Application of Dimensionality Reduction Methods for Eye Movement Data Classification

Abstract

In this paper we apply two data dimensionality reduction methods to eye movement dataset and analyse how the feature reduction method improves classification accuracy. Due to the specificity of the recording process, eye movement datasets are characterized by both big size and high-dimensionality that make them difficult to analyse and classify using standard classification approaches. Here, we analyse eye movement data from BioEye 2015 competition and to deal with the problem of high dimensionality we apply SVM combined with PCA feature extraction and random forests wrapper variable selection. Our results show that the reduction of the number of variables improves classification results. We also show that some of classes (participants) can be classified (recognised) with high accuracy while others are very difficult to be correctly identified.

Biometric Identification Based on Eye Movement Dynamic Features

“…The feature vectors described earlier were used in the classification process as an input to several classification algorithms. For the research purpose, the methods applied in the previously conducted studies [ 4 , 6 , 11 , 21 ] were utilized to check their performance on a different data set.…”

Secure gateway for Internet of Things with internal AAA mechanism

“…[23]) is another important research topic. Secure communication and applying security policies to such interaction should be missioncritical for developers and architects.…”