Subject-Level Aggregated Wavelet Packet Energy-Variance Features for EEG-Based Autism Spectrum Disorder Classification

Zaky Naufal; Melinda Melinda; Siti Rusdiana; Yunidar Yunidar; Aufa Rafiki; Lola Vivita

doi:10.35882/jeeemi.v8i4.1908

Zaky Naufal Department of Electrical and Computer Engineering, Faculty of Engineering, Universitas Syiah Kuala, Jalan Teuku Nyak Arief Darussalam, Banda Aceh 23111, Indonesia https://orcid.org/0009-0000-0696-5338
Melinda Melinda Department of Electrical and Computer Engineering, Faculty of Engineering, Universitas Syiah Kuala, Banda Aceh, Indonesia https://orcid.org/0000-0001-9082-6639
Siti Rusdiana Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia https://orcid.org/0000-0002-3501-8521
Yunidar Yunidar Department of Electrical and Computer Engineering, Faculty of Engineering, Universitas Syiah Kuala, Jalan Teuku Nyak Arief Darussalam, Banda Aceh 23111, Indonesia https://orcid.org/0009-0008-4453-9215
Aufa Rafiki Department of Electrical and Computer Engineering, Faculty of Engineering, Universitas Syiah Kuala, Jalan Teuku Nyak Arief Darussalam, Banda Aceh 23111, Indonesia https://orcid.org/0009-0008-3031-8008
Lola Vivita Banda Aceh City Regional Development Planning Agency, Banda Aceh 23243, Indonesia https://orcid.org/0009-0009-0560-7091

DOI: https://doi.org/10.35882/jeeemi.v8i4.1908

Keywords: Wavelet Packet Transform, Subject-level aggregation, Infomax ICA, LOSO cross-validation, Logistic Regression

Abstract

This study addresses a key clinical challenge in EEG-based autism spectrum disorder (ASD) diagnosis: most prior work reports accuracy at the window level, whereas the clinical diagnostic unit is the individual subject, a mismatch that can inflate performance estimates. We develop and validate a subject-level EEG feature aggregation framework, combining Wavelet Packet Transform (WPT) energy-variance features, fold-safe ANOVA feature selection, and per-subject aggregation, evaluated under leakage-safe nested leave-one-subject-out (LOSO) cross-validation. Sixteen-channel EEG was recorded from 16 participants (8 ASD, 8 neurotypical) in Banda Aceh, Indonesia, using a single OpenBCI Cyton board with a Daisy module for native simultaneous 16-channel acquisition, preprocessed with Infomax ICA artifact removal, and classified using Logistic Regression. The framework achieved a nested LOSO balanced accuracy of 93.75% (F1 = 0.9412); because this estimate derives from only 16 subjects, the repeated subject-pair evaluation (balanced accuracy 0.9525 ± 0.0529, AUC 0.9897 ± 0.0163, permutation p = 0.0196) is treated as the primary robustness indicator. A learning-curve analysis indicated that performance approaches, but has not fully reached, a plateau at this cohort size. Sensitivity analyses across nine window/overlap configurations and six wavelets, selected within the nested cross-validation, confirmed the result was not selection-dependent. A controlled ablation indicated Infomax ICA outperformed MSICA-DWT (Wilcoxon p < 0.001), though a participant-level bootstrap interval was wide and included zero, reflecting the limited power of the 16-subject cohort. Overall, these results demonstrate the methodological feasibility of subject-level WPT energy-variance aggregation for leakage-safe ASD screening research rather than diagnostic readiness, and external multicenter validation on larger, demographically characterized cohorts is required before any clinical use.

Downloads

Download data is not yet available.

References

C. J. L. Murray and GBD 2021 Collaborators, “Findings from the Global Burden of Disease Study 2021,” Lancet, vol. 403, no. 10440, pp. 2259–2262, May 2024, doi: 10.1016/S0140-6736(24)00769-4.

J. Li et al., “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.

S. Das et al., “Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review,” Prog. Neuropsychopharmacol. Biol. Psychiatry, vol. 123, Art. no. 110705, Apr. 2023, doi: 10.1016/j.pnpbp.2022.110705.

S. J. Webb et al., “The Autism Biomarkers Consortium for Clinical Trials: Initial evaluation of a battery of candidate EEG biomarkers,” Am. J. Psychiatry, vol. 180, no. 1, pp. 41–49, Jan. 2023, doi: 10.1176/appi.ajp.21050485.

X. Geng et al., “Abnormalities of EEG functional connectivity and effective connectivity in children with autism spectrum disorder,” Brain Sci., vol. 13, no. 1, Art. no. 130, Jan. 2023, doi: 10.3390/brainsci13010130.

S. Kurkin et al., “Features of the resting-state functional brain network of children with autism spectrum disorder: EEG source-level analysis,” Eur. Phys. J. Spec. Top., vol. 232, no. 5, pp. 683–693, 2023, doi: 10.1140/epjs/s11734-022-00717-0.

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.

