Application of Time-Scale Decomposition of Entropy for Eye Movement Analysis

Abstract

The methods for nonlinear time series analysis were used in the presented research to reveal eye movement signal characteristics. Three measures were used: approximate entropy, fuzzy entropy, and the Largest Lyapunov Exponent, for which the multilevel maps (MMs), being their time-scale decomposition, were defined. To check whether the estimated characteristics might be useful in eye movement events detection, these structures were applied in the classification process conducted with the usage of the kNN method. The elements of three MMs were used to define feature vectors for this process. They consisted of differently combined MM segments, belonging either to one or several selected levels, as well as included values either of one or all the analysed measures. Such a classification produced an improvement in the accuracy for saccadic latency and saccade, when compared with the previously conducted studies using eye movement dynamics.

A systematic review on Evaluation of Existing Face Eyes Detection Algorithms for Monitoring Systems

“…Infrared light is used because it is "invisible" to the naked eye and does not distract the subject. The ambient lighting level has no effect on measurements because infrared detectors are not affected by other light sources [48] .…”

Multiscale Entropy Approaches and Their Applications

“…Harezlak et al studied eye movement signal characteristics [ 11 ]. For this purpose, the authors used several methods: approximate entropy, fuzzy entropy, and the largest Lyapunov exponent.…”

Correlation dimension and entropy in the assessment of sex differences based on human gait data

“…There are also numerous applications of approximate and sample entropies in the description of biological time-series data. Among others, they were used in the analysis of gait represented by ground reaction forces (Wu et al, 2017 ), in the classification of eye movement data (Harężlak and Kasprowski, 2020 ), the assessment of the influence of walking speed and ground slope on the gait control based on mocap sequences (Szczęsna, 2019 ), characterization of downhill skiing registered by inertial measurement units (Szczęsna and Janiak, 2019 ), examination of regularity of the center of pressure during the performance of four yoga poses (Błażkiewicz, 2020 ), diagnosis of unilateral knee pain (Bacon et al, 2022 ) as well as investigation of angular displacement when balancing on a stability platform (Becker and Hung, 2020 ).…”