A Pilot Study on Using Forcemyography to Record Upper-limb Movements for Human-machine Interactive Control.

Forcemyography (FMG) is a useful method to record real-time body motions, which has application potentials for human-machine interactive control. The FMG registers the change of force distribution in the normal direction on muscle surface during limb movements, and the body motions can be recognized by decoding the FMG patterns. In this study, we used FMG to record upper-limb movements and evaluated the influence of different configurations of signal channel and feature on motion classification performances. A four-channel wearable FMG acquisition system was developed to record seven upper-limb movements on each of six able-bodied subjects. The preliminary results showed that the signal channel number has significant influence on motion classification performance; however, the influence of signal feature number on motion classification was insignificant. In addition, the influence of channel combination and feature combination were also discussed in this paper. This work would support the application potential of FMG for body motion recording and may provide useful instructions for the application of FMG in human-machine interactive control.

A Novel Flexible Sensor for Muscle Shape Change Monitoring in Limb Motion Recognition.

Human limb movement intent recognition fundamentally provides the control mechanism for assistive devices such as exoskeleton and limb prosthesis. While different biopotential signals have been utilized for limb movement intent decoding, they seldom could account for spatial information associated with changes in muscle shape that could also be used to characterize the limb motor intent. Therefore, this study developed a novel nano gold stretchable-flexible sensor that captures spatial information associated with the muscle shape change signal (MSCS) during different muscle activation patterns. The novel sensor consists of 2-channels to acquire MSCS at a sampling rate of 125 Hz, corresponding to multiple classes of upper limb movements acquired across six able-bodied subjects. By utilizing the linear discriminant analysis algorithm on the acquired data with a single extracted feature, an overall average motion decoding accuracy of 90.9% was achieved. In addition, the waveform analysis results show that the novel sensor's recordings were less affected by external interferences, thus yielding high quality signals. This study is the first to utilize nano gold stretchable-flexible material for sensor fabrication in pattern recognition of upper limb movement intent, which may facilitate the development of effective assistive devices.