Feature Selection on Thermal-stress Dataset

TL;DR

This paper investigates feature selection methods for thermal-stress data to enhance stress classification accuracy, finding that genetic algorithms with neural networks significantly improve predictions and that magnitude measures offer a good balance of efficiency and performance.

Contribution

It introduces and compares three feature selection techniques for thermal-stress data, demonstrating the effectiveness of genetic algorithms with neural networks in stress prediction.

Findings

Genetic algorithm with ANN improves accuracy by 19.1%.

Magnitude measure balances computation time and performance.

Feature selection enhances stress recognition systems.

Abstract

Physical symptoms caused by high stress commonly happen in our daily lives, leading to the importance of stress recognition systems. This study aims to improve stress classification by selecting appropriate features from Thermal-stress data, ANUstressDB. We explored three different feature selection techniques: correlation analysis, magnitude measure, and genetic algorithm. Support Vector Machine (SVM) and Artificial Neural Network (ANN) models were involved in measuring these three algorithms. Our result indicates that the genetic algorithm combined with ANNs can improve the prediction accuracy by 19.1% compared to the baseline. Moreover, the magnitude measure performed best among the three feature selection algorithms regarding the balance of computation time and performance. These findings are likely to improve the accuracy of current stress recognition systems.