FFT-based CNN Classification for Schizophrenia Detection in EEG Recordings

Year 2025, Volume: 2 Issue: 1, 10 - 25, 29.05.2025

Zekeriya Edahil , Sema Koç Kayhan

Abstract

Machine learning enhances computer-aided medical diagnosis by enabling accurate and swift decision-making. This study proposes a method for detecting schizophrenia (SZ) using electroencephalography, which measures brain electrical activity to diagnose neurological disorders. Schizophrenia is characterized by complex neural patterns, challenging to identify with traditional methods. This research employs deep learning algorithms to analyze EEG signals for schizophrenia detection, aiming to improve classification accuracy. The methodology involves preprocessing Electroencephalography (EEG) time series to extract spectral power features using Fast Fourier Transformation (FFT), which transforms time-domain signals into the frequency domain, revealing brain oscillatory activity. These features are converted into RGB images representing brain activity's spatial information. A convolutional neural network (CNN) is then used to classify these images. The proposed method achieved an average accuracy of 95.97% with FFT, indicating that FFT-based features are highly effective for classification in this context. The results underscore the importance of data representation when using CNN models for EEG signal analysis.

Keywords

CNN, EEG, Schizophrenia, FFT, Classification

References

• Alfeld, P. (1984). A trivariate Clough-Tocher scheme for tetrahedral data. Computer Aided Geometric Design, 1(2), 169–181.
• Bashivan, P., Rish, I., Yeasin, M., and Codella, N. (2016). Learning representations from EEG with deep recurrent-convolutional neural networks, published as a conference paper at ICLR
• Bonita, J. D., Ambolode, L. C. C., Rosenberg, B. M., Cellucci, C. J., Watanabe, T. A. A., and Rapp, P. E. (2014). Time domain measures of inter-channel EEG correlations: a comparison of linear, nonparametric and nonlinear measures. Cogn Neurodyn, 8, 1–15.
• Chen, Z., Zhao, Y., Jin, C., & Zhao, W. (2019). A Review on EEG Based Emotion Classification. https://doi.org/10.1109/iaeac47372.2019.8997704
• Delorme, A. (2019). EEG preprocessing in EEGLAB [PDF]. Swartz Center for Computational Neuroscience. https://sccn.ucsd.edu/githubwiki/files/eeglab2019_aspet_artifact_and_ica.pdf
• Ganesh, R. N., and Kumar, D. K. (2011). An overview of independent component analysis and its applications. Informatica, 35(1).
• Gorbachevskaya, N. and Borisov, S. (2019). EEG of healthy adolescents and adolescents with symptoms of schizophrenia (Database). http://brain.bio.msu.ru/eeg_schizophrenia.htm, 2019. (Accessed date: 7 January 2025).
• Harm, M., Hope, M., and Household, A. (2013). Diagnostic and Statistical Manual of Mental Disorders. American Psychiatric Association. (5th ed. pp. 87-90).
• Harrison, G., Hopper, K., Craig, T., Laska, E., Siegel, C., and Wanderling, J. (2001). Recovery from psychotic illness: A 15-and 25-year international follow-up study. The British Journal of Psychiatry, 178, 506-517.
• Jaeschke, K., Hanna, F., Ali, S., Chowdhary, N., Dua, T., and Charlson, F. (2021). Global estimates of service coverage for severe mental disorders: Findings from the WHO Mental Health Atlas 2017. Global Mental Health, 8, e27.
• Kingphai, K., and Moshfeghi, Y. (2021). On EEG Preprocessing Role in Deep Learning Effectiveness for Mental Workload Classification. 10.1007/978-3-030-91408-0_6.
• Koshiyama, D., Miyakoshi, M., Tanaka-Koshiyama, K., Joshi, Y. B., Sprock, J., Braff, D. L., and Light, G. A. (2021). Abnormal phase discontinuity of alpha- and theta-frequency oscillations in schizophrenia. Schizophrenia Research, 231, 73–81. https://doi.org/10.1016/j.schres.2021.03.007
