An automatic scheme with diagnostic index for identification of normal and depression EEG signals

Akari, Hesam and Sadiq, Muhammad Tariq and Siuly, Siuly ORCID: https://orcid.org/0000-0003-2491-0546 and Li, Yan ORCID: https://orcid.org/0000-0002-4694-4926 and Wen, Peng (Paul) ORCID: https://orcid.org/0000-0003-0939-9145 (2021) An automatic scheme with diagnostic index for identification of normal and depression EEG signals. In: 10th International Conference on Health Information Science (HIS 2021), 25 Oct - 28 oct 2021, Melbourne, Australia.


Abstract

Detection of depression utilizing electroencephalography (EEG) signals is one of the major challenges in neural engineering applications. This study introduces a novel automated computerized depression detection method using EEG signals. In proposed design, firstly, EEG signals are decomposed into 10 empirically chosen intrinsic mode functions (IMFs) with the aid of variational mode decomposition (VMD). Secondly, the fluctuation index (FI) of IMFs is computed as the discrimination features. Finally, these features are fed into cascade forward neural network and feed-forward neural network classifiers which achieved better classification accuracy, sensitivity, and specificity from the right brain hemisphere in a 10-fold cross-validation strategy in comparison with available literature. In this study, we also propose a new depression diagnostic index (DDI) using the FI of IMFs in the VMD domain. This integrated index would assist in a quicker and more objective identification of normal and depression EEG signals. Both the proposed computerized framework and the DDI can help health workers, large enterprises and product developers to build a real-time system.


Statistics for USQ ePrint 45392
Statistics for this ePrint Item
Item Type: Conference or Workshop Item (Commonwealth Reporting Category E) (Paper)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Historic - Faculty of Health, Engineering and Sciences - School of Sciences (6 Sep 2019 - 31 Dec 2021)
Faculty/School / Institute/Centre: Historic - Faculty of Health, Engineering and Sciences - School of Mechanical and Electrical Engineering (1 Jul 2013 - 31 Dec 2021)
Date Deposited: 15 Feb 2022 23:29
Last Modified: 10 Apr 2022 09:29
Uncontrolled Keywords: EEG ; depression; variational mode decomposition; fluctuation index; depression diagnostic index; classification
Fields of Research (2008): 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080199 Artificial Intelligence and Image Processing not elsewhere classified
09 Engineering > 0903 Biomedical Engineering > 090399 Biomedical Engineering not elsewhere classified
Fields of Research (2020): 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460299 Artificial intelligence not elsewhere classified
46 INFORMATION AND COMPUTING SCIENCES > 4601 Applied computing > 460102 Applications in health
Socio-Economic Objectives (2008): C Society > 92 Health > 9202 Health and Support Services > 920203 Diagnostic Methods
Socio-Economic Objectives (2020): 20 HEALTH > 2099 Other health > 209999 Other health not elsewhere classified
Identification Number or DOI: https://doi.org/10.1007/978-3-030-90885-0_6
URI: http://eprints.usq.edu.au/id/eprint/45392

Actions (login required)

View Item Archive Repository Staff Only