A Data Acquisiton System with sEMG Signal and Camera Images for Finger Classification with Machine Learning Algorithms

Abstract

Advances in robotics and biomedical engineering have expanded the possibilities of Human-Computer Interaction (HCI) in the last few years. The identification of hand movements is the accurate and real-time signal acquisition of hand movements through the use of image-based systems and surface electromyography sensors. This study uses multithreading to record motion signals from the forearm muscles in conjunction with a surface electromyography (sEMG) sensor and a camera image. The finger movement information labels were tabulated and analyzed along with the simultaneous acquisition of surface electromyography signals and these gestures through the camera. After the acquisition, signal processing techniques were applied to the sEMG signal markered from the camera. Therefore, once the interface is established, data sets suitable for machine learning can be generated.