EOG Signal Classification with Wavelet and Supervised Learning Algorithms KNN, SVM and DT

Sandy Nohemy Hernández Pérez; Francisco David Pérez Reynoso; Carlos Alberto González Gutiérrez; María De Los Ángeles Cosío León; Rocío Ortega Palacios

doi:10.3390/s23094553

EOG Signal Classification with Wavelet and Supervised Learning Algorithms KNN, SVM and DT

Sensors (Basel). 2023 May 7;23(9):4553. doi: 10.3390/s23094553.

Authors

Sandy Nohemy Hernández Pérez¹, Francisco David Pérez Reynoso², Carlos Alberto González Gutiérrez², María De Los Ángeles Cosío León³, Rocío Ortega Palacios¹

Affiliations

¹ Master's Degree in Information and Communications Technologies, Universidad Politécnica de Pachuca (UPP), Zempoala 43830, Mexico.
² Center for Research, Innovation and Technological Development UVM (CIIDETEC-UVM), Universidad del Valle de México, Querétaro 76230, Mexico.
³ Direction of Research, Innovation and Graduate Studies, Universidad Politécnica de Pachuca (UPP), Zempoala 43830, Mexico.

Abstract

The work carried out in this paper consists of the classification of the physiological signal generated by eye movement called Electrooculography (EOG). The human eye performs simultaneous movements, when focusing on an object, generating a potential change in origin between the retinal epithelium and the cornea and modeling the eyeball as a dipole with a positive and negative hemisphere. Supervised learning algorithms were implemented to classify five eye movements; left, right, down, up and blink. Wavelet Transform was used to obtain information in the frequency domain characterizing the EOG signal with a bandwidth of 0.5 to 50 Hz; training results were obtained with the implementation of K-Nearest Neighbor (KNN) 69.4%, a Support Vector Machine (SVM) of 76.9% and Decision Tree (DT) 60.5%, checking the accuracy through the Jaccard index and other metrics such as the confusion matrix and ROC (Receiver Operating Characteristic) curve. As a result, the best classifier for this application was the SVM with Jaccard Index.

Keywords: EOG; classifier algorithms; wavelet transform.

MeSH terms

Algorithms*
Electrooculography / methods
Eye Movements
Humans
Support Vector Machine*
Wavelet Analysis

Grants and funding

This research was partially financed by the Polytechnic University of Pachuca, Universidad del Valle de México Queretaro Campus and the National Council of Science and Technology (CONACYT), co-financed with federal funds.