SchizoGoogLeNet: The GoogLeNet-Based Deep Feature Extraction Design for Automatic Detection of Schizophrenia
Article
Article Title | SchizoGoogLeNet: The GoogLeNet-Based Deep Feature Extraction Design for Automatic Detection of Schizophrenia |
---|---|
ERA Journal ID | 14562 |
Article Category | Article |
Authors | Siuly, Siuly (Author), Li, Yan (Author), Wen, Peng (Author) and Alcin, Omer Faruk (Author) |
Journal Title | Computational Intelligence and Neuroscience |
Journal Citation | 2022, pp. 1-13 |
Article Number | 1992596 |
Number of Pages | 13 |
Year | 2022 |
Publisher | Hindawi Publishing Corporation |
Place of Publication | United Kingdom |
ISSN | 1687-5265 |
1687-5273 | |
Digital Object Identifier (DOI) | https://doi.org/10.1155/2022/1992596 |
Web Address (URL) | https://www.hindawi.com/journals/cin/2022/1992596/ |
Abstract | Schizophrenia (SZ) is a severe and prolonged disorder of the human brain where people interpret reality in an abnormal way. Traditional methods of SZ detection are based on hand-crafted feature extraction methods (manual process), which are tedious and unsophisticated, and also limited in their ability to balance efficiency and accuracy. To solve this issue, this study designs a deep learning-based feature extraction scheme involving GoogLeNet model called ‘SchizoGoogLeNet’ that can efficiently and automatically distinguish schizophrenic patients from healthy control (HC) subjects using electroencephalogram (EEG) signals with improved performance. The proposed framework involves multiple stages of EEG data processing. Firstly, this study employs the average filtering method to remove noise and artifacts from the raw EEG signals for improving signal-to-noise ratio. After that, a GoogLeNet model is designed to discover significant hidden features from denoised signals to identify schizophrenic patients from HC subjects. Finally, the obtained deep feature set is evaluated by GoogleNet classifier and also some renowned machine learning classifiers to find a sustainable classification method for the obtained deep feature set. Experimental results show that the proposed deep feature extraction model with support vector machine performs as the best, producing 99.02% correct classification rate for SZ, with an overall accuracy of 98.84%. Moreover, our proposed model outperforms other existing methods. The proposed design is able to accurately discriminate SZ from HC, and it will be useful for developing a diagnostic tool for SZ detection. |
Keywords | Schizophrenia detection, EEG, Deep learning, GoogLeNet, Feature extraction, Classification |
ANZSRC Field of Research 2020 | 460299. Artificial intelligence not elsewhere classified |
400399. Biomedical engineering not elsewhere classified | |
400304. Biomedical imaging | |
Byline Affiliations | Victoria University |
School of Mathematics, Physics and Computing | |
School of Engineering | |
Malatya Turgut Ozal University, Turkiye | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q7qw8/schizogooglenet-the-googlenet-based-deep-feature-extraction-design-for-automatic-detection-of-schizophrenia
Download files
63
total views35
total downloads2
views this month2
downloads this month