Artificial Neural Network Classification Models for Stress in Reading

Abstract

Stress is a major problem facing our world today and it is important to develop an understanding of how an average person responds to stress in a typical activity like reading. The aim for this paper is to determine whether an artificial neural network (ANN) using measures from stress response signals can be developed to recognize stress in reading text with stressful content. This paper proposes and tests a variety of ANNs that can be used to classify stress in reading using a novel set of stress response signals. It also proposes methods for ANNs to deal with hundreds of features derived from the response signals using a genetic algorithm (GA) based approach. Results show that ANNs using features optimized by GAs helped to select features for stress classification, dealt with corrupted signals and provided better classifications. ANNs using GAs were generated to exploit the time-varying nature of the signals and it was found to be the best method to classify stress compared to all the other ANNs.