EMG-based hand gesture recognition for realtime biosignal interfacing

Abstract

In this paper the development of an electromyogram (EMG) based interface for hand gesture recognition is presented. To recognize control signs in the gestures, we used a single channel EMG sensor positioned on the inside of the forearm. In addition to common statistical features such as variance, mean value, and standard deviation, we also calculated features from the time and frequency domain including Fourier variance, region length, zerocrosses, occurrences, etc. For realizing real-time classification assuring acceptable recognition accuracy, we combined two simple linear classifiers (k-NN and Bayes) in decision level fusion. Overall, a recognition accuracy of 94% was achieved by using the combined classifier with a selected feature set. The performance of the interfacing system was evaluated through 40 test sessions with 30 subjects using an RC Car. Instead of using a remote control unit, the car was controlled by four different gestures performed with one hand. In addition, we conducted a study to investigate the controllability and ease of use of the interface and the employed gestures.

Design and Optimization of Levenberg-Marquardt based Neural Network Classifier for EMG Signals to Identify Hand Motions

“…However, though the use of increased numbers of channels will increase the average classification accuracy, a reduced efficiency may be observed for the numbers of channels greater than four [17]. On the other hand, some researchers are interested in considering the best and significant features other than using multichannel EMG signals or a combination of these approaches [22]. Placement of electrodes in different locations of muscle sites may help to achieve an improved classification rate despite the utilization of increased numbers of features.…”

Automatic Circumference Measurement for Aiding in the Estimation of Maximum Voluntary Contraction (MVC) in EMG Systems

“…They show much potential for naturally interfacing the complexity of our body movements with everyday electronics, and have influenced the development of many devices, including prothesis [1], exoskeletons [2], and electrical devices [3]. This technology however has never really reached the general population, as the complexity and discrepancies between users prevents the development of standards for compensating for the multitude of different body compositions.…”

Recognition of sketching from surface electromyography

“…Previously, sEMG signals have been successfully used in several fields such as robot [13] and wheelchair [14] controlling, medicine [15], development of prosthesis [16,17], fatigue detection [18,19,20], force prediction [21], etc. Researchers also have used EMG to develop a new kind of human computer interface, known as Muscle Computer Interface (muCI) [22,12,23] for recognition of hand gestures [24,25], body languages [26] and facial expressions [11].…”