Natural and Horizontal Visibility Graphs of EEG Power Spectra for Autism Spectrum Disorder Classification
Downloads
Autism spectrum disorder (ASD) is primarily identified through behavioral and developmental assessment, which may require specialist expertise and considerable time. Electroencephalography (EEG) offers non-invasive neurophysiological information, but reliable ASD classification remains challenging because EEG signals are nonstationary and highly variable across individuals. This study evaluates whether visibility-graph topology derived from EEG power spectral density (PSD) curves provides complementary information beyond conventional spectral descriptors. Resting-state EEG from the Banda Aceh dataset (7 ASD and 7 typically developing participants, 250 Hz) and the KAU dataset (8 ASD and 8 control participants, 256 Hz) were processed independently. Preprocessing included quality inspection, 0.5–45-Hz zero-phase filtering, dataset-specific 50/60-Hz notch filtering, common average referencing, and non-overlapping 30-s segmentation. Welch PSD was estimated using 2-s Hann windows with 50% overlap across five frequency bands. Direct PSD, natural visibility graph features, and horizontal visibility graph features were compared using RBF-SVM and a six-hidden-layer MLP. Evaluation used subject-wise balanced cross-validation, with performance calculated at the epoch level from participant-disjoint outer-test folds. VG-NVG-PSD with SVM achieved the best observed accuracy of 97.14 ± 3.29% on Banda Aceh, representing a 0.97-percentage-point numerical gain over direct PSD-SVM. VG-HVG-PSD with SVM achieved 96.83 ± 2.34% on KAU, representing a 0.35-percentage-point gain. SVM produced the highest observed configuration on both datasets, whereas graph-spectral transformation did not consistently improve MLP performance. Bonferroni-corrected pairwise comparisons did not establish statistical superiority among individual methods. These findings indicate that PSD-derived visibility graphs provide an interpretable complementary representation for EEG-based ASD classification, although the preferred visibility criterion was dataset-dependent. Larger cohorts and external validation are required before clinical generalization
[1] American Psychiatric Association, Diagnostic and Statistical Manual of Mental Disorders, 5th ed., text rev. Washington, DC, USA: American Psychiatric Association Publishing, 2022, doi: 10.1176/appi.books.9780890425787.
[2] C. Lord et al., “The Lancet Commission on the future of care and clinical research in autism,” Lancet, vol. 399, no. 10321, pp. 271–334, Jan. 2022, doi: 10.1016/S0140-6736(21)01541-5.
[3] K. A. Shaw et al., “Prevalence and early identification of autism spectrum disorder among children aged 4 and 8 years: Autism and Developmental Disabilities Monitoring Network, 16 sites, United States, 2022,” MMWR Surveill. Summ., vol. 74, no. 2, pp. 1–22, Apr. 2025, doi: 10.15585/mmwr.ss7402a1.
[4] J. Zeidan et al., “Global prevalence of autism: A systematic review update,” Autism Res., vol. 15, no. 5, pp. 778–790, May 2022, doi: 10.1002/aur.2696.
[5] M. Milovanovic and R. Grujicic, “Electroencephalography in assessment of autism spectrum disorders: A review,” Front. Psychiatry, vol. 12, Art. no. 686021, Sep. 2021, doi: 10.3389/fpsyt.2021.686021.
[6] J. Li, X. Kong, L. Sun, X. Chen, G. Ouyang, X. Li, and S. Chen, “Identification of autism spectrum disorder based on electroencephalography: A systematic review,” Comput. Biol. Med., vol. 170, Art. no. 108075, Mar. 2024, doi: 10.1016/j.compbiomed.2024.108075.
[7] P. Garcés et al., “Resting state EEG power spectrum and functional connectivity in autism: A cross-sectional analysis,” Mol. Autism, vol. 13, Art. no. 22, May 2022, doi: 10.1186/s13229-022-00500-x.
[8] W. S. Neo, D. Foti, B. Keehn, and B. Kelleher, “Resting-state EEG power differences in autism spectrum disorder: A systematic review and meta-analysis,” Transl. Psychiatry, vol. 13, Art. no. 389, Dec. 2023, doi: 10.1038/s41398-023-02681-2.
[9] M. Parsa et al., “EEG-based classification of individuals with neuropsychiatric disorders using deep neural networks: A systematic review of current status and future directions,” Comput. Methods Programs Biomed., vol. 240, Art. no. 107683, Oct. 2023, doi: 10.1016/j.cmpb.2023.107683.
