Graph signal processing approaches for EEG-based neural pattern discovery
Dhanaji Waghdrdhanajiwagh@gmail.comDepartment of PhysiologyKrishna Institute of Medical SciencesKrishna Vishwa Vidyapeeth (Deemed to be University)Karad, Maharashtra, 415539, IndiaView full profile → , *Varun Kumar SharmaCorresponding authorvarun1.sharma@niu.edu.inDepartment of Biotechnology and MicrobiologyNoida International UniversityGreater Noida, Uttar Pradesh, 201312, IndiaView full profile → , Sathyabalaji Kannansathyabalaji.kannan@vit.eduDepartment of Engineering Science and HumanitiesVishwakarma Institute of TechnologyPune, Maharashtra, 411037, IndiaView full profile → , Yogash Chandra Joshiyogashchandra1508@vardhaman.orgDepartment of Computer Science and Engineering (Artificial Intelligence & Machine Learning)Vardhaman College of EngineeringShamshabad, Hyderabad, Telangana, 501218, IndiaView full profile → , G. Saralasaralag@maher.ac.inDepartment of NeurologyMeenakshi Medical College Hospital and Research InstituteMeenakshi Academy of Higher Education & ResearchChennai, Tamil Nadu, 600087, IndiaView full profile → , Sharyu Ikharsharyuikhar@researcherconnect.comResearcher Connect Innovations and Impact Private LimitedNagpur, Maharashtra, 440028, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Mar 2026
- Published Online:
- 31 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2490
- Pages:
- 3631–3644
Abstract
EEG is a non-invasive tool to study complex activity of neurons, but traditional signal processing techniques typically process individual EEG channels separately and fail to adequately model spatial and functional relationships between brain regions. In this paper, we introduce a Graph Signal Processing Graph Attention Network (GSP – GAT) framework for the EEG-based neural pattern discovery and classification. Multichannel EEG signals are preprocessed, segmented and displayed as functional connectivity graphs, where electrodes are nodes and the relationship between channels are weighted edges. Global, local, and multiscale spatial–spectral characteristics are extracted using the graph Fourier Transform, graph spectral energy analysis, graph filtering and graph wavelet analysis. Through comparative and ablation analyses, we show the potential advantages of explicit graph signal representations and attention-based graph learning over regular machine learning, deep learning and standalone graph-based methods. Comparative and ablation analyses illustrate the potential benefits of combining explicit graph signal representations with attention-based graph learning, compared to regular machine learning, deep learning and standalone graph-based methods. The proposed framework is an effective and comprehensible approach to neural pattern discovery and has the potential to be applied in brain–computer interfaces, cognitive-state recognition, neurological assessment, seizure analysis, and other intelligent systems that rely on EEG.
Keywords
Subject Classifications
References
[1] A. Samara, L. Galway, R. Bond, and H. Wang, “Affective state detection via facial expression analysis within a human–computer interaction context,” J. Ambient Intell. Humaniz. Comput., vol. 10, no. 6, pp. 2175–2184 (2019), doi: 10.1007/s12652-017-0636-8.
[2] X. Wang, M. Hersche, M. Magno, and L. Benini, “MI-BMInet: An efficient convolutional neural network for motor imagery brain–machine interfaces with EEG channel selection,” IEEE Sens. J., vol. 24, no. 6, pp. 8835–8847 (2024), doi: 10.1109/JSEN.2024.3353146.
[3] P. A. Constable, J. O. Pinzon-Arenas, L. R. Mercado Diaz, I. O. Lee, F. Marmolejo-Ramos, L. Loh, A. Zhdanov, M. Kulyabin, M. Brabec, D. H. Skuse, D. A. Thompson, and H. Posada-Quintero, “Spectral analysis of light-adapted electroretinograms in neurodevelopmental disorders: Classification with machine learning,” Bioengineering, vol. 12, no. 1, Art. no. 15 (2025), doi: 10.3390/bioengineering12010015.
[4] I. A. Hurjui, R. M. Hurjui, L. L. Hurjui, I. L. Serban, I. Dobrin, M. Apostu, and R. P. Dobrin, “Biomarkers and neuropsychological tools in attention-deficit/hyperactivity disorder: From subjectivity to precision diagnosis,” Medicina, vol. 61, no. 7, Art. no. 1211 (2025), doi: 10.3390/medicina61071211.
[5] S. M. Manjur, L. R. M. Diaz, I. O. Lee, D. H. Skuse, D. A. Thompson, F. Marmolejo-Ramos, P. A. Constable, and H. F. Posada-Quintero, “Detecting autism spectrum disorder and attention deficit hyperactivity disorder using multimodal time-frequency analysis with machine learning using the electroretinogram,” J. Autism Dev. Disord., vol. 55, no. 4, pp. 1365–1378 (2025), doi: 10.1007/s10803-024-06290-w.
[6] X. Gong and X. Li, “Human–robot interactive communication and cognitive psychology intelligent decision system based on artificial intelligence—Case study,” Int. J. Humanoid Robot., vol. 20, Art. no. 2240005 (2023).
[7] H. Liu, Y. Cheng, S. Gao, and H. Yang, “A large-scale optimization method based on gradient approximation and hybrid grouping,” J. Inf. Optim. Sci., vol. 47, no. 6, pp. 2165–2191 (2026), doi: 10.47974/JIOS-2005.
[8] S. M. S. A. Abdullah, S. Y. A. Ameen, M. A. M. Sadeeq, and S. Zeebaree, “Multimodal emotion recognition using deep learning,” J. Appl. Sci. Technol. Trends, vol. 2, no. 1, pp. 73–79 (2021), doi: 10.38094/jastt20291
[9] S. V. Faraone et al., “Attention-deficit/hyperactivity disorder,” Nat. Rev. Dis. Primers, vol. 10, Art. no. 11 (2024).
[10] P. A. Constable, E. R. Ritvo, A. R. Ritvo, et al., “Light-adapted electroretinogram differences in autism spectrum disorder,” J. Autism Dev. Disord., vol. 50, no. 8, pp. 2874–2885 (2020), doi: 10.1007/s10803-020-04396-5.
[11] M. Soufineyestani, D. Dowling, and A. Khan, “Electroencephalography (EEG) technology applications and available devices,” Appl. Sci., vol. 10, no. 21, Art. no. 7453 (2020), doi: 10.3390/app10217453.
[12] K. Atiah, S. Nasiru, and S. Katara, “Chen proportional hazards model with application to lifetime data,” J. Stat. Manag. Syst., vol. 29, no. 3, pp. 231–254 (2026), doi: 10.47974/JSMS-1356.
[13] G. Li, C. H. Lee, J. J. Jung, Y. C. Youn, and D. Camacho, “Deep learning for EEG data analytics: A survey,” Concurr. Comput. Pract. Exp., vol. 32, no. 18, Art. no. e5199 (2020), doi: 10.1002/cpe.5199.
[14] I. O. Lee, D. H. Skuse, P. A. Constable, F. Marmolejo-Ramos, L. R. Olsen, and D. A. Thompson, “The electroretinogram b-wave amplitude: A differentical measure for neurodevelopmental disorders,” J. Neurodev. Disord., vol. 14, Art. no. 30 (2022).
