Search

Human activity recognition (HAR) is one of the important research areas in pervasive computing. Among HAR, sensor-based activity recognition refers to acquiring a high-level knowledge about human activities from readings of many low-level sensors. In recent years, although the existing methods of deep learning (DL) have been widely used for sensor-based HAR with some good performance, they still face such challenges as feature extraction and characterization, continuous action segmentation in dealing with time series problems. In this study, a multichannel fusion model is proposed with the idea of dividing. In this proposed architecture, a multichannel convolutional neural network (CNN) is used to enhance the ability to extract features at different scales, and then the fused features are fed into the gated recurrent unit (GRU) for feature labeling and enhanced feature representation, through the learning of temporal relationships. Finally, the multichannel CNN-GRU model is designed using global average pooling (GAP) to connect the feature maps with the final classification. The model performance was conducted on three benchmark datasets of WISDM, UCI-HAR, and PAMAP2 with the accuracy of 96.41%, 96.67%, and 96.25% respectively. The results show that the proposed model demonstrates better activity detection capability than some of the reported results.

This paper studies a non-linear energy harvesting (EH) enabled full-duplex (FD) cooperative non-orthogonal multiple access (C-NOMA) system, where the near user acts as an FD relay to assist the transmission from BS to far user with power-splitting (PS) protocol. We derive the close-form expressions of outage probability in this considered system, and also give the asymptotic outage probability under high signal-to-noise ratio (SNR) regime. Additionally, we obtain the optimal power allocation parameter to minimize the outage probability, and discuss the impact of self-interference (SI) on outage performance. Moreover, it is observed from simulation results that the presence of SI improve the outage performance, which is caused by the so-called self-energy recycling.

Rehabilitation robots play an increasingly important role in the recovery of motor function for stroke. To ensure a natural physical human-robot interaction (pHRI) and enhance the active participation of subjects, it is necessary for the robots to understand the human intention and cooperate actively with humanlike characteristics. This study proposed a hybrid active control algorithm with human motion intention detection. The motion intention was defined as the desired position and velocity, which were continuously estimated according to the human upper-limb model and minimum jerk model, respectively. The motion intention was then fed into a hybrid force and position controller of an upper-limb cable driven rehabilitation robot (CDRR). And a three-dimensional reaching task without predefined trajectory was employed to validate the effectiveness of the proposed control algorithm. Experimental results showed that the control algorithm could continuously recognize the human motion intention and enabled the robot better movement performance indicated as smaller offset error, smoother trajectory, and lower impact. The proposed method could guarantee a natural pHRI and improve the engagement of the subjects, which has great potential in clinical applications.

Wave energy is a renewable clean and resources for ships. According to the rolling characteristics of merchant ships, this research designs an energy recovery device installed on the ship deck to harvest the energy generated by waves. And a typical 50,000-ton ship is selected as the experimental platform of the device. The mathematical model is established and solved by Newmark- $\beta $ method, and a simulation platform is built in MATLAB. By simulating the movement of the slider in the device, it shows that the slider can realize reciprocating motion when the ship rolls continuously. Then, the relevant parameters in different combinations of natural frequency $\omega _{n}$ and damping ratio $\varepsilon $ are calculated, the power output of the device and the motion law of the slider are analyzed, and parameters’ variable curves are drawn in figures. A reasonable combination of $\omega _{n}=1.225$ Hz, $\varepsilon =0.0612$ and a relatively ideal average power (174.11 W) are found by comparing amounts of simulated results from typical sea conditions. It is indicated that four main factors affecting the power generation of the device include the elasticity coefficient $K$ , effective damping coefficient $C$ in the device, the ship rolling period and rolling angle. Besides, the device can still output power continuously by simulation in complex sea condition. Based on the research, it is proved that the device mentioned in this study has good feasibility in generating electric energy during ship rolling, which can provide valuable ideas for the application of wave energy in ships on voyage.

The study of a metro traction power supply system reliability makes a significant contribution to researching on new power supply principles and configuration, and also providing a reference for system design and operation. According to the power supply structure and operation mode of the metro traction substation power supply system, based on the internal equipment, the reliability evaluation model of the traction substation is established by the block processing fault tree. An improved sequential Monte Carlo method is used to realize the quantitative reliability evaluation of the metro traction substation power supply system. The conclusions show that the reliability model and the sequential Monte Carlo simulation method proposed in this paper can obtain rich reliability indexes. Through visual simulation and theoretical calculation, the reliability of the metro traction power supply system can be effectively evaluated.