In the past years, traditional pattern recognition methods have made great progress. However, these methods rely heavily on manual feature extraction, which may hinder the generalization model performance. With the increasing popularity and success of deep learning methods, using these techniques to recognize human actions in mobile and wearable computing scenarios has attracted widespread attention. In this paper, a deep neural network that combines convolutional layers with long short-term memory (LSTM) was proposed. This model could extract activity features automatically and classify them with a few model parameters. LSTM is a variant of the recurrent neural network (RNN), which is more suitable for processing temporal sequences. In the proposed architecture, the raw data collected by mobile sensors was fed into a two-layer LSTM followed by convolutional layers. In addition, a global average pooling layer (GAP) was applied to replace the fully connected layer after convolution for reducing model parameters. Moreover, a batch normalization layer (BN) was added after the GAP layer to speed up the convergence, and obvious results were achieved. The model performance was evaluated on three public datasets (UCI, WISDM, and OPPORTUNITY). Finally, the overall accuracy of the model in the UCI-HAR dataset is 95.78%, in the WISDM dataset is 95.85%, and in the OPPORTUNITY dataset is 92.63%. The results show that the proposed model has higher robustness and better activity detection capability than some of the reported results. It can not only adaptively extract activity features, but also has fewer parameters and higher accuracy. INDEX TERMS Human activity recognition, convolution, long short-term memory, mobile sensors.

In a photovoltaic (PV) system, the serial arc is mainly due to the discontinuity in the current‐carrying conductor. Different from the AC arc, the DC arc does not have a periodic zero‐crossing and more easily blossoms into sustained arc, which is more likely to cause accidents. When a serial arc occurs in the DC system, it would lead to a steep drop in current or some unpredictable, irregular change of the current wave. The occurrence of the serial arc can be detected by analyzing the change of amplitude at different frequencies. An arc‐fault detection method based on wavelet packet (WP) and support vector machine (SVM) analysis is proposed in this paper. The threshold to distinguish arcing from normal operation is determined by analyzing the characteristics of the WP coefficients of the DC arc current collected from a real system. Compared to that of the fast Fourier transform (FFT), the effectiveness of the proposed algorithms has been validated with experiments in a 5‐kW grid‐connected PV inverter. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

The commutation torque ripple in the six-step square-wave driving mode of the brushless DC motor affects the motor performance and generates mechanical vibrations and noise when used for industrial applications. The cause of commutation torque ripple is analysed in this study and a non-linear transient model of the phase current during the commutation interval is developed. According to the transient-current model, the commutation voltage and the time required to produce a constant torque can be calculated without current sampling; this makes the control system easier to realise in industrial applications, and reduces the need for a high performance controller. Based on the pulsewith modulated chopping method and quasi-Z-source net, the proposed control system can adjust the motor speed using a constant-voltage power supply and reduce the commutation torque ripple over the entire speed-adjustable range. A torque transducer is used to measure the dynamic torque ripple in the experiment. The results show that the proposed commutation torque-ripple reduction strategy can reduce the dynamic torque ripple by about 70% in both simulation and experiment compared with the traditional driving methods. Torque ripple in BLDCM driving systemThe torque ripple of the BLDCM is formed by three components: cogging torque, reluctance torque and mutual torque [23]. Cogging torque is a common shortcoming in PM motors, and can be minimised during motor design. PM motors with surface mounted

Racquet sports can provide positive benefits for human healthcare. A reliable detection device that can effectively distinguish movement with similar sub-features is therefore needed. In this paper, a racquet sports recognition wristband system and a multilayer hybrid clustering model are proposed to achieve reliable activity recognition and perform number counting. Additionally, a Bluetooth mesh network enables communication between a phone and wristband, and sets-up the connection between multiple devices. This allows users to track their exercise through the phone and share information with other players and referees. Considering the complexity of the classification algorithm and the user-friendliness of the measurement system, the improved multi-layer hybrid clustering model applies three-level K-means clustering to optimize feature extraction and segmentation and then uses the density-based spatial clustering of applications with noise (DBSCAN) algorithm to determine the feature center of different movements. The model can identify unlabeled and noisy data without data calibration and is suitable for smartwatches to recognize multiple racquet sports. The proposed system shows better recognition results and is verified in practical experiments.

No abstract

In response to environmental pollution and the spread of Coronavirus Disease 2019 , this paper proposes a new type of smart mask design, and specifically proposes an optimized double closedloop control method, especially an improved filtering fusion algorithm. Using the filtering fusion algorithm proposed in this paper, after the Kalman filter (KF) filters the raw data of the attitude sensor, explicit complementary filtering and data fusion are used to obtain the attitude angle of the body. At the same time, the obtained attitude angle is combined with acceleration and blood oxygen concentration to obtain the behaviour characteristic value. On this basis, the speed of the oxygen supply fan captured by the photoelectric sensor is used to form a closed loop with the characteristic value of the behaviour. Finally, the structure of the mask is upgraded and optimized through fluid mechanics simulation, and experiments have verified that the combination of the replaceable filter cloth, the intelligent control system and the ultraviolet disinfection device can effectively protect people's health.

Direct current (DC) serial arc faults usually occur in the damaged insulation lines or line connections, which will cause serious accidents such as fires and explosions. With the rapid increase of electric vehicles, DC serial arc faults are more and more dangerous to battery system. Therefore, a binary classification model based on machine learning algorithm was proposed to detect DC serial arc faults effectively in this study. It was optimised according to the characteristic signals of the arc to be satisfied with different loads for higher detection accuracy and robustness. In the simulative experiments for the power system electric vehicle, while the loads changing to the motor, the resistor or the inverter, it will all reach a highly successful detection rate, respectively.

Electric vehicle (EV) power system is flammable and explosive when the direct current (DC) arc occurs at elevated temperature. Thus, DC serial arc real-time monitoring is an insurance to keep away from disaster. In this study, the detection algorithm of DC serial arc is proposed. The wavelet entropy algorithm, the classification model based on support vector machine and logistic regression are analysed separately. The above algorithms are combined to identify the DC serial arc faults effectively under different types of loads in EV power system. The results show that the combined algorithm has a good performance of DC serial arc detection with high accuracy and robustness compared with a simple approach. Meanwhile, the false detection rate of the detection algorithm is close to zero, which could ensure the safety and stable operation of the system.