Enhancing EEG based cognitive state classification using graph Fourier transform

Shweta Sharma; Ayushi Kotwal; Rajneet Kaur Bijral; Vinod Sharma; Jatinder Manhas; Shweta Sharma; Ayushi Kotwal; Rajneet Kaur Bijral; Vinod Sharma; Jatinder Manhas

doi:10.3934/Neuroscience.2026011

AIMS Neuroscience

2026, Volume 13, Issue 2: 263-276. doi: 10.3934/Neuroscience.2026011

Previous Article Next Article

Research article

Enhancing EEG based cognitive state classification using graph Fourier transform

Department of Computer Science & IT, University of Jammu, Jammu & Kashmir, India

Received: 28 January 2026 Revised: 11 April 2026 Accepted: 24 April 2026 Published: 15 May 2026

Electroencephalography (EEG) based cognitive state classification has been widely explored with deep-learning models demonstrating remarkable performance. Deep-learning models need high computational resources and large datasets, creating a need for an alternative methodology. Graph signal processing (GSP) techniques provide an effective lightweight alternative by capturing spatial dependencies across the channels. This study investigates the effectiveness of GSP-based graph Fourier transform (GFT) features on a publicly available EEG mental arithmetic task (EEGMAT) dataset. A strict 5-fold cross-validation has been used as an evaluation technique. GFT is applied to extract spatial-spectral features by modeling EEG-channels as graph nodes. The extracted features have been evaluated using multiple classifiers including Random Forest (RF), Extreme Gradient Boosting (XGB), Decision Tree (DT), and Logistic Regression (LR). Statistical analysis confirms the significance of GFT features compared to raw signals. RF gave the highest accuracy of approximately 99 percent. Model interpretability based on Shapley additive explanations (SHAP) revealed that the frontal and central regions contributed to the classification aligning with the findings of cognitive neuroscientists.
- EEG,
- graph Fourier transform (GFT),
- graph signal processing (GSP),
- machine learning,
- SHAP
Citation: Shweta Sharma, Ayushi Kotwal, Rajneet Kaur Bijral, Vinod Sharma, Jatinder Manhas. Enhancing EEG based cognitive state classification using graph Fourier transform[J]. AIMS Neuroscience, 2026, 13(2): 263-276. doi: 10.3934/Neuroscience.2026011

Related Papers:

Abstract

Electroencephalography (EEG) based cognitive state classification has been widely explored with deep-learning models demonstrating remarkable performance. Deep-learning models need high computational resources and large datasets, creating a need for an alternative methodology. Graph signal processing (GSP) techniques provide an effective lightweight alternative by capturing spatial dependencies across the channels. This study investigates the effectiveness of GSP-based graph Fourier transform (GFT) features on a publicly available EEG mental arithmetic task (EEGMAT) dataset. A strict 5-fold cross-validation has been used as an evaluation technique. GFT is applied to extract spatial-spectral features by modeling EEG-channels as graph nodes. The extracted features have been evaluated using multiple classifiers including Random Forest (RF), Extreme Gradient Boosting (XGB), Decision Tree (DT), and Logistic Regression (LR). Statistical analysis confirms the significance of GFT features compared to raw signals. RF gave the highest accuracy of approximately 99 percent. Model interpretability based on Shapley additive explanations (SHAP) revealed that the frontal and central regions contributed to the classification aligning with the findings of cognitive neuroscientists.

Conflict of interest

The authors declare no conflict of interest.

Authors' contributions

Shweta Sharma: Research scholar in University of Jammu. She conceptualized the study, conducted the experiments and wrote the original draft. Ayushi Kotwal: Research scholar in University of Jammu. She assisted in development of the algorithm and experiments. Rajneet K Bijral: Assistant professor in University of Jammu. Contributed in writing, editing and finalizing the manuscript. Vinod Sharma: Professor in University of Jammu. Provided supervision and guidance at every step. Jatinder Manhas: Professor in University of Jammu. Provided supervision and guidance in EEG-related experimentation. All authors approved the final version for publication.

