The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals

Over the past few years, Deep learning (DL) has revolutionized field of data analysis. Not only are algorithmic paradigms changed, but also performance in various classification and prediction tasks been significantly improved with respect to state-of-the-art, especially area computer vision. The progress made vision produced a spillover many other domains, such as biomedical engineering. Some recent works directed towards surface electromyography (sEMG) based hand gesture recognition, often addressed an image problem solved using tools Convolutional Neural Networks (CNN). This paper extends our previous work on application Hilbert space-filling curve for generation representations from multi-electrode sEMG signals, by investigating how compares Peano- Z-order curves. proposed mapping methods evaluated variety network architectures some cases yield improvement at least 3%, when used structure inputs before feeding them into original architectures.