CLASSIFICATION OF EEG SPECTROGRAM IMAGES WITH DEEP LEARNING MODELS FOR ALCOHOLISM DETECTION

Year 2024, Volume: 2 Issue: 2, 140 - 149, 17.01.2025

Öznur Yildirim , Yahya Cihat Söker , Mehmet Zahid Yıldırım , Emrah Özkaynak

https://doi.org/10.71074/CTC.1596824

Abstract

Electroencephalogram (EEG) signals are time series that play an essential role in un- derstanding the electrical behavior of the brain. The complex structure of the brain makes the in- terpretation of EEG signals difficult. In this study, the classification of EEG signals based on image processing with deep learning is performed differently from traditional methods. Images of EEG signals obtained for the detection of alcoholism were used to classify healthy and alcohol-addicted individuals using a Convolutional Neural Network (CNN). Three models have been implemented in the experiments conducted on the EEG images: Resnet50, Xception, and custom CNN. The findings demonstrate that Xception achieves the best accuracy with 100% classification success.

Keywords

Machine learning, Electroencephalography (EEG), Spectrogram, Convolutional neural network (CNN).

References

• H. Berger, Über das Elektrenkephalogramm des Menschen. Archiv f. Psychiatrie 87, 527–570 (1929).
• S. Q. O. Omar, C. Tepe, EEG Sinyallerini İşlemek İçin Makine Öğreniminin Kullanıldığı Konular Üzerine Bir İnceleme, Bayburt Üniversitesi Fen Bilimleri Dergisi 5 (1) (2022) 124–137.
• G. Zhang, V. Davoodnia, A. Sepas-Moghaddam, Y. Zhang, A. Etemad, Classification of hand movements from eeg using a deep attention-based lstm network, IEEE Sensors Journal 20 (6) (2019) 3113–3122.
• M. Savadkoohi, T. Oladunni, L. Thompson, A machine learning approach to epileptic seizure prediction using electroen- cephalogram (eeg) signal, Biocybernetics and Biomedical Engineering 40 (3) (2020) 1328–1341.
• V. Doma, M. Pirouz, A comparative analysis of machine learning methods for emotion recognition using eeg and peripheral physiological signals, Journal of Big Data 7 (1) (2020) 18.
• D. Pirrone, E. Weitschek, P. Di Paolo, S. De Salvo, M. C. De Cola, Eeg signal processing and supervised machine learning to early diagnose alzheimer’s disease, Applied sciences 12 (11) (2022) 5413.
• L. Farsi, S. Siuly, E. Kabir, H. Wang, Classification of alcoholic eeg signals using a deep learning method, IEEE Sensors Journal 21 (3) (2020) 3552–3560.
• M. M. Shaker, Eeg waves classifier using wavelet transform and fourier transform, brain 2 (3) (2006) 169–174.
• S. Lekshmi, V. Selvam, M. P. Rajasekaran, Eeg signal classification using principal component analysis and wavelet transform with neural network, in: 2014 International Conference on Communication and Signal Processing, IEEE, 2014, pp. 687–690.
• A. Subasi, M. I. Gursoy, Eeg signal classification using pca, ica, lda and support vector machines, Expert systems with applications 37 (12) (2010) 8659–8666.
• B. Arı, Alkolik ve normal eeg sinyallerinin zaman-alan tanımlayıcı analizi tabanlı otomatik sınıflandırılması, Fırat Üniversitesi Mühendislik Bilimleri Dergisi 35 (1) 291–300.
• B. Adhikari, A. Shrestha, S. Mishra, S. Singh, A. K. Timalsina, Eeg based directional signal classification using rnn variants, in: 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS), IEEE, 2018, pp. 218–223.
• N. Olgun, ˙I. Türkoğlu, Defining materials using laser signals from long distance via deep learning, Ain Shams Engineering Journal 13 (3) (2022) 101603.
• V. Bajaj, Y. Guo, A. Sengur, S. Siuly, O. F. Alcin, A hybrid method based on time–frequency images for classification of alcohol and control eeg signals, Neural Computing and Applications 28 (2017) 3717–3723.
• S. Rajwal, S. Aggarwal, Convolutional neural network-based eeg signal analysis: A systematic review, Archives of Computational Methods in Engineering 30 (6) (2023) 3585–3615.
• S. Rajwal, S. Aggarwal, Evris¸imsel sinir ag˘ı tabanlı eeg sinyal analizi: Sistematik bir ˙Inceleme, Archives of Computational Methods in Engineering 30 (2023) 3585–3615.
• N. Thapliyal, M. Manwal, V. Kukreja, R. Sharma, Artificial intelligence-based resnet50, xception, and vgg16 models for an efficient detection of lung cancer, in: 2024 5th International Conference for Emerging Technology (INCET), IEEE, 2024, pp. 1–5.
• P. Refaeilzadeh, L. Tang, H. Liu, Cross-validation, Encyclopedia of database systems (2009) 532–538.
• S. Mohammed, Eeg spectrogram images, accessed: 2024-12-01 (2024). URL https://www.kaggle.com/datasets/sayeemmohammed/eeg-spectrogram-images