Hand Gesture Recognition-Based Control of Motorized Wheelchair using Electromyography Sensors and Recurrent Neural Network

Abstract

Mobility has been identified to be a major characteristic of living things. Humans who are deprived of efficient mobility either by natural or man-made factors loose significant relationship with their environment. The growing demand to produce effective rehabilitation devices for the aged population and disabled individuals, have spurred us to develop a reliable and easy to use biosignal based auto control wheelchair. This is to ensure independent mobility of persons with disabilities and the aged. In this paper, a Recurrent Neural Network (RNN) architecture called Long Short Term Memory (LSTM) is engaged for the classification EMG signals to the corresponding hand-gesture category. The LSTM model in this study yielded a validation accuracy that provides a basis for an improved solution towards real-time deployment.

Use of Advanced Materials and Artificial Intelligence in Electromyography Signal Detection and Interpretation

“…Diagnose bruxism [132] forearm Physiotherapy [133] RNN It can view data as sequences Time information can be modeled Problem of long-term dependence High computational cost Motorized wheelchair control [134] Myoelectric prostheses control [135] CNN Image-based Can extract more potential features Optimization function is easy to fall into a local optimal solution Easy gradient disappears High computational cost Myoelectric hand control or neuro-prosthesis control [136,137] LDA is a supervised dimensionality reduction method, similar to principal component analysis (PCA), which is to project data in different dimensional spaces to achieve the purpose of dimensionality reduction. Both have been used for classifying EMG data for a wide range of applications.…”

Real-time continuous gesture recognition system based on PSO-PNN

“…Under CG recognition, compared to template matching and probabilistic analysis, neural network models, with their excellent feature extraction capabilities and adaptability, perform exceptionally well in complex and variable gesture recognition tasks. In neural networks, researchers mainly use machine learning and deep learning methods to meet the needs of high-performance intelligent interaction systems [31][32][33][34][35]. In the field of deep learning, the DFFN algorithm has achieved accuracies of up to 99.93% and 96.1% in recognizing American and Chinese sign language, respectively, based on wearable sensors.…”

Eye-Gaze Controlled Wheelchair Based on Deep Learning

“…A growing body of research is dedicated to the application of artificial intelligence technologies to modify power wheelchairs to improve the quality of life of people with ALS. In the past few decades, researchers have carried out corresponding research on wheelchair motion control methods, including gesture control [1][2][3][4][5], voice control [6][7][8][9][10], eye-tracking control [11][12][13][14][15], and brain-computer interfaces [16][17][18][19][20][21][22]. These control methods can replace the rocker to complete the reading of the user's motion direction intention and realize the motion control of the wheelchair.…”