Detection Of Mental State From Eeg Signal Data: An Investigation With Machine Learning Classifiers

Authors

  • Mohammed Haroon Hussain1 B.E. Student, Department of IT, Lords Institute of Engineering and Technology, Hyderabad Author
  • Syed Shah Maaz Uddin2 B.E. Student, Department of IT, Lords Institute of Engineering and Technology, Hyderabad Author
  • Syed Shah Quzaima Hassan3 B.E. Student, Department of IT, Lords Institute of Engineering and Technology, Hyderabad Author
  • M.Neelima Assistant Professor, Department of IT, Lords Institute of Engineering and Technology, Hyderabad Author

Abstract

The mental state of an individual is influenced by a
complex interplay of neural activities, shaped by
numerous external and internal factors. By analyzing
EEG patterns, it is possible to ascertain an
individual's mental state. Utilizing a dataset from
Kaggle, ten machine learning techniques were
explored, and models were developed.
Hyperparameter tuning was performed using the
RandomSearchCV method, and a comparative
analysis was conducted for both tuned and non-tuned
hyperparameters. Upon evaluating the performance
metrics, the Support Vector Machine (SVM)
demonstrated the highest accuracy at 95.36%.
Gradient Boosting (GrB) also showed a promising
accuracy of 95.24%, while K-Nearest Neighbors
(KNN) and XGBoost (XGB) both achieved an
accuracy of 93.10%. Consequently, the effective
integration of ML-based detection methods can
potentially regulate a person's mental state, fostering
a deeper understanding of human psychology and
predicting their behavior

Downloads

Download data is not yet available.

Downloads

Published

2024-08-29

Issue

Vol. 9 No. 8 (2024): August

Section

Articles

How to Cite

Detection Of Mental State From Eeg Signal Data: An Investigation With Machine Learning Classifiers. (2024). International Journal of Multidisciplinary Engineering In Current Research, 9(8), 59-67. https://ijmec.com/index.php/multidisciplinary/article/view/487