(School of Electrical Engineering
Telkom University
Bandung, Indonesia, Indonesia)(2) Achmad Rizal
(School of Electrical Engineering
Telkom University
Bandung, Indonesia, Indonesia)(3) * Inung Wijayanto
(School of Electrical Engineering
Telkom University
Bandung, Indonesia, Indonesia)*corresponding author
AbstractAlcohol consumption can alter electrical activity in the brain, and these changes can be captured through electroencephalogram recordings. Automatically recognizing such patterns may help support early identification and reduce the reliance on subjective screening methods. In this work, a three-dimensional Short-Time Fourier Transform (3D STFT) representation is developed to encode temporal, spectral, and spatial characteristics contained in multichannel EEG data. Each electrode receives the STFT in order to produce a unique time-frequency map, which are then combined into a 3D tensor that preserves how the signal evolves across channels. Unlike 2D spectrogram, the 3D representation preserves spatial interactions across electrodes within the time-frequency domain. This multidimensional structure allows the model to interpret the EEG not as separate slices but as a unified volume. The 3D tensor is subsequently used as a 3D CNN's input for classifying EEG trials into alcoholic and non-alcoholic categories. Evaluation is performed using publicly available UCI Alcoholic EEG dataset. The proposed approach yields strong performance, producing accuracy, precision, and recall reaching 98.96%, 98.76%, and 99.17%, respectively, alongside an F1-score of 98.96 and AUC of 99.50%.. These results indicate that combining temporal, spectral, and spatial information within a single representation allows the network to extract deeper and more informative neural patterns compared to conventional 1D features or 2D spectrogram-based inputs. While STFT’s fixed window length limits its ability to represent rapid or highly irregular non-stationary changes, the overall results show that the 3D representation provides a comprehensive view of EEG dynamics and enables effective classification of alcoholic versus non-alcoholic subjects.
KeywordsBinary Classification; Convolutional Neural Network; Electroencephalogram; Short-Time Fourier Transform; 3D Representation
|
DOIhttps://doi.org/10.26555/ijain.v12i3.2319 |
Article metricsAbstract views : 181 | PDF views : 2 |
Cite |
Full Text Download
|
References
[1] “Global status report on alcohol and health and treatment of substance use disorders,” World Health Organization, 2024. [Online]. Available at: https://www.who.int/publications/i/item/9789240096745.
[2] W. Yang, R. Singla, O. Maheshwari, C. J. Fontaine, and J. Gil-Mohapel, “Alcohol Use Disorder: Neurobiology and Therapeutics,” Biomedicines, vol. 10, no. 5, p. 1192, May 2022, doi: 10.3390/biomedicines10051192.
[3] K. Renu et al., “Molecular mechanisms of alcohol’s effects on the human body: A review and update,” J. Biochem. Mol. Toxicol., vol. 37, no. 12, p. e23502, Dec. 2023, doi: 10.1002/jbt.23502.
[4] M. Matuszewska et al., “The Long-Term Effects of Alcohol on the Central Nervous System: Mechanisms, Cognitive Decline, and Associated Disorders,” J. Educ. Heal. Sport, vol. 80, p. 59611, Apr. 2025, doi: 10.12775/JEHS.2025.80.59611.
[5] S. Maharjan et al., “Executive Dysfunction in Patients With Alcohol Use Disorder: A Systematic Review,” Cureus, p. 14, Sep. 2022, doi: 10.7759/cureus.29207.
[6] M. Roberge, M. Boisvert, and S. Potvin, “A Meta-Analysis of Task-Based fMRI Studies on Alcohol Use Disorder,” Brain Sci., vol. 15, no. 7, p. 665, Jun. 2025, doi: 10.3390/brainsci15070665.
[7] C. E. Fairbairn, D. Kang, and K. D. Federmeier, “Alcohol and Neural Dynamics: A Meta-analysis of Acute Alcohol Effects on Event-Related Brain Potentials,” Biol. Psychiatry, vol. 89, no. 10, pp. 990–1000, May 2021, doi: 10.1016/j.biopsych.2020.11.024.