[10] A. Anuragi, D. S. Sisodia, and R. B. Pachori, “Mitigating the curse of dimensionality using feature projection techniques on electroencephalography datasets: An empirical review,” Artif. Intell. Rev., vol. 57, Art. no. 75, 2024, doi: 10.1007/s10462-024-10711-8.
[11] M. Baygin et al., “Automated ASD detection using hybrid deep lightweight features extracted from EEG signals,” Comput. Biol. Med., vol. 134, Art. no. 104548, Jul. 2021, doi: 10.1016/j.compbiomed.2021.104548.
[12] B. Ari, N. Sobahi, Ö. F. Alçin, A. Şengür, and U. R. Acharya, “Accurate detection of autism using Douglas-Peucker algorithm, sparse coding based feature mapping and convolutional neural network techniques with EEG signals,” Comput. Biol. Med., vol. 143, Art. no. 105311, Apr. 2022, doi: 10.1016/j.compbiomed.2022.105311.
[13] M. N. A. Tawhid, S. Siuly, H. Wang, F. Whittaker, K. Wang, and Y. Zhang, “A spectrogram image based intelligent technique for automatic detection of autism spectrum disorder from EEG,” PLoS One, vol. 16, no. 6, Art. no. e0253094, Jun. 2021, doi: 10.1371/journal.pone.0253094.
[14] L. Shi, L. Ma, J. Zhao, Z. Kuang, S. Wang, H. Yang, H. Wang, Q. Han, and L. Sun, “TFSNet: A time-frequency synergy network based on EEG signals for autism spectrum disorder classification,” Brain Sci., vol. 15, no. 7, Art. no. 684, Jun. 2025, doi: 10.3390/brainsci15070684.
[15] A. Belhadi, P. G. Lind, Y. Djenouri, and A. Yazidi, “Enhanced visibility graph for EEG classification,” Front. Neurosci., vol. 19, Art. no. 1541062, May 2025, doi: 10.3389/fnins.2025.1541062.
[16] T. Kong, J. Shao, J. Hu, X. Yang, S. Yang, and R. Malekian, “EEG-based emotion recognition using an improved weighted horizontal visibility graph,” Sensors, vol. 21, no. 5, Art. no. 1870, Mar. 2021, doi: 10.3390/s21051870.
[17] H. Azizi and S. Sulaimany, “A review of visibility graph analysis,” IEEE Access, vol. 12, pp. 93517–93530, 2024, doi: 10.1109/ACCESS.2024.3401485.
[18] G. Brookshire et al., “Data leakage in deep learning studies of translational EEG,” Front. Neurosci., vol. 18, Art. no. 1373515, May 2024, doi: 10.3389/fnins.2024.1373515.
[19] H. T. Lee, H. R. Cheon, S. H. Lee, M. Shim, and H. J. Hwang, “Risk of data leakage in estimating the diagnostic performance of a deep-learning-based computer-aided system for psychiatric disorders,” Sci. Rep., vol. 13, Art. no. 16633, Oct. 2023, doi: 10.1038/s41598-023-43542-8.
[20] M. Melinda, P. D. Purnamasari, F. Fahmi, E. P. Sinulingga, M. Muliyadi, Y. Away, Y. Yunidar, and F. H. Juwono, “A comprehensive EEG dataset and performance assessment for autism spectrum disorder,” Sci. Rep., vol. 15, Art. no. 34981, Oct. 2025, doi: 10.1038/s41598-025-18934-7.
[21] M. J. Alhaddad, M. I. Kamel, H. M. Malibary, E. A. Alsaggaf, K. Thabit, F. Dahlwi, and A. A. Hadi, “Diagnosis autism by Fisher linear discriminant analysis FLDA via EEG,” Int. J. Bio-Sci. Bio-Technol., vol. 4, no. 2, pp. 45–54, Jun. 2012.
[22] F. Fahmi, M. Melinda, P. D. Purnamasari, E. Elizar, and A. Rafiki, “Recognition of EEG features in autism disorder using SWT and Fisher linear discriminant analysis,” Diagnostics, vol. 15, no. 18, Art. no. 2291, Sep. 2025, doi: 10.3390/diagnostics15182291.
[23] P. Chawla, S. B. Rana, H. Kaur, and K. Singh, “Diagnosis of autism spectrum disorder using EEMD and multiscale fluctuation based dispersion entropy with Bayesian optimized LightGBM,” Multimed. Tools Appl., vol. 83, no. 24, pp. 65341–65362, 2024, doi: 10.1007/s11042-023-18059-x.
