EEG-CDILNet: a lightweight and accurate CNN network using circular dilated convolution for motor imagery classification

Aug 8, 2023Journal of neural engineering

A lightweight and accurate neural network using circular dilated convolution for classifying imagined movements

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

The proposed EEG-circular dilated convolution (CDIL) network achieved an average classification accuracy of 79.63% for the BCIIV2a dataset.

The model utilizes depth-separable convolution to minimize trainable parameters while enhancing classification accuracy.
It extracts both temporal and spatial features from motor imagery electroencephalography (EEG) signals.
The CDIL network combines features from different stages and employs global average pooling to further reduce parameters.
For the HGD four-classification task, the model achieved a classification accuracy of 94.53%.
The BCIIV2b two-classification task resulted in a classification accuracy of 87.82%.
The model demonstrates a favorable balance between decoding performance and computational cost compared to other lightweight models.

AI simplified

The combination of the motor imagery (MI) electroencephalography (EEG) signals and deep learning-based methods is an effective way to improve MI classification accuracy. However, deep learning-based methods often need too many trainable parameters. As a result, the trade-off between the network decoding performance and computational cost has always been an important challenge in the MI classification research.In the present study, we proposed a new end-to-end convolutional neural network (CNN) model called the EEG-circular dilated convolution (CDIL) network, which takes into account both the lightweight model and the classification accuracy. Specifically, the depth-separable convolution was used to reduce the number of network parameters and extract the temporal and spatial features from the EEG signals. CDIL was used to extract the time-varying deep features that were generated in the previous stage. Finally, we combined the features extracted from the two stages and used the global average pooling to further reduce the number of parameters, in order to achieve an accurate MI classification. The performance of the proposed model was verified using three publicly available datasets.The proposed model achieved an average classification accuracy of 79.63% and 94.53% for the BCIIV2a and HGD four-classification task, respectively, and 87.82% for the BCIIV2b two-classification task. In particular, by comparing the number of parameters, computation and classification accuracy with other lightweight models, it was confirmed that the proposed model achieved a better balance between the decoding performance and computational cost. Furthermore, the structural feasibility of the proposed model was confirmed by ablation experiments and feature visualization.The results indicated that the proposed CNN model presented high classification accuracy with less computing resources, and can be applied in the MI classification research. Objective. Approach. Main results. Significance.

Full Text

Full text is available at the source.

View full text (HTML) ↗View full text (PDF) ↗

EEG-CDILNet: a lightweight and accurate CNN network using circular dilated convolution for motor imagery classification

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief

Abstract

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief