Contact Us
Journal Statistics & Approval Details
Recent Published Paper
Our Author's Feedback
 •  SJIF Impact Factor: 8.067       •  ISRA Impact Factor 7.894       •  Hard Copy of Certificates to All Authors       •  DOI by Crossref for all Published Papers       •  Soft Copy of Certificates- Within 04 Hours       •  Authors helpline No: +91-8813907089(Whatsapp)       •  No Publication Fee for Paper Submission       •  Hard Copy of Certificates to all Authors       •  UGC Approved Journal: IJRASET- Click here to Check       •  Conference on 18th and 19th Dec at Sridevi Womens Engineering College     
ISSN: 2321-9653
Estd : 2013

Ijraset Journal For Research in Applied Science and Engineering Technology

EEG-Based Cognitive State Classification for Multiple Mental Conditions

Authors: Prof. Supriya Jawale, Dr. G. M. Asutkar , Dhanshree Lanjewar, Ishika Ambagade, Janvi Bhonde

DOI Link: https://doi.org/10.22214/ijraset.2026.79167

Certificate: View Certificate

Abstract

Electroencephalography (EEG) has gained importance in the objective study of mental and neurological states due to its high temporal resolution, noninvasiveness, and low cost. The increasing prevalence of neurological and mental health problems calls for reliable, data-driven diagnostic and monitoring techniques that go beyond traditional subjective assessments. This review provides a systematic overview of EEG-based mental state detection techniques, including data collection methods, preprocessing techniques, feature extraction strategies, and classification models. In order to capture discriminative patterns of brain activity across time, frequency, time–frequency, nonlinear, and connection domains, the significance of feature extraction techniques is examined. We cover both sophisticated deep learning architectures like Convolutional Neural Networks, Recurrent Neural Networks, and hybrid models, as well as fundamental machine learning classifiers like Random Forests and Support Vector Machines. According to published performance evaluations, deep learning-based techniques usually provide better resilience and classification accuracy. Despite these advancements, there are still significant issues with noise artifacts, inter-subject variability, the lack of datasets, and overlapping mental state characteristics. This review also outlines future research directions with a focus on improved preprocessing, improved feature learning, scalable model architectures, and therapeutically useful EEG-based systems.

Introduction

Electroencephalography (EEG) is a non-invasive technique for monitoring brain activity, useful for understanding mental states, neurological conditions (e.g., epilepsy, Parkinson’s, Alzheimer’s), and psychiatric disorders, as well as for brain-computer interfaces (BCIs). EEG signals are complex, noisy, and nonstationary, so feature extraction—including time-domain, frequency-domain, nonlinear, time-frequency, connectivity, and learned deep features—is crucial for meaningful analysis. Machine learning and deep learning techniques such as SVM, Random Forest, k-NN, CNNs, RNNs, LSTMs, and hybrid models are employed to classify EEG signals, enabling accurate detection of cognitive and emotional states. Advances in preprocessing, feature engineering, and deep learning have improved EEG classification, providing potential for more reliable mental health diagnosis, personalized care, and enhanced human-computer interaction.

References

[1] Y. Liu &Z. Huang, \"Mental state identification based on the classification of EEG signals,\" in Proc. 15th Int. Congr. Image Signal Process., BioMed. Eng. Inform. (CISP-BMEI), 2022, pp. 1–6. [2] S. Patnaik, L. Moharkar, and A. Chaudhari, \"Deep RNN Learning for EEG based Functional Brain State Inference,\" in Proc. Int. Conf. Commun. Electron. Syst. (ICCES), 2018, pp. 810–813. [3] X. Wu and X. Guo, \"Mental EEG Analysis based on Independent Component Analysis,\" in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), vol. 6, 2001, pp. 3525–3528. [4] D. R. Edla, K. Mangalorekar, G. Dhavalikar, and S. Dodia, \"Classification of EEG data for human mental state analysis using Random Forest Classifier,\" Procedia Comput. Sci., vol. 132, pp. 1523–1532, 2018. [5] S. W. Purnami et al., “Mental state classification based on electroencephalogram (EEG) using multiclass support vector machine,” Heliyon, vol. 7, no. 1, p. e05927, Jan. 2021. [6] Z. Ahmed et al., \"Psychiatric disorders from EEG signals through deep learning models,\" IBRO Neurosci. Rep., vol. 17, pp. 300–310, Dec. 2024. [7] T. Kotkar, K. Nagpure, P. Phadke, S. Patil, and R. P. K, \"Analysis of EEG Signals using Machine Learning for Prediction and Detection of Stress,\" in Smart Innovation, Systems and Technologies, vol. 317, Singapore: Springer, 2022. [8] Z. Liu and J. Zhao, \"Leveraging deep learning for robust EEG analysis in mental health monitoring,\" Front. Neuroinform., vol. 18, p. 1494970, Jan. 2025. [9] Y. Xu et al., \"Depressive Disorder Recognition Based on Frontal EEG Signals and Deep Learning,\" Sensors, vol. 23, no. 20, p. 8639, Oct. 2023. [10] K. Natarajan, R. Acharya U, F. Alias, T. Tiboleng, and S. K. Puthusserypady, \"Nonlinear analysis of EEG signals at different mental states,\" BioMed. Eng. OnLine, vol. 3, no. 1, p. 7, Mar. 2004.

Download Paper

Paper Id : IJRASET79167

Publish Date : 2026-03-31

ISSN : 2321-9653

Publisher Name : IJRASET

DOI Link : Click Here

Whatsapp Submit Paper Online