Annual Conference of KIPS (한국정보처리학회:학술대회논문집)

  • 2024.10a
  • /
  • Pages.549-552
  • /
  • 2024
  • /
  • 2005-0011(pISSN)
  • /
  • 2671-7298(eISSN)
Korea Information Processing Society (한국정보처리학회)
권호 표지

Phase Locked Value-Based Siamese Network For EEG Depression Classification

EEG 우울증 분류를 위한 위상 잠금 값 기반 샴 네트워크

  • Ngumimi Karen Iyortsuun (Department of Artificial Intelligence Convergence, Chonnam National University, South Korea University) ;
  • Soonja Yeom (School of Information and Communication Technology, University of Tasmania) ;
  • Soo-Hyung Kim (Department of Artificial Intelligence Convergence, Chonnam National University, South Korea University) ;
  • Aera Kim (Department of Artificial Intelligence Convergence, Chonnam National University, South Korea University)
  • ;
  • 염순자 (정보통신기술대학, 태즈메이니아 대학교) ;
  • 김수형 (인공지능융합학과 대학원 전남대학교) ;
  • 김애라 (인공지능융합학과 대학원 전남대학교)
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Mental health conditions such as Major Depressive Disorder (MDD) undoubtedly pose severe life-threatening effects if not properly diagnosed and treated promptly. In this paper, we aim to differentiate depressed patients from healthy controls by determining the level of co-functionality relationships between brain regions using the Multi-modal Open Dataset for Mental Disorder Analysis (MODMA) 128-channel resting-state Electroencephalography (EEG) data. By proposing a method that adopts the combination of Phase Locking Value (PLV) functional connectivity analysis with a Contrastive Siamese Network model, we extract PLV-based features and employ the proposed Contrastive Siamese Network to learn discriminative features from the PLV matrices. Our proposed approach achieved an accuracy of 0.88, surpassing prior research works on the same dataset. The results suggest that PLV can serve as a reliable biomarker for depression detection, effectively distinguishing between both classes and leading to robust classification outcomes.

Keywords

Acknowledgement

This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Development (IITP-2023-RS-2023-00256629) grant funded by the Korea government (MSIT), the ITRC (Information Technology Research Center) support program (IITP-2024-RS-2024-00437718) supervised by IITP, and the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (RS-2023-00219107).

References

  1. N. K. Iyortsuun, S.-H. Kim, M. Jhon, H.-J. Yang, and S. Pant, "A review of machine learning and deep learning approaches on mental health diagnosis," in Healthcare, 2023, vol. 11, no. 3: MDPI, p. 285.
  2. C. M. Michel and M. M. Murray, "Towards the utilization of EEG as a brain imaging tool," Neuroimage, vol. 61, no. 2, pp. 371-385, 2012.
  3. P. Hovel, A. Viol, P. Loske, L. Merfort, and V. Vuksanovic, "Synchronization in functional networks of the human brain," Journal of Nonlinear Science, vol. 30, no. 5, pp. 2259-2282, 2020.
  4. E. Gore and S. Rathi, "Surveying machine learning algorithms on eeg signals data for mental health assessment," in 2019 IEEE Pune Section International Conference (PuneCon), 2019: IEEE, pp. 1-6.
  5. H. Cai et al., "A multi-modal open dataset for mental-disorder analysis," Scientific Data, vol. 9, no. 1, p. 178, 2022.
  6. A. Ksibi, M. Zakariah, L. J. Menzli, O. Saidani, L. Almuqren, and R. A. M. Hanafieh, "Electroencephalography-based depression detection using multiple machine learning techniques," Diagnostics, vol. 13, no. 10, p. 1779, 2023.
  7. J. Shen et al., "An optimal channel selection for EEG-based depression detection via kernel-target alignment," IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 7, pp. 2545-2556, 2020.
  8. S. Sun, J. Li, H. Chen, T. Gong, X. Li, and B. Hu, "A study of resting-state EEG biomarkers for depression recognition," arXiv preprint arXiv:2002.11039, 2020.