[8] H. Zhang, J. Yao, C. Xu, and C. Wang, “Targeting electroencephalography for alcohol dependence: A narrative review,” CNS Neurosci. Ther., vol. 29, no. 5, pp. 1205–1212, May 2023, doi: 10.1111/cns.14138.
[9] T. S. Bel-Bahar, A. A. Khan, R. B. Shaik, and M. A. Parvaz, “A scoping review of electroencephalographic (EEG) markers for tracking neurophysiological changes and predicting outcomes in substance use disorder treatment,” Front. Hum. Neurosci., vol. 16, pp. 1–31, Oct. 2022, doi: 10.3389/fnhum.2022.995534.
[10] R. L. Hack, M. Aigner, M. Musalek, R. Crevenna, and L. Konicar, “Brain regulation training improves emotional competences in patients with alcohol use disorder,” Soc. Cogn. Affect. Neurosci., vol. 19, no. 1, pp. 1–14, Aug. 2024, doi: 10.1093/scan/nsae048.
[11] E. López-Caneda, F. Cadaveira, A. Correas, A. Crego, F. Maestú, and S. Rodríguez Holguín, “The Brain of Binge Drinkers at Rest: Alterations in Theta and Beta Oscillations in First-Year College Students with a Binge Drinking Pattern,” Front. Behav. Neurosci., vol. 11, pp. 1–10, Sep. 2017, doi: 10.3389/fnbeh.2017.00168.
[12] Y. Liu et al., “Resting-state EEG, Substance use and Abstinence After Chronic use: A Systematic Review,” Clin. EEG Neurosci., vol. 53, no. 4, pp. 344–366, Jul. 2022, doi: 10.1177/15500594221076347.
[13] K. M. Tlotleng and R. S. Jamisola, “An Analysis of the Severity of Alcohol Use Disorder Based on Electroencephalography Using Unsupervised Machine Learning,” Big Data Cogn. Comput., vol. 9, no. 7, p. 170, Jun. 2025, doi: 10.3390/bdcc9070170.
[14] W. Bauer et al., “Initial study on quantitative electroencephalographic analysis of bioelectrical activity of the brain of children with fetal alcohol spectrum disorders (FASD) without epilepsy,” Sci. Rep., vol. 13, no. 1, p. 109, Jan. 2023, doi: 10.1038/s41598-022-26590-4.
[15] A. K. Mohd Nazri et al., “Partial directed coherence analysis of resting-state EEG signals for alcohol use disorder detection using machine learning,” Front. Neurosci., vol. 18, pp. 1–15, Jan. 2025, doi: 10.3389/fnins.2024.1524513.
[16] K. Masroor, D. M. Khan, H. R. Khan, N. Yahya, K. Arshad, and K. Assaleh, “Deciphering Default Mode Network Dynamics in Alcohol Use Disorder through Directed Transfer Function Analysis of EEG,” IEEE Access, pp. 1–1, 2024, doi: 10.1109/ACCESS.2024.3518916.
[17] L. J. Aradhana Manekar, “Automated Classification of Alcoholism Using Discrete Cosine Harmonic Wavelet-Packet Transform,” J. Inf. Syst. Eng. Manag., vol. 10, no. 10s, pp. 125–136, Feb. 2025, doi: 10.52783/jisem.v10i10s.1361.
[18] A. Rizal, D. S. Beu, and S. Ziani, “Alcoholic EEG Classification Multichannel FFT Image,” 2025, pp. 473–478, doi: 10.1007/978-3-031-90921-4_66.
[19] P. Croce, A. Quercia, S. Costa, and F. Zappasodi, “EEG microstates associated with intra- and inter-subject alpha variability,” Sci. Rep., vol. 10, no. 1, p. 2469, Feb. 2020, doi: 10.1038/s41598-020-58787-w.
[20] A. Raj, P. Verma, and S. Nagarajan, “Structure-function models of temporal, spatial, and spectral characteristics of non-invasive whole brain functional imaging,” Front. Neurosci., vol. 16, pp. 1–11, Aug. 2022, doi: 10.3389/fnins.2022.959557.
