Reconstruction of Galvanic Skin Response Peaks via Sparse Representation

Continuous and long-term measurement of physiological signals out of clinical settings may face different processing requirements resulting in higher costs or reduced performance. Improved techniques of signal reconstruction from compressed representation may be a solution. This paper presents an approach based on Compressed Sensing to reconstruct peaks of Galvanic Skin Response measured by a wrist-worn device. Specifically, a random measurement matrix is employed in the reconstruction phase. Results show that the proposed approach detects the correct number of peaks better than the Ledalab automatic toolbox, even with high compression rates.