Dynamic Gesture Recognition Using Surface EMG Signals Based on Multi-Stream Residual Network

Abstract

Gesture recognition technology is widely used in the flexible and precise control of manipulators in the assisted medical field. Our MResLSTM algorithm can effectively perform dynamic gesture recognition. The result of surface EMG signal decoding is applied to the controller, which can improve the fluency of artificial hand control. Much current gesture recognition research using sEMG has focused on static gestures. In addition, the accuracy of recognition depends on the extraction and selection of features. However, Static gesture research cannot meet the requirements of natural human-computer interaction and dexterous control of manipulators. Therefore, a multi-stream residual network (MResLSTM) is proposed for dynamic hand movement recognition. This study aims to improve the accuracy and stability of dynamic gesture recognition. Simultaneously, it can also advance the research on the smooth control of the Manipulator. We combine the residual model and the convolutional short-term memory model into a unified framework. The architecture extracts spatiotemporal features from two aspects: global and deep, and combines feature fusion to retain essential information. The strategy of pointwise group convolution and channel shuffle is used to reduce the number of network calculations. A dataset is constructed containing six dynamic gestures for model training. The experimental results show that on the same recognition model, the gesture recognition effect of fusion of sEMG signal and acceleration signal is better than that of only using sEMG signal. The proposed approach obtains competitive performance on our dataset with the recognition accuracies of 93.52%, achieving state-of-the-art performance with 89.65% precision on the Ninapro DB1 dataset. Our bionic calculation method is applied to the controller, which can realize the continuity of human-computer interaction and the flexibility of manipulator control.

Retinal Vessel Segmentation Algorithm Based on Residual Convolution Neural Network

“…To avoid the inevitable problems of deep neural networks as gradient disappearance and gradient explosion, residual learning (Chen et al, 2020;Feng et al, 2020;Yang et al, 2021) is introduced into the network. The parallel method is applied and the identity mapping is added to the output of the stacked convolution layer.…”

Genetic Algorithm-Based Trajectory Optimization for Digital Twin Robots

“…Digital twin-based precision distribution for production logistics is a combined application of digital twin technology and mobile robots ( Li et al, 2019c ; Li et al, 2020 ). Production logistics, including internal logistics and external logistics, is the key to ensure normal production, improve production efficiency and reduce product costs ( Liu J et al, 2021 ; Yang et al, 2021 ). Digital twin production logistics refers to a new production logistics operation mode driven by twin data, through real mapping of physical entities and virtual models, real-time interaction and closed-loop control, to achieve task combination optimization, transportation path planning and transportation process control of production logistics, so as to achieve seamless and intelligent production process logistics ( Sun et al, 2020b ; Liu et al, 2021b ).…”

Intelligent Detection of Steel Defects Based on Improved Split Attention Networks

“…The application of Bio-inspired computation and artificial intelligence technology is gradually taking an important position in the field of mechanical engineering. More specifically, bio-inspired algorithms can replace humans to a certain extent, through training and learning to complete the tedious task of detecting steel surface defects ( Chen et al, 2021a ; Yang et al, 2021 ; Yun et al, 2021 , 2022 ). Research on steel plate defect detection based on visual attention mechanisms and bionic algorithms will help the steel industry move towards intelligence and information.…”