[21] Z. Zhang, “Spectral and Time-Frequency Analysis,” in EEG Signal Processing and Feature Extraction, Singapore: Springer Singapore, 2019, pp. 89–116, doi: 10.1007/978-981-13-9113-2_6.
[22] G. Lekkas, E. Vrochidou, and G. A. Papakostas, “Time–Frequency Transformations for Enhanced Biomedical Signal Classification with Convolutional Neural Networks,” BioMedInformatics, vol. 5, no. 1, p. 7, Jan. 2025, doi: 10.3390/biomedinformatics5010007.
[23] A. F. Almurshedi, “Envelope analysis and short time Fourier transform of EEG for epilepsy diagnosis enhancement,” Rom. J. Neurol., vol. 24, no. 1, pp. 35–41, Mar. 2025, doi: 10.37897/RJN.2025.1.12.
[24] “EEG Database,” UCI Machine Learning Repository, 1999. [Online]. Available at: https://archive.ics.uci.edu/dataset/121/eeg+database.
[25] C. Liu, P. Han, and J. Kang, “Integrating short-time linear canonical transform and joint space-time-frequency analysis for advanced representation of subsurface information in ground penetrating radar,” Sci. Rep., vol. 15, no. 1, p. 23315, Jul. 2025, doi: 10.1038/s41598-025-06795-z.
[26] P. Ewert, B. Wicher, and T. Pajchrowski, “Application of the STFT for Detection of the Rotor Unbalance of a Servo-Drive System with an Elastic Interconnection,” Electronics, vol. 13, no. 2, p. 441, Jan. 2024, doi: 10.3390/electronics13020441.
[27] M. Zhang, “Multi-resolution short-time Fourier transform providing deep features for 3D CNN to classify rolling bearing fault vibration signals,” Eng. Res. Express, vol. 6, no. 3, p. 035201, Sep. 2024, doi: 10.1088/2631-8695/ad5d52.
[28] H. Jeon, Y. Jung, S. Lee, and Y. Jung, “Area-Efficient Short-Time Fourier Transform Processor for Time–Frequency Analysis of Non-Stationary Signals,” Appl. Sci., vol. 10, no. 20, p. 7208, Oct. 2020, doi: 10.3390/app10207208.
[29] J. Chmiel, J. Nadobnik, S. Smerdel, and M. Niedzielska, “Neural Correlates of Huntington’s Disease Based on Electroencephalography (EEG): A Mechanistic Review and Discussion of Excitation and Inhibition (E/I) Imbalance,” J. Clin. Med., vol. 14, no. 14, p. 5010, Jul. 2025, doi: 10.3390/jcm14145010.
[30] Z. Wang, L. Chen, P. Xiao, L. Xu, and Z. Li, “Enhancing time-frequency resolution via deep-learning framework,” IET Signal Process., vol. April, pp. 1–19, 2023, doi: 10.1049/sil2.12210.
[31] S. Kumawat, M. Verma, Y. Nakashima, and S. Raman, “Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 9, pp. 4839–4851, Jul. 2020, doi: 10.1109/TPAMI.2021.3076522.
[32] I. Rakhmatulin, M.-S. Dao, A. Nassibi, and D. Mandic, “Exploring Convolutional Neural Network Architectures for EEG Feature Extraction,” Sensors, vol. 24, no. 3, p. 877, Jan. 2024, doi: 10.3390/s24030877.
[33] C. Jannu and S. D. Vanambathina, “Multi-stage Progressive Learning-Based Speech Enhancement Using Time–Frequency Attentive Squeezed Temporal Convolutional Networks,” Circuits, Syst. Signal Process., vol. 42, no. 12, pp. 7467–7493, Dec. 2023, doi: 10.1007/s00034-023-02455-7.
[34] B. Wang et al., “Automatic epileptic seizure detection based on EEG using a moth-flame optimization of one-dimensional convolutional neural networks,” Front. Neurosci., vol. 17, pp. 1–16, Dec. 2023, doi: 10.3389/fnins.2023.1291608.
