Title: EEG-based variable node functional network comparison for multiclass brain disease detection using stacked ensemble model
Authors: Mangesh Ramaji Kose; Mitul Kumar Ahirwal; Mithilesh Atulkar
Addresses: Department of Computer Applications, National Institute of Technology, Raipur – 492010, India ' Department of Computer Applications, Maulana Azad National Institute of Technology Bhopal, Bhopal – 462003, India ' Department of Computer Applications, National Institute of Technology, Raipur – 492010, India
Abstract: The brain connectivity network (BCN) is considered to be an effective approach for analysing brain functionality. The EEG-based BCN considers electrodes as a node and functional similarity between EEGs from corresponding nodes as edge. The EEG dataset available for the evaluation might contain variable number of nodes. The variable number of nodes provides biased results while performing graph classification. Hence, the study proposed a strategy to mitigate the aforementioned challenge. The proposed method characterises variable node BCN with the help of network level metrics as a feature vector. The extracted metrics characterises the network as a whole and do not rely on the number of nodes. Two public datasets, with 16 electrodes and 19 electrodes EEG data, are used to test the suggested method. The classification is performed with the stacked-ensemble classification technique. Finally, the quantitative analysis of the proposed approach represents a significant performance with the 92.34% classification accuracy.
Keywords: brain connectivity network; BCN; electroencephalogram; EEG; graph theory-based metrics; SMOTE; stacked-ensemble classification.
DOI: 10.1504/IJBET.2024.137345
International Journal of Biomedical Engineering and Technology, 2024 Vol.44 No.3, pp.242 - 270
Received: 29 Dec 2022
Accepted: 02 May 2023
Published online: 13 Mar 2024 *