A5044442796- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Hand Gesture Recognition Systems
- Technology and Security Systems
- Tactile and Sensory Interactions
- Simulation and Modeling Applications
- Digital Imaging for Blood Diseases
- Wireless Sensor Networks and IoT
- Video Surveillance and Tracking Methods
- Motor Control and Adaptation
- Image and Object Detection Techniques
Wuhan University of Science and Technology
2019-2023
Summary For the problem of surface electromyography (sEMG) gesture recognition, considering fact that traditional machine learning model is susceptible to sEMG feature extraction method, it difficult distinguish subtle differences between similar gestures. The NinaPro DB1 dataset used as research object, and image Convolutional Neural Network (CNN) are combined recognize 52 movements. CNN effectively solves limitations in combines 1‐dim convolution kernel extract deep abstract features...
Based on HSV gamut space, a visualization system of muscle activity is proposed to study the mapping relationship between hand motion and active areas upper arm muscle. There significant threshold change in starting ending points segment original EMG signal, part that exceeds TH date. Set window width K fixed increment Kt time remove redundant data. The sEMG intensity information each sampling electrode obtained by calculating MAV window, simulation experiment conducted space. Through...
sEMG(surface electromyography) signals have been widely used in rehabilitation medicine the past decades because of their non-invasive, convenient and informative features, especially human action recognition, which has developed rapidly. However, research on sparse EMG multi-view fusion made less progress compared to high-density signals, for problem how enrich feature information, a method that can effectively reduce information loss channel dimension is needed. In this paper, novel IMSE...