[35] S. Siuly, Y. Guo, O. F. Alcin, Y. Li, P. Wen, and H. Wang, “Exploring deep residual network based features for automatic schizophrenia detection from EEG,” Phys. Eng. Sci. Med., vol. 46, no. 2, pp. 561–574, Jun. 2023, doi: 10.1007/s13246-023-01225-8.
[36] G. D. Paladugu, H. K. Goru, J. M. Gundu, P. Medisetty, and K. K. Kumari, “Alcoholism Identification From Variational Mode Decomposed EEG Signal Using Machine Learning Techniques,” in 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Jul. 2023, pp. 1–7, doi: 10.1109/ICCCNT56998.2023.10307977.
[37] A. Ebrahimi, U. K. Wiil, A. Naemi, M. Mansourvar, K. Andersen, and A. S. Nielsen, “Identification of clinical factors related to prediction of alcohol use disorder from electronic health records using feature selection methods,” BMC Med. Inform. Decis. Mak., vol. 22, no. 1, p. 304, Nov. 2022, doi: 10.1186/s12911-022-02051-w.
[38] W. Mumtaz, P. L. Vuong, L. Xia, A. S. Malik, and R. B. A. Rashid, “An EEG-based machine learning method to screen alcohol use disorder,” Cogn. Neurodyn., vol. 11, no. 2, pp. 161–171, Apr. 2017, doi: 10.1007/s11571-016-9416-y.
[39] T. Yang and Y. Ying, “AUC Maximization in the Era of Big Data and AI: A Survey,” ACM Comput. Surv., vol. 55, no. 8, pp. 1–37, Aug. 2023, doi: 10.1145/3554729.
[40] J. Y. Verbakel et al., “ROC curves for clinical prediction models part 1. ROC plots showed no added value above the AUC when evaluating the performance of clinical prediction models,” J. Clin. Epidemiol., vol. 126, pp. 207–216, Oct. 2020, doi: 10.1016/j.jclinepi.2020.01.028.
[41] M. Gabardi, A. Saibene, F. Gasparini, D. Rizzo, and F. A. Stella, “A multi-artifact EEG denoising by frequency-based deep learning,” in ISSN 1613-0073 CEUR Workshop Proceedings, 2023, pp. 1–14, [Online]. Available at: https://ceur-ws.org/Vol-3576/paper4.pdf.
[42] W. Yan, Q. Luo, and C. Du, “Channel component correlation analysis for multi-channel EEG feature component extraction,” Front. Neurosci., vol. 19, pp. 1–11, Apr. 2025, doi: 10.3389/fnins.2025.1522964.
[43] Y. Yan, S. B. Samdin, and K. N. Minhad, “Window-based Time-Frequency Methods for Analyzing Epileptic EEG Signals,” in 2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Dec. 2022, pp. 292–297, doi: 10.1109/IECBES54088.2022.10079259.
[44] W. Yan and Y. Wu, “A time-frequency denoising method for single-channel event-related EEG,” Front. Neurosci., vol. 16, pp. 1–14, Nov. 2022, doi: 10.3389/fnins.2022.991136.
[45] A. Manekar and L. Jolly, “Wavelet Decomposition based Automated Alcoholism Classification using EEG Signal,” in 2022 IEEE Bombay Section Signature Conference (IBSSC), Dec. 2022, pp. 1–6, doi: 10.1109/IBSSC56953.2022.10037362.
[46] P. D. Purnamasari, F. H. Zulkarnaen, M. Melinda, E. P. Sinulingga, F. Fahmi, and A. A. P. Ratna, “Alcoholic EEG Signal Feature Extraction Based on Relative Wavelet Bispectrum and Bispectrum-Gaussian Using CNN and ANN Classifier,” in 2024 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Dec. 2024, pp. 1–6, doi: 10.1109/IECBES61011.2024.10990911.
[47] M. Shen, P. Wen, B. Song, and Y. Li, “Detection of alcoholic EEG signals based on whole brain connectivity and convolution neural networks,” Biomed. Signal Process. Control, vol. 79, p. 104242, Jan. 2023, doi: 10.1016/j.bspc.2022.104242.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0