J. Shan et al., “A scoping review of physiological biomarkers in autism,” Front. Neurosci., vol. 17, Art. no. 1269880, Sep. 2023, doi: 10.3389/fnins.2023.1269880.

B. Sun et al., “Identification of diagnostic markers for ASD: A restrictive interest analysis based on EEG combined with eye tracking,” Front. Neurosci., vol. 17, Art. no. 1236637, Oct. 2023, doi: 10.3389/fnins.2023.1236637.

B. Sun et al., “Interest paradigm for early identification of autism spectrum disorder: An analysis from electroencephalography combined with eye tracking,” Front. Neurosci., vol. 18, Art. no. 1502045, Nov. 2024, doi: 10.3389/fnins.2024.1502045.

L. Bogéa Ribeiro and M. da Silva Filho, “Systematic review on EEG analysis to diagnose and treat autism by evaluating functional connectivity and spectral power,” Neuropsychiatr. Dis. Treat., vol. 19, pp. 415–424, 2023, doi: 10.2147/NDT.S394363.

P. Garcés et al., “Resting state EEG power spectrum and functional connectivity in autism: A cross-sectional analysis,” Mol. Autism, vol. 13, no. 1, Art. no. 22, May 2022, doi: 10.1186/s13229-022-00500-X.

S. Y. Ke et al., “Classification of autism spectrum disorder using electroencephalography in Chinese children: A cross-sectional retrospective study,” Front. Neurosci., vol. 18, Art. no. 1330556, Jan. 2024, doi: 10.3389/fnins.2024.1330556.

J. Rogala et al., “Enhancing autism spectrum disorder classification in children through the integration of traditional statistics and classical machine learning techniques in EEG analysis,” Sci. Rep., vol. 13, no. 1, Art. no. 21748, Dec. 2023, doi: 10.1038/s41598-023-49048-7.

Y. Xu, Z. Yu, Y. Li, Y. Liu, Y. Li, and Y. Wang, “Autism spectrum disorder diagnosis with EEG signals using time series maps of brain functional connectivity and a combined CNN–LSTM model,” Comput. Methods Programs Biomed., vol. 250, Art. no. 108196, Jun. 2024, doi: 10.1016/j.cmpb.2024.108196.

N. K. Al-Qazzaz, A. A. Aldoori, A. K. Buniya, S. H. B. M. Ali, and S. A. Ahmad, “Transfer learning and hybrid deep convolutional neural networks models for autism spectrum disorder classification from EEG signals,” IEEE Access, vol. 12, pp. 64510–64530, 2024, doi: 10.1109/ACCESS.2024.3396869.

L. Shi et al., “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.

W. Hu, G. Jiang, J. Han, X. Li, and P. Xie, “Regional-asymmetric adaptive graph convolutional neural network for diagnosis of autism in children with resting-state EEG,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 32, pp. 200–211, 2024, doi: 10.1109/TNSRE.2023.3347134.

P. Chawla, S. B. Rana, H. Kaur, and K. Singh, “Computer-aided diagnosis of autism spectrum disorder from EEG signals using deep learning with FAWT and multiscale permutation entropy features,” Proc. Inst. Mech. Eng. H, vol. 237, no. 2, pp. 282–294, Feb. 2023, doi: 10.1177/09544119221141751.

G. Eroğlu, “Electroencephalography-based machine learning for biomarker detection in dyslexia and autism spectrum disorder: A comparative review of models, features, and diagnostic utility,” Diagnostics, vol. 15, no. 18, Art. no. 2388, Sep. 2025, doi: 10.3390/diagnostics15182388.

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.

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.

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, Sep. 2025, doi: 10.1016/j.compbiomed.2025.110608.

T. J. Bradshaw, Z. Huemann, J. Hu, and A. Rahmim, “A guide to cross-validation for artificial intelligence in medical imaging,” Radiol. Artif. Intell., vol. 5, no. 4, Art. no. e220232, Jul. 2023, doi: 10.1148/ryai.220232.

S. Luo, P. Ren, J. Wu, X. Wu, and X. Zhang, “Feature extraction method of EEG based on wavelet packet reconstruction and deep learning model of VR motion sickness feature classification and prediction,” PLoS One, vol. 19, no. 7, Art. no. e0305733, Jul. 2024, doi: 10.1371/journal.pone.0305733.

Q. M. Ud Din and A. K. Jayanthy, “Wavelet scattering transform and deep learning networks based autism spectrum disorder identification using EEG signals,” Traitement du Signal, vol. 39, no. 6, pp. 2069–2076, Dec. 2022, doi: 10.18280/TS.390619.

H. Albaqami, G. M. Hassan, A. Subasi, and A. Datta, “Automatic detection of abnormal EEG signals using wavelet feature extraction and gradient boosting decision tree,” Biomed. Signal Process. Control, vol. 70, Art. no. 102957, Sep. 2021, doi: 10.1016/j.bspc.2021.102957.

Y. Wang, C. Song, T. Zhang, Z. Yao, Z. Chang, and D. Wang, “Feature extraction of motor imagery EEG via discrete wavelet transform and generalized maximum fuzzy membership difference entropy: A comparative study,” Electronics, vol. 12, no. 10, Art. no. 2207, May 2023, doi: 10.3390/electronics12102207.

