A Novel Feature Optimization for Wearable Human-Computer Interfaces Using Surface Electromyography Sensors

Abstract

The novel human-computer interface (HCI) using bioelectrical signals as input is a valuable tool to improve the lives of people with disabilities. In this paper, surface electromyography (sEMG) signals induced by four classes of wrist movements were acquired from four sites on the lower arm with our designed system. Forty-two features were extracted from the time, frequency and time-frequency domains. Optimal channels were determined from single-channel classification performance rank. The optimal-feature selection was according to a modified entropy criteria (EC) and Fisher discrimination (FD) criteria. The feature selection results were evaluated by four different classifiers, and compared with other conventional feature subsets. In online tests, the wearable system acquired real-time sEMG signals. The selected features and trained classifier model were used to control a telecar through four different paradigms in a designed environment with simple obstacles. Performance was evaluated based on travel time (TT) and recognition rate (RR). The results of hardware evaluation verified the feasibility of our acquisition systems, and ensured signal quality. Single-channel analysis results indicated that the channel located on the extensor carpi ulnaris (ECU) performed best with mean classification accuracy of 97.45% for all movement’s pairs. Channels placed on ECU and the extensor carpi radialis (ECR) were selected according to the accuracy rank. Experimental results showed that the proposed FD method was better than other feature selection methods and single-type features. The combination of FD and random forest (RF) performed best in offline analysis, with 96.77% multi-class RR. Online results illustrated that the state-machine paradigm with a 125 ms window had the highest maneuverability and was closest to real-life control. Subjects could accomplish online sessions by three sEMG-based paradigms, with average times of 46.02, 49.06 and 48.08 s, respectively. These experiments validate the feasibility of proposed real-time wearable HCI system and algorithms, providing a potential assistive device interface for persons with disabilities.

Electromyography Signal Analysis for the Detection of TMJ Disorder Using Classification Models and Multivariate Analysis

“…where, N is an even integer [14]. The set of wavelets than forms an orthonormal basis which we use to decompose signal.…”

“…The noninvasive method for acquiring EMG signals was chosen over the invasive method [13], which used single use and sticky type electrodes for EMG signal acquisition. Because the study concentrated on the temporal and masseter muscles, the first electrode was put on the masseter, the second on the temporal muscle as a reference electrode, and the reference on the forehead as a ground electrode [14]. The EMG recording of these muscles was done in both groups at rest position and during maximum clenching.…”

A Review of EMG-, FMG-, and EIT-Based Biosensors and Relevant Human–Machine Interactivities and Biomedical Applications

“…Human–machine interaction system based on EOG and temporalis EMG [ 111 ]. Feature optimization of sEMG in human–machine interaction [ 112 ]. Tractor manipulation via EMG-based human–machine interface [ 113 ].…”

Assistance Robotics and Biosensors

“…In this sense, the use of appropriate signals for each case is of great importance. In “A Novel Feature Optimization for Wearable Human–Computer Interfaces Using Surface Electromyography Sensors” [ 7 ], the authors carried out a study of the signals and selection of optimal-feature selection made according to a modified entropy criteria (EC) and Fisher discrimination (FD) criteria. The feature selection results were evaluated using four different classifiers, and compared with other conventional feature subsets.…”