Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/4594
Title: | Fusion of Multi-Scale CNN for Motor Imagery EEG Classification |
Authors: | Devi, Kshetrimayum Shalu Ari, Samit |
Keywords: | Motor imagery multi-scale convolutional neural network EEG classification |
Issue Date: | Jun-2024 |
Citation: | 2nd International Conference on Computer, Electronics, Electrical Engineering and their applications (IC2E3 2024), NIT Uttarakhand, 6-7 June 2024 |
Abstract: | Brain-computer interface (BCI) is a groundbreaking and innovative paradigm in human-computer interaction, with the potential to enhance the living standard with technological advancement. The electroencephalogram (EEG) signals associated with motor imagery (MI) have been widely employed in several BCI systems. However, the challenge of individual variability in signal patterns hinders the classifier’s efficacy. This article presents a fusion multi-scale convolutional neural network (MCNN) to perform an end-to-end MI EEG classification BCI system. The proposed multi-scale CNN fusion employed spatial and depthwise filters to learn temporal and spatial MI EEG features. Multiple scales of CNN are used, since characteristics at multiple scales to develop a subject-dependent model are crucial to learn, as each individual exhibits a unique signal pattern. The evaluation for classification performance is executed using the BCI Competition IV 2a (BCIC IV 2a) dataset. Furthermore, t-SNE visualisation is shown to illustrate features extracted for a subject. Compared with some existing state-of-the-art methodologies, the proposed method demonstrates enhancements in performance metrics. |
Description: | Copyright belongs to proceeding publisher |
URI: | http://hdl.handle.net/2080/4594 |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2024_IC2E3_KSDevi_Fusion.pdf | 307.99 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.