Investigation of the effect of rosemary odor on mental workload using EEG: an artificial intelligence approach


Şahin Sadık E., Saraoğlu H. M., Canbaz Kabay S., Tosun M., Keskinkılıç C., Akdağ G.

Signal, Image and Video Processing, vol.16, no.2, pp.497-504, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 16 Issue: 2
  • Publication Date: 2022
  • Doi Number: 10.1007/s11760-021-01992-5
  • Journal Name: Signal, Image and Video Processing
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, zbMATH
  • Page Numbers: pp.497-504
  • Keywords: EEG, Mental workload, Stroop test, CART, Rosemary odor, Classification
  • Kütahya Health Sciences University Affiliated: Yes

Abstract

© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.Mental load is the load that occurs on the brain during a cognitive activity. Excessive increase in mental load causes a decrease in the success of the work or the inability to do the work. In this study, the effect of rosemary essential odor on mental load was evaluated with the Stroop test. The aim of the study is to show that the mental load during the Stroop test is reduced in volunteers who smell rosemary odor and to examine the effect of rosemary odor on the Stroop test. When the Stroop test results were evaluated statistically, the Stroop test task has completed an average of 1 second faster for each card in the presence of rosemary odor and the time responses were examined with the help of the one-way ANOVA test. Electroencephalogram (EEG) signals of 30 volunteers were collected in the study. For each volunteer, spectral features in 4 sub bands (delta, theta, alpha and beta) were extracted from the EEG signal using the Welch method, and the most significant features were selected from the extracted features using the decision tree feature importance method. The data were separated as 80% training and 20% testing, and with the help of the classification and regression tree algorithm, the mental workload created by the Stroop test cards on the volunteers could be classified with an accuracy of 96.88%.