An automatic scheme with diagnostic index for identification of normal and depression EEG signals
Paper
Paper/Presentation Title | An automatic scheme with diagnostic index for identification of normal and depression EEG signals |
---|---|
Presentation Type | Paper |
Authors | Akari, Hesam (Author), Sadiq, Muhammad Tariq (Author), Siuly, Siuly (Author), Li, Yan (Author) and Wen, Peng (Paul) (Author) |
Editors | Siuly, Siuly, Wang, Hua, Chen, Lu, Guo, Yanhui and Xing, Chunxiao |
Journal or Proceedings Title | Proceedings of the 10th International Conference on Health Information Science (HIS 2021) |
Journal Citation | 13079, pp. 59-70 |
Number of Pages | 11 |
Year | 2021 |
Place of Publication | Switzerland |
ISBN | 9783030908843 |
9783030908850 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-90885-0_6 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-030-90885-0_6 |
Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-3-030-90885-0 |
Conference/Event | 10th International Conference on Health Information Science (HIS 2021) |
Event Details | 10th International Conference on Health Information Science (HIS 2021) Parent International Conference on Health Information Science (HIS) Delivery In person Event Date 25 to end of 28 Oct 2021 Event Location 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. |
Keywords | EEG ; depression; variational mode decomposition; fluctuation index; depression diagnostic index; classification |
ANZSRC Field of Research 2020 | 460299. Artificial intelligence not elsewhere classified |
460102. Applications in health | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Series | Lecture Notes in Computer Science |
Byline Affiliations | Islamic Azad University, Iran |
University of Lahore, Pakistan | |
Victoria University | |
School of Sciences | |
School of Mechanical and Electrical Engineering | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q6xxv/an-automatic-scheme-with-diagnostic-index-for-identification-of-normal-and-depression-eeg-signals
156
total views3
total downloads5
views this month0
downloads this month