Dynamic Mode Decomposition Based Artifact Removal from EEG Signals and Classification Using MI Tasks with Hybrid CNN-LSTM Network
Alt Text: Dynamic Mode Decomposition Based Artifact Removal from EEG Signals and Classification Using MI Tasks with Hybrid CNN-LSTM Network
Title: Dynamic Mode Decomposition Based Artifact Removal from EEG Signals and Classification Using MI Tasks with Hybrid CNN-LSTM Network
Caption: An advanced EEG classification approach using artifact removal via DMD.
Description: This study presents a method for artifact removal from EEG signals using Dynamic Mode Decomposition (DMD) to improve Brain-Computer Interfacing (BCI) classification accuracy. A four-class Motor Imagery EEG dataset from BCI Competition IIIa is analyzed using a hybrid CNN-LSTM network, achieving enhanced classification performance.
Keywords: IJET JOURNAL, Artifact Removal, DMD, BCI, EEG, Motor Imagery
International Journal of Engineering and Techniques – Volume 10 Issue 6, December 2024
Keerthi Krishnan K*, Reshmi S
Department of Electronics and Communication, NSS College of Engineering, Palakkad, India
Abstract
Data interpretation is critical for Electroencephalogram (EEG)-based Brain-Computer Interfacing (BCI) systems. Artifacts interfere with EEG signals, leading to classification errors. This study introduces Dynamic Mode Decomposition (DMD) for artifact removal, improving EEG classification using a hybrid CNN-LSTM network.
Keywords
Artifact Removal, DMD, BCI, EEG, Motor Imagery, Deep Learning
How to Cite
Keerthi Krishnan K, Reshmi S, “Dynamic Mode Decomposition Based Artifact Removal from EEG Signals and Classification Using MI Tasks with Hybrid CNN-LSTM Network,” International Journal of Engineering and Techniques, Volume 10, Issue 6, 2024. ISSN 2395-1303
Post Comment