Open Software/Hardware Platform for Human-Computer Interface Based on Electrooculography (EOG) Signal Classification

• DOI: 10.3390/s20092443
• Publication Date: 2020-04-28T14:30:58Z
• Authors: Jayro Martínez-Ce...; Majid Khalili Ardali; Andres Jaramillo-...; Shizhe Wu; Alessandro Tonin; Niels Birbaumer; Ujwal Chaudhary
• Keywords: Electrooculography; Biosignal; Python; Interface (matter); Raspberry Pi

Electrooculography (EOG) signals have been widely used in Human-Computer Interfaces (HCI). The HCI systems proposed the literature make use of self-designed or closed environments, which restrict number potential users and applications. Here, we present a system for classifying four directions eye movements employing EOG signals. is based on open source ecosystems, Raspberry Pi single-board computer, OpenBCI biosignal acquisition device, an open-source python library. designed provides cheap, compact, easy to carry that can be replicated modified. We Maximum, Minimum, Median trial values as features create Support Vector Machine (SVM) classifier. A mean 90% accuracy was obtained from 7 out 10 subjects online classification Up, Down, Left, Right movements. This input HCI, i.e., assisted communication paralyzed people.