• Kwon, J. S., and Carpenter, C. J. (2007). Electroencephalography in schizophrenia. Schizophrenia Bulletin, 33(2), 253-265.
• Min, S., Lee, B., and Yoon, S. (2017). Deep learning in bioinformatics. Briefings in Bioinformatics, 18, 851–869
• Murphy, M., and Öngür, D. (2019). Decreased peak alpha frequency and impaired visual evoked potentials in first episode psychosis. NeuroImage. Clinical, 22, 101693. https://doi.org/10.1016/j.nicl.2019.101693
• Naira, C. A. T., and Alamo, C. J. L. D. (2019). Classification of People who Suffer Schizophrenia and Healthy People by EEG Signals using Deep Learning. International Journal of Advanced Computer Science and Applications(IJACSA), 10(10). http://dx.doi.org/10.14569/IJACSA.2019.0101067
• Newson, J. J., and Thiagarajan, T. C. (2019). EEG frequency bands in psychiatric disorders: A review of resting state studies. Frontiers in Human Neuroscience, 12, 521. https://doi.org/10.3389/fnhum.2018.00521
• Niedermeyer, E., and Lopes da Silva, F. H. (2005). Electroencephalography: Basic principles, clinical applications, and related fields (6th ed., pp. 123-145, 200-210). Lippincott Williams & Wilkins.
• Oostenveld, R., and Praamstra, P. (2001). The five percent electrode system for high-resolution EEG and ERP measurements. Clinical Neurophysiology, 112(4), 713–719.
• Phang, C. R., Ting, C. M., Samdin S. B., and Ombao, H. (2019). Classification of EEG-based Effective Brain Connectivity in Schizophrenia using Deep Neural Networks. 9th International IEEE/EMBS Conference on Neural Engineering (NER), San Francisco, CA, USA. pp. 401-406, doi: 10.1109/NER.2019.8717087.
• Plis, S. M., Hjelm, D. R., Salakhutdinov, R., Allen, E. A., Bockholt, H. J., Long, J. D., Johnson, H. J., Paulsen, J. S., Turner, J. A., and Calhoun, V. D. (2014). Deep learning for neuroimaging: a validation study. Frontiers in Neuroscience, 8(August):1–11. ISSN 1662-453X. https://doi.org/10.3389/fnins.2014.00229
• Savio, A., Charpentier, J., Termenon, M., Shinn, A. K., and Graña, M. (2010). Neural classifiers for schizophrenia diagnostic support on diffusion imaging data. Neural Network World, 20, 935–949.
• Sharma, G., and Joshi, A. (2021). Novel EEG based Schizophrenia Detection with IoMT Framework for Smart Healthcare. cornell university. https://doi.org/10.48550/arxiv.2111.11298
• Sharma, M., Patel, R.K., Garg, A., SanTan, R., and Rajendra Acharya, U. (2023). Automated detection of schizophrenia using deep learning: A review for the last decade. Physiological Measurements, 44(03TR01). https://doi.org/10.1088/1361-6579/acb24d
• Singh, K., Singh, S., and Malhotra, J. (2021). Spectral features based convolutional neural network for accurate and prompt identification of schizophrenic patients. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 235(2), 167-184. doi:10.1177/0954411920966937
• Sun, J., Cao, R., Zhou, M., Hussain, W., Wang, B., Xue, J., and Xiang, J. (2021). A hybrid deep neural network for classification of schizophrenia using EEG data. Scientific Reports, 11, 4706. https://doi.org/10.1038/s41598-021-83350-6
• Upadhyay, R., Manglick, A., Reddy. D. K., Padhy, P. K., and Kankar, P. K. (2015). Channel optimization and nonlinear feature extraction for electroencephalogram signals classification. Computers and Electrical Engineering, 45, 222–234
• World Health Organization. (2023). Schizophrenia. [Fact sheet]. World Health Organization. September 1. https://www.who.int/news-room/fact-sheets/detail/schizophrenia
• Wu, D., and Yao, D. (2007). The azimuth projection for the display of 3-D EEG data. Computers in Biology and Medicine, 37(12), 1821-1826. https://doi.org/10.1016/j.compbiomed.2007.06.006