EEG-FMCNN: A fusion multi-branch 1D convolutional neural network for EEG-based motor imagery classification

Sep 20, 2023Medical & biological engineering & computing

Combining multiple neural network paths to classify imagined movements from EEG signals

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

The proposed EEG-FMCNN model achieved accuracies of 78.82% and 68.41% for subject-dependent and subject-independent modes, respectively.

Motor imagery EEG signals are challenging to decode due to low signal-to-noise ratios and variability between subjects.
The EEG-FMCNN model employs a novel multi-branch architecture that improves noise tolerance and addresses inter-subject variability.
By capturing information from different frequency bands, the model establishes optimal convolutional scales and depths.
Incorporation of 1D squeeze-and-excitation blocks and shortcut connections enhances the network's generalization and robustness.
Ablative and fine-tuning experiments demonstrated an average performance improvement of 7%.

AI simplified

Motor imagery (MI) electroencephalogram (EEG) signal is recognized as a promising paradigm for brain-computer interface (BCI) systems and has been extensively employed in various BCI applications, including assisting disabled individuals, controlling devices and environments, and enhancing human capabilities. The high-performance decoding capability of MI-EEG signals is a key issue that impacts the development of the industry. However, decoding MI-EEG signals is challenging due to the low signal-to-noise ratio and inter-subject variability. In response to the aforementioned core problems, this paper proposes a novel end-to-end network, a fusion multi-branch 1D convolutional neural network (EEG-FMCNN), to decode MI-EEG signals without pre-processing. The utilization of multi-branch 1D convolution not only exhibits a certain level of noise tolerance but also addresses the issue of inter-subject variability to some extent. This is attributed to the ability of multi-branch architectures to capture information from different frequency bands, enabling the establishment of optimal convolutional scales and depths. Furthermore, we incorporate 1D squeeze-and-excitation (SE) blocks and shortcut connections at appropriate locations to further enhance the generalization and robustness of the network. In the BCI Competition IV-2a dataset, our proposed model has obtained good experimental results, achieving accuracies of 78.82% and 68.41% for subject-dependent and subject-independent modes, respectively. In addition, extensive ablative experiