Page 25 - BH-2-2

Brain & Heart

REVIEW ARTICLE
Recognition predictive modeling using

electroencephalogram

3,4
S. K. B. Sangeetha 1 , Sandeep Kumar Mathivanan 2 , Saurav Mallik * ,
and Aimin Li 5
1 Department of Computer Science and Engineering, Faculty of Computer Science and Engineering,
SRM Institute of Science and Technology, Chennai, Tamil Nadu, India
2 Department of Computer Science and Engineering, School of Computer Science and Engineering,
Galgotias University, Greater Noida, Uttar Pradesh, India
3 Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston,
Massachusetts, United States of America
4 Department of Pharmacology and Toxicology, The University of Arizona, Tucson, Arizona,
United States of America
5 School of Computer Science and Engineering, Xi’an University of Technology, Xi’an, Shaanxi, China
(This article belongs to Special Issue: Deep Learning and Optimization Insight into Cardiovascular
Risk Factors, Cognitive Decline)

Abstract

A machine learning model that operates on raw electroencephalogram (EEG) signals
is essential for accurately discerning the user’s current thoughts. Given the difficulty
of categorizing EEG signals for use in brain-computer interface (BCI) programs,
we adopted a systematic approach in this study to select an optimal predictive
*Corresponding author: model. To enhance the effectiveness of our systematic approach, we extracted
Saurav Mallik features such as band powers, averages, and root-mean-squared values. K-nearest
(smallik@arizona.edu) neighbor (KNN), principal component analysis, and dual-layer neural networks were
Citation: Sangeetha SKB, employed to evaluate and validate the effectiveness of the extracted features. The
Mathivanan SK, Mallik S, Li A. BCI IV competition-I dataset was utilized for analysis and validation. KNN achieved
Recognition predictive modeling an average classification success rate of 98.02% compared to other methods.
using electroencephalogram. Brain
& Heart. 2024;2(2):2819. Furthermore, our research extends the application of this approach using it to create,
doi: 10.36922/bh.2819 test, and evaluate human driving behavior as a case study.
Received: January 24, 2024
Accepted: March 19, 2024 Keywords: Brain-computer interface; Electroencephalogram; Feature extraction; Human-
computer interface; Machine learning; Neural network
Published Online: May 15, 2024
Copyright: © 2024 Author(s).
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution 1. Introduction
License, permitting distribution,
and reproduction in any medium, With recent developments in imaging techniques for the brain and the field of cognitive
provided the original work is neuroscience, we now have the ability to directly interface with individuals’ minds.
properly cited. Studies of how our thoughts evolve over time may be recorded and monitored in the
Publisher’s Note: AccScience form of low-power electrical signals using these technologies and cutting-edge sensors.
Publishing remains neutral with This knowledge has paved the way for brain-computer interfaces (BCIs) and other types
regard to jurisdictional claims in
published maps and institutional of communication systems that allow users to control computers and equipment solely
1
affiliations. with their minds as opposed to physically moving them. BCIs have moved their attention

Volume 2 Issue 2 (2024) 1 doi: 10.36922/bh.2819