach yields a better result compared to the existing machine learning methods, and it provides a low-cost yet promising solution for privacy-preserving scenarios.

In this paper, an effective wavelength detection approach based on long short-term memory (LSTM) network is proposed for fiber Bragg grating (FBG) sensor networks. The FBG sensor network utilizes a model-sharing mechanism, where the whole spectral wavelength is divided into several shareable regions and spectral overlap is allowed in each region. LSTM, a representative recurrent neural network in deep learning, is applied to learn the features directly from the spectra of FBGs and build the wavelength detection model. By feeding the spectra sequentially into the well-trained model, the Bragg wavelengths of FBGs can be quickly determined under overlap. The obtained LSTM model can be repeatedly used without re-training to improve the multiplexing capability. The results demonstrate that the LSTM-based method can realize high-accuracy and high-speed wavelength detection in the spectral overlapping situations. The proposed approach offers a flexible tool to enhance the sensing capacity of FBG sensor networks.

An efficient method based on a hybrid approach that combines extreme learning machine (ELM) technique and differential evolution (DE) algorithm is proposed to optimize the multi-pumped Raman fiber amplifier (RFA). The proposed method takes advantage of the fast learning speed and high generalization of the ELM as well as the strong global search capability of DE. From a novel perspective, we utilize ELM as a powerful learning tool to construct the nonlinear mapping between the pump parameters and gains of RFA. Instead of time-consuming integration of Raman coupled equations, the gains can be directly and accurately determined by ELM model. To obtain a flat gain spectrum, DE algorithm is employed to find the optimal wavelengths and powers of pumps. The well-trained ELM model is incorporated into the evolution of DE to accelerate the search process. The results show that the designed RFAs with the optimized pump parameters achieve the desired gain performance and meanwhile maintain very low level of gain ripple. In comparison to other related methods, the proposed method significantly shortens the computation time and enhances the overall optimization efficiency, which offers potential for real-time adjustment and flexibility of RFA design.

Detecting the components in aerial images is a crucial task in automatic visual inspection for power lines. Currently, deep learning models guided by external knowledge have achieved promising performances compared to directly applying the benchmark detectors. However, the component relationship, as human commonsense knowledge for object reasoning, is rarely investigated in this field. This study presents a graph-based relation guided network for power line component detection, which exploits correlations of regions, images, and categories. The visual relation module is employed to learn region-to-region relationship and enhance the visual features of each proposal that may contain components. Meanwhile, two guidance modules are proposed to capture image-to-region correlation and distinctively facilitate the category classification and position regression, which has not been considered in previous methods. Moreover, the category graphs built in these two modules are able to explore category-to-category dependencies that can further promote the network ability. Experimental results demonstrate that the proposed method can achieve more accurate and reasonable component detection compared to previous methods, which verifies the effectiveness of the proposed model incorporated with relation knowledge.

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.