M. M. Rahmat, Y. Yunidar, and M. Melinda, “A comparative study of MSPCA and MSICA denoising for EEG based autism spectrum disorder classification using LightGBM and TCN-SA,” Int. J. Intell. Eng. Syst., vol. 19, no. 6, pp. 186–201, Jun. 2026, doi: 10.22266/ijies2026.0630.11.

M. Muliyadi, M. Melinda, Y. Away, S. Gazali, A. Rafiki, and W. K. Wong, “Bayesian-optimized Butterworth-PID preprocessing for EEG-based autism spectrum disorder classification,” IEEE Access, vol. 14, pp. 100364–100382, 2026, doi: 10.1109/ACCESS.2026.3709120.

J. Sabio, N. S. Williams, G. M. McArthur, and N. A. Badcock, “A scoping review on the use of consumer-grade EEG devices for research,” PLoS One, vol. 19, no. 3, Art. no. e0291186, Mar. 2024, doi: 10.1371/journal.pone.0291186.

M. Muliyadi, M. Melinda, Y. Away, S. Gazali, A. Rafiki, and W. K. Wong, “Temporal deep learning with multiscale principal component features for autism classification from electroencephalographic signals,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, vol. 8, no. 3, pp. 1239–1259, Jul. 2026, doi: 10.35882/jeeemi.v8i3.1735.

Z. Jamil, A. Jamil, and M. Majid, “Artifact removal from EEG signals recorded in non-restricted environment,” Biocybern. Biomed. Eng., vol. 41, no. 2, pp. 503–515, Apr. 2021, doi: 10.1016/j.bbe.2021.03.009.

P. Arpaia et al., “A systematic review of techniques for artifact detection and artifact category identification in electroencephalography from wearable devices,” Sensors, vol. 25, no. 18, Art. no. 5770, Sep. 2025, doi: 10.3390/s25185770.

S. S. Khan, J. S. Sudan, A. Pathak, R. Pandit, P. Rane, and A. K. Kumawat, “A review of EEG artifact removal methods for brain-computer interface applications,” Ingénierie des Systèmes d’Information, vol. 29, no. 1, pp. 247–252, Feb. 2024, doi: 10.18280/ISI.290124.

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.

R. R. Coifman and M. V. Wickerhauser, “Entropy-based algorithms for best basis selection,” IEEE Trans. Inf. Theory, vol. 38, no. 2, pp. 713–718, 1992, doi: 10.1109/18.119732.

O. A. Rosso et al., “Wavelet entropy: A new tool for analysis of short duration brain electrical signals,” J. Neurosci. Methods, vol. 105, no. 1, pp. 65–75, Jan. 2001, doi: 10.1016/S0165-0270(00)00356-3.

I. Guyon and A. Elisseeff, “An introduction to variable and feature selection,” J. Mach. Learn. Res., vol. 3, pp. 1157–1182, Mar. 2003. [Online]. Available: https://www.jmlr.org/papers/v3/guyon03a.html

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009, doi: 10.1007/978-0-387-84858-7.

M. Salmi, D. Atif, D. Oliva, A. Abraham, and S. Ventura, “Handling imbalanced medical datasets: Review of a decade of research,” Artif. Intell. Rev., vol. 57, no. 10, Art. no. 273, Sep. 2024, doi: 10.1007/s10462-024-10884-2.

T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.

J. A. Hanley and B. J. McNeil, “The meaning and use of the area under a receiver operating characteristic (ROC) curve,” Radiology, vol. 143, no. 1, pp. 29–36, 1982, doi: 10.1148/radiology.143.1.7063747.

J. Wainer and G. Cawley, “Nested cross-validation when selecting classifiers is overzealous for most practical applications,” Expert Syst. Appl., vol. 182, Art. no. 115222, Nov. 2021, doi: 10.1016/j.eswa.2021.115222.

C. O. Fritz, P. E. Morris, and J. J. Richler, “Effect size estimates: Current use, calculations, and interpretation,” J. Exp. Psychol. Gen., vol. 141, no. 1, pp. 2–18, 2012, doi: 10.1037/a0024338.

L. D. Brown, T. T. Cai, and A. DasGupta, “Interval estimation for a binomial proportion,” Stat. Sci., vol. 16, no. 2, pp. 101–133, May 2001, doi: 10.1214/ss/1009213286.

F. S. Fonseca et al., “Supporting ASD diagnosis with EEG, ML and swarm intelligence: Early detection of autism spectrum disorder based on electroencephalography analysis by machine learning and swarm intelligence,” AI Sens., vol. 1, no. 1, Art. no. 3, Jun. 2025, doi: 10.3390/aisens1010003.

T. Tang et al., “A hybrid graph network model for ASD diagnosis based on resting-state EEG signals,” Brain Res. Bull., vol. 206, Art. no. 110826, Jan. 2024, doi: 10.1016/j.brainresbull.2023.110826.