Learning to modulate the partial powers of a single sEMG power spectrum through a novel human-computer interface

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

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.

Effects of muscle fatigue on the usability of a myoelectric human-computer interface

Electromyography-based human-computer interface development is an active field of research. However, knowledge on the effects of muscle fatigue for specific devices is limited. We have developed a novel myoelectric human-computer interface in which subjects continuously navigate a cursor to targets by manipulating a single surface electromyography (sEMG) signal. Two-dimensional control is achieved through simultaneous adjustments of power in two frequency bands through a series of dynamic low-level muscle contractions. Here, we investigate the potential effects of muscle fatigue during the use of our interface. In the first session, eight subjects completed 300 cursor-to-target trials without breaks; four using a wrist muscle and four using a head muscle. The wrist subjects returned for a second session in which a static fatiguing exercise took place at regular intervals in-between cursor-to-target trials. In the first session we observed no declines in performance as a function of use, even after the long period of use. In the second session, we observed clear changes in cursor trajectories, paired with a target-specific decrease in hit rates.