[24] M. O’Sullivan, A. Temko, A. Bocchino, C. O’Mahony, G. Boylan, and E. Popovici, “Analysis of a low-cost EEG monitoring system and dry electrodes toward clinical use in the neonatal ICU,” Sensors, vol. 19, no. 11, Art. no. 2637, Jun. 2019, doi: 10.3390/s19112637.
[25] M. E. Peltola et al., “Routine and sleep EEG: Minimum recording standards of the International Federation of Clinical Neurophysiology and the International League Against Epilepsy,” Clin. Neurophysiol., vol. 147, pp. 108–120, 2023, doi: 10.1016/j.clinph.2023.01.002.
[26] A. Chaddad, Y. Wu, R. Kateb, and A. Bouridane, “Electroencephalography signal processing: A comprehensive review and analysis of methods and techniques,” Sensors, vol. 23, no. 14, Art. no. 6434, Jul. 2023, doi: 10.3390/s23146434.
[27] P. D. Welch, “The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms,” IEEE Trans. Audio Electroacoust., vol. 15, no. 2, pp. 70–73, Jun. 1967, doi: 10.1109/TAU.1967.1161901.
[28] L. Lacasa, B. Luque, F. Ballesteros, J. Luque, and J. C. Nuño, “From time series to complex networks: The visibility graph,” Proc. Natl. Acad. Sci. USA, vol. 105, no. 13, pp. 4972–4975, Apr. 2008, doi: 10.1073/pnas.0709247105.
[29] B. Luque, L. Lacasa, F. Ballesteros, and J. Luque, “Horizontal visibility graphs: Exact results for random time series,” Phys. Rev. E, vol. 80, no. 4, Art. no. 046103, Oct. 2009, doi: 10.1103/PhysRevE.80.046103.
[30] S. Sulaimany and Z. Safahi, “Visibility graph analysis for brain: Scoping review,” Front. Neurosci., vol. 17, Art. no. 1268485, Sep. 2023, doi: 10.3389/fnins.2023.1268485.
[31] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.
[32] I. H. Sarker, “Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions,” SN Comput. Sci., vol. 2, no. 6, Art. no. 420, 2021, doi: 10.1007/s42979-021-00815-1.
[33] F. Del Pup, A. Zanola, L. F. Tshimanga, A. Bertoldo, L. Finos, and M. Atzori, “The role of data partitioning on the performance of EEG-based deep learning models in supervised cross-subject analysis: A preliminary study,” Comput. Biol. Med., vol. 196, Art. no. 110608, 2025, doi: 10.1016/j.compbiomed.2025.110608.
[34] S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, Art. no. 100804, Sep. 2023, doi: 10.1016/j.patter.2023.100804.
[35] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, Art. no. 6086, Mar. 2024, doi: 10.1038/s41598-024-56706-x.
[36] N. Alotaibi and K. Maharatna, “Classification of autism spectrum disorder from EEG-based functional brain connectivity analysis,” Neural Comput., vol. 33, no. 7, pp. 1914–1941, Jul. 2021, doi: 10.1162/neco_a_01394.
[37] M. Z. Ullah and D. Yu, “Grid-tuned ensemble models for 2D spectrogram-based autism classification,” Biomed. Signal Process. Control, vol. 93, Art. no. 106151, Jul. 2024, doi: 10.1016/j.bspc.2024.106151.
[38] S. Alhassan, A. Soudani, and M. Almusallam, “Energy-efficient EEG-based scheme for autism spectrum disorder detection using wearable sensors,” Sensors, vol. 23, no. 4, Art. no. 2228, Feb. 2023, doi: 10.3390/s23042228.
[39] A. J. O. Dede, W. Xiao, N. Vaci, M. X. Cohen, and E. Milne, “Exploring EEG resting state differences in autism: Sparse findings from a large cohort,” Mol. Autism, vol. 16, Art. no. 13, Feb. 2025, doi: 10.1186/s13229-025-00647-3.
[40] J. M. Mayor-Torres, S. Medina-DeVilliers, T. Clarkson, M. D. Lerner, and G. Riccardi, “Evaluation of interpretability for deep learning algorithms in EEG emotion recognition: A case study in autism,” Artif. Intell. Med., vol. 143, Art. no. 102545, Sep. 2023, doi: 10.1016/j.artmed.2023.102545.
Copyright (c) 2026 Melinda Melinda, Muhammad Saifullah Nur, Yuwaldi Away, Siti Rusdiana, Souvik Das, Zulfan Zulfan (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
