Home > Table of Contents


Proceedings of 2009 International Workshop on Information Security and Application (IWISA 2009)

Qingdao, China, November 21-22, 2009

Editors: Feng Gao and Xijun Zhu

AP Catalog Number: AP-PROC-CS-09CN004

ISBN: 978-952-5726-06-0

Page(s): 446-449

Estimating VDT Visual Fatigue Based on the Features of ECG Waveform

Aihua Zhang, Zhiyue Zhao, and Yetai Wang

Full text: PDF


In order to find an objective evaluation method of visual fatigue, we simulate VDT (Visual Display Terminal) operating environment, and test 34 students for 1.5 hour VDT fatigue experiment. ECG (Electrocardiogram) signals are collected from the subjects by using the MP425 data acquisition card and LABVIEW acquisition system. The features of ECG waveforms are extracted by analyzing and processing ECG signals. SVM (Support Vector Machine) is adopted to identify visual fatigue state. The results show that ECG signal features change significantly before and after VDT fatigue experiment, the accuracy rate of classification is above 80% by using a single ECG feature, and the accuracy rate of classification is above 90% by using features combination. Hence ECG waveform features and SVM could be a promising method for estimating VDT visual fatigue.

Index Terms

visual fatigue, ECG, feature extraction, SVM

Copyright @ 2009 ACADEMY PUBLISHER All rights reserved