An EMG Gesture Recognition System with Flexible High-Density Sensors and Brain-Inspired High-Dimensional Classifier

Abstract

EMG-based gesture recognition shows promise for human-machine interaction. Systems are often afflicted by signal and electrode variability which degrades performance over time.We present an end-to-end system combating this variability using a large-area, high-density sensor array and a robust classification algorithm. EMG electrodes are fabricated on a flexible substrate and interfaced to a custom wireless device for 64-channel signal acquisition and streaming. We use braininspired high-dimensional (HD) computing for processing EMG features in one-shot learning. The HD algorithm is tolerant to noise and electrode misplacement and can quickly learn from few gestures without gradient descent or back-propagation. We achieve an average classification accuracy of 96.64% for five gestures, with only 7% degradation when training and testing across different days. Our system maintains this accuracy when trained with only three trials of gestures; it also demonstrates comparable accuracy with the state-of-the-art when trained with one trial.

Analysis of Contraction Effort Level in EMG-Based Gesture Recognition Using Hyperdimensional Computing

“…We used a custom, wireless 64-channel EMG signal acquisition device [8] to record a dataset of EMG signals from five able-bodied, adult male subjects 1 . A flexible 16x4 array of electrodes was wrapped completely around the subject's upper forearm, capturing activity of the extrinsic flexor and extensor muscles involved in finger movements with 1 kS/s sampling rate.…”

“…We used mean absolute value (MAV) with nonoverlapping windows of 50 samples as input features. Features are then encoded spatially (across 64 channels) and temporally (250 ms windows) into HD hypervectors exactly as described in [8]. Spatiotemporal hypervectors calculated using data from each gesture class are bundled together (i.e., summed) and bipolarized (i.e.…”

“…In this paper, we propose building a general classification model based on hyperdimensional (HD) computing [7] to deal with varying muscle contraction effort levels. HD computing has shown promising results in classification tasks using biosignals such as EMG in recognizing hand gestures [8] and electrocorticography (ECoG) for seizure detection with oneshot learning [9]. With slight modifications to our previously introduced encoding scheme [8], we analyze the muscle contraction level variations in two different ways, depending on the application: If discrimination between different gestures is the only goal, the classifier should output the same gesture class regardless of the subject's effort level.…”

“…A dataset of 5 human subjects performing 9 hand gestures ( Fig. 1) with low, medium, and high contraction effort levels was recorded using a wireless, high-channel count EMG recording system [8] which provided visual feedback of effort level. Classification accuracy results for both gesture-only and gesture+effort cases are presented.…”

Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing

“…• The exploration of the system scalability with respect to the number of electrodes available, following the general trend of bio-potential pattern recognition systems [22].…”