Spatio-Temporal Explanation of 3D-EEGNet for Motor Imagery EEG Classification Using Permutation and Saliency
Open Access
- 7 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 31 (15344320) , 4504-4513
Abstract
Recently, convolutional neural network (CNN)-based classification models have shown good performance for motor imagery (MI) brain-computer interfaces (BCI) using electroencephalogram (EEG) in end-to-end learning. Although a few explainable artificial intelligence (XAI) techniques have been developed, it is still challenging to interpret the CNN models for EEG-based BCI classification effectively. In this research, we propose 3D-EEGNet as a 3D CNN model to improve both the explainability and performance of MI EEG classification. The proposed approach exhibited better performances on two MI EEG datasets than the existing EEGNet, which uses a 2D input shape. The MI classification accuracies are improved around 1.8% and 6.1% point in average on the datasets, respectively. The permutation-based XAI method is first applied for the reliable explanation of the 3D-EEGNet. Next, to find a faster XAI method for spatio-temporal explanation, we design a novel technique based on the normalized discounted cumulative gain (NDCG) for selecting the best among a few saliency-based methods due to their higher time complexity than the permutation-based method. Among the saliency-based methods, DeepLIFT was selected because the NDCG scores indicated its results are the most similar to the permutation-based results. Finally, the fast spatio-temporal explanation using DeepLIFT provides deeper understanding for the classification results of the 3D-EEGNet and the important properties in the MI EEG experiments.Keywords
Funding Information
- Ministry of Science and ICT (MSIT), South Korea, through the High-Potential Individuals Global Training Program (2020001560)
- Artificial Intelligence Convergence Innovation Human Resources Development, Kyung Hee University, supervised by the Institute for Information and Communications Technology Planning and Evaluation (RS-2022-00155911)
This publication has 43 references indexed in Scilit:
- A Classification Algorithm for Electroencephalography Signals by Self-Induced Emotional StimuliIEEE Transactions on Cybernetics, 2015
- EEG Based Stress Monitoring2015
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Learning saliency-based visual attention: A reviewSignal Processing, 2013
- Extended BSI for continuous EEG monitoring in carotid endarterectomyClinical Neurophysiology, 2006
- The BCI competition III: validating alternative approaches to actual BCI problemsIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006
- Motor imageryJournal of Physiology-Paris, 2006
- Chapter 26 Spatiotemporal ERD/ERS patterns during voluntary movement and motor imagery2000
- Sensorimotor Cortex and Supplementary Motor Area Changes in SchizophreniaThe British Journal of Psychiatry, 1995
- Practical design rules for optimum FIR bandpass digital filtersIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979