Dual Attention Relation Network With Fine-Tuning for Few-Shot EEG Motor Imagery Classification
- 28 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (11) , 15479-15493
Abstract
Recently, motor imagery (MI) electroencephalography (EEG) classification techniques using deep learning have shown improved performance over conventional techniques. However, improving the classification accuracy on unseen subjects is still challenging due to intersubject variability, scarcity of labeled unseen subject data, and low signal-to-noise ratio (SNR). In this context, we propose a novel two-way few-shot network able to efficiently learn how to learn representative features of unseen subject categories and classify them with limited MI EEG data. The pipeline includes an embedding module that learns feature representations from a set of signals, a temporal-attention module to emphasize important temporal features, an aggregation-attention module for key support signal discovery, and a relation module for final classification based on relation scores between a support set and a query signal. In addition to the unified learning of feature similarity and a few-shot classifier, our method can emphasize informative features in support data relevant to the query, which generalizes better on unseen subjects. Furthermore, we propose to fine-tune the model before testing by arbitrarily sampling a query signal from the provided support set to adapt to the distribution of the unseen subject. We evaluate our proposed method with three different embedding modules on cross-subject and cross-dataset classification tasks using brain–computer interface (BCI) competition IV 2a, 2b, and GIST datasets. Extensive experiments show that our model significantly improves over the baselines and outperforms existing few-shot approaches.Keywords
Funding Information
- Daegu Gyeongbuk Institute of Science and Technology (DGIST) Research and Development Program of the Ministry of Science and the ICT (19-RT-01)
- Smart Health Care Program funded by the Korean National Police Agency (220222M01)
This publication has 75 references indexed in Scilit:
- Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signalsComputers in Biology and Medicine, 2018
- Driving behavior recognition using EEG data from a simulated car-following experimentAccident Analysis & Prevention, 2018
- Data Augmentation for EEG-Based Emotion Recognition with Deep Convolutional Neural Networks2018
- Deep learning with convolutional neural networks for EEG decoding and visualizationHuman Brain Mapping, 2017
- EEG datasets for motor imagery brain–computer interfaceGigaScience, 2017
- Adaptive Feature Extraction of Motor Imagery EEG with Optimal Wavelet Packets and SE-IsomapApplied Sciences, 2017
- Noninvasive Electroencephalogram Based Control of a Robotic Arm for Reach and Grasp TasksScientific Reports, 2016
- Classification of motor imagery movements using multivariate empirical mode decomposition and short time Fourier transform based hybrid methodEngineering Science and Technology, an International Journal, 2016
- Proprioceptive Feedback and Brain Computer Interface (BCI) Based NeuroprosthesesPLOS ONE, 2012
- A brain-actuated wheelchair: Asynchronous and non-invasive Brain–computer interfaces for continuous control of robotsClinical Neurophysiology, 2008