References

[1]	Sanei S, Chambers JA (2013) EEG signal processing. John Wiley & Sons.
[2]	Qin Y, Zhang Y, Zhang Y, et al. (2023) Application and development of EEG acquisition and feedback technology: a review. Biosensors (Basel) 13: 930. https://doi.org/10.3390/bios13100930
[3]	He C, Chen YY, Phang CR, et al. (2023) Diversity and suitability of the state-of-the-art wearable and wireless EEG systems review. IEEE J Biomed Health Inform 27: 3830-3843. https://doi.org/10.1109/jbhi.2023.3239053
[4]	Zhou M, Tian C, Cao R, et al. (2018) Epileptic seizure detection based on EEG signals and CNN. Front Neuroinform 12: 95. https://doi.org/10.3389/fninf.2018.00095
[5]	Kotwal A, Sharma V, Manhas J (2023) Deep neural based learning of EEG features using spatial, temporal and spectral dimensions across different cognitive workload of human brain: dimensions, methodologies, research challenges and future scope. International Conference on Emerging Trends in Expert Applications & Security . Singapore: Springer Nature Singapore 61-69. https://doi.org/10.1007/978-981-99-1946-8_7
[6]	Blanco-Diaz CF, Guerrero-Mendez CD, Furtado GR, et al. (2024) Deep learning approach for EEG classification in lower-limb movement phases: towards enhanced brain-computer interface control. IEEE 2024: 1-7. https://doi.org/10.1109/mesa61532.2024.10704914
[7]	Jenke R, Peer A, Buss M (2014) Feature extraction and selection for emotion recognition from EEG. IEEE Trans Affect Comput 5: 327-339. https://doi.org/10.1109/taffc.2014.2339834
[8]	Al-Fahoum AS, Al-Fraihat AA (2014) Methods of EEG signal features extraction using linear analysis in frequency and time-frequency domains. ISRN Neurosci 2014: 730218. https://doi.org/10.1155/2014/730218
[9]	Lim SH, Nisar H, Thee KW, et al. (2018) A novel method for tracking and analysis of EEG activation across brain lobes. Biomed Signal Process Control 40: 488-504. https://doi.org/10.1016/j.bspc.2017.06.017
[10]	Antolínez D, Cisnal A, Martínez-Cagigal V, et al. (2025) Development and validation of an affordable wearable multichannel EEG system with active electrodes and innovative flexible headbands. IEEE Access 13: 83983-83995. https://doi.org/10.1109/access.2025.3568302
[11]	Khosla A, Khandnor P, Chand T (2020) A comparative analysis of signal processing and classification methods for different applications based on EEG signals. Biocybern Biomed Eng 40: 649-690. https://doi.org/10.1016/j.bbe.2020.02.002
[12]	Tuncer T, Dogan S, Ertam F, et al. (2020) A novel ensemble local graph structure based feature extraction network for EEG signal analysis. Biomed Signal Process Control 61: 102006. https://doi.org/10.1016/j.bspc.2020.102006
[13]	Rahman SMA, Khalil MI, Zhou H, et al. (2025) Advancement in graph neural networks for EEG signal analysis and application: a review. IEEE Access . https://doi.org/10.1109/access.2025.3549120
[14]	Zarjam P, Epps J, Lovell NH (2015) Beyond subjective self-rating: EEG signal classification of cognitive workload. IEEE Trans Auton Ment Dev 7: 301-310. https://doi.org/10.1109/tamd.2015.2441960
[15]	Elkerdawy M, Elhalaby M, Hassan A, et al. (2020) Building cognitive profiles of learners using EEG. IEEE 2020: 027-032. https://doi.org/10.1109/ICICS49469.2020.239535
[16]	Apicella A, Arpaia P, Frosolone M, et al. (2022) EEG-based measurement system for monitoring student engagement in learning 4.0. Sci Rep 12: 5857. https://doi.org/10.1038/s41598-022-09578-y
[17]	Chakladar DD, Roy PP, Iwamura M (2021) EEG-based cognitive state classification and analysis of brain dynamics using deep ensemble model and graphical brain network. IEEE Trans Auton Ment Dev 14: 1507-1519. https://doi.org/10.1109/tcds.2021.3116079
[18]	Chakladar DD, Dey S, Roy PP, et al. (2020) EEG-based mental workload estimation using deep BLSTM-LSTM network and evolutionary algorithm. Biomed Signal Process Contr 60: 101989. https://doi.org/10.1016/j.bspc.2020.101989
[19]	Bhuiyan MK, Bayesh MR, Das S (2024) Enhancing E-learning: EEG signal classification to evaluate students' Understanding of online lectures. IEEE 2024: 13-18. https://doi.org/10.1109/iceeict62016.2024.10534580
[20]	Adhikari S, Choudhury N, Bhattacharya S, et al. (2025) Analysis of frequency domain features for the classification of evoked emotions using EEG signals. Exp Brain Res 243: 65. https://doi.org/10.1007/s00221-025-07002-1
[21]	‌Choudhury N, Das D, Deka D, et al. (2026) NeuroFeat: An adaptive neurological EEG feature engineering approach for improved classification of major depressive disorder. Biomed Signal Process Contr 113: 109031. https://doi.org/10.1016/j.bspc.2025.109031
[22]	Hallal L, Rhinelander J, Venkat R, et al. (2026) Efficient feature extraction for EEG-based classification: a comparative review of deep learning models. AI 7: 50. https://doi.org/10.3390/ai7020050
[23]	‌Sharma R, Meena HK (2023) Utilizing graph signal-processing-based spectrum to classify mental tasks with multichannel EEG signals. IEEE Sens J 24: 3952-3959. https://doi.org/10.1109/jsen.2023.3337519
[24]	Jiao M, Wan G, Guo Y, et al. (2022) A graph fourier transform based bidirectional long short-term memory neural network for electrophysiological source imaging. Front Neurosci 16: 867466. https://doi.org/10.3389/fnins.2022.867466
[25]	Gangapuram H, Manian V (2024) Electroencephalogram functional connectivity analysis and classification of mental arithmetic working memory task. Signals 5: 296-325. https://doi.org/10.3390/signals5020016
[26]	Mathur P, Chakka VK (2022) Graph signal processing based cross-subject mental task classification using multi-channel EEG signals. IEEE Sens J 22: 7971-7978. https://doi.org/10.1109/jsen.2022.3156152
[27]	Zyma I, Tukaev S, Seleznov I, et al. (2019) Electroencephalograms during mental arithmetic task performance. Data 4: 14. https://doi.org/10.3390/data4010014

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)