Gesture Classification from Compressed EMG Based on Compressive Covariance Sensing

Simultaneous sEMG Recognition of Gestures and Force Levels for Interaction With Prosthetic Hand

“…[9] collected the sEMG data of twelve subjects with five gestures, and the average recognition accuracy reached 98.7% by the neural network. [10] proposed the sEMG compression scheme to classify gestures based on compressed covariance sensing. The proposed method was verified by NinaPro open-source data that contained forty-nine gestures and achieved good results.…”

Compressed Sensing Approach for Physiological Signals: A Review

“…Further studies have shown that 6-bit uniform random coefficients are preferable for some bio-signals. C. Park et al [111] used CCS with various Linear Sparse ruler (LSR) sampling, and length-20 LSR shows favorable results regarding compression ratio and classification accuracy. A deterministic measurement matrix is proposed in [43] and easily implemented in hardware.…”

“…To overcome the sparsity constraint in EMG signals, CCS (Compressive Covariance Sensing) is proposed by D. Romero et al [117]; rather than reconstructing the original signal itself, CCS reconstructs its covariance, which is not a significant fact since several signal processing methods use covariance as a signal (e.g., power spectrum density, multiple signal classification, and machine learning covariance features). In [111], the authors use a CCS compression scheme for EMG signals for gesture classification. It is a good compression technique, but it cannot recover the original signal.…”

“…domain with the L1 approach. C. Park et al [111] used compressive covariance sensing (CCS) with the least square method; it showed effective compression techniques for EMG. Even though the original signal cannot be recovered, most applications do not need to retrieve it.…”