Multi-objective squirrel search algorithm for EEG feature selection
Article
Wang, Chao, Li, Songjie, Shi, Miao, Zhao, Jie, Wen, Tao Wen, Acharya, U. Rajendra, Xie, Neng-gang and Cheong, Kang Hao. 2023. "Multi-objective squirrel search algorithm for EEG feature selection." Journal of Computational Science. 73. https://doi.org/10.1016/j.jocs.2023.102140
Article Title | Multi-objective squirrel search algorithm for EEG feature selection |
---|---|
ERA Journal ID | 42116 |
Article Category | Article |
Authors | Wang, Chao, Li, Songjie, Shi, Miao, Zhao, Jie, Wen, Tao Wen, Acharya, U. Rajendra, Xie, Neng-gang and Cheong, Kang Hao |
Journal Title | Journal of Computational Science |
Journal Citation | 73 |
Article Number | 102140 |
Number of Pages | 14 |
Year | 2023 |
Publisher | Elsevier |
Place of Publication | United Kingdom |
ISSN | 1877-7503 |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.jocs.2023.102140 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S1877750323002004 |
Abstract | Feature selection plays a critical role in the application of Brain Computer Interface (BCI) systems. Many methods have been used to solve the feature selection problem, but they model it as a single-objective problem, considering only classification accuracy or number of features. To close this critical gap, we improve the squirrel search algorithm by combining it with the grid method, and propose a Multi-Objective Squirrel Search Algorithm (MOSSA) to solve the feature selection problem in BCI. We conduct experiments on three publicly available motion imagery datasets, and the experimental results reveal the best classification results of the method on dataset 1. The average classification accuracy of dataset 2 is 96.71%, with the number of selected features reduced to 18 on average. The highest classification accuracy of dataset 3 is 83.57% on the training set and 82.86% on the test set. In addition, we compare MOSSA with other algorithms and the results show the superiority of our proposed method in solving the feature selection problem. Finally, we combine MOSSA with an online application of BCI, where subjects visualize controlling the robot to perform the corresponding actions by the left and right hand movements. The average recognition rate of the three subjects is approximately 70%. In summary, the MOSSA is an effective method for solving the feature selection problem and is useful for the development of online applications of BCI. |
Keywords | Brain computer interface; Feature selection; MOSSA; Motor Imagery |
ANZSRC Field of Research 2020 | 400306. Computational physiology |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Anhui Polytechnic University, China |
Anhui Province Key Laboratory of Multidisciplinary Management and Control of Complex Systems, China | |
Anhui University of Science and Technology, China | |
Singapore University of Technology and Design | |
School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z1w45/multi-objective-squirrel-search-algorithm-for-eeg-feature-selection
37
total views0
total downloads4
views this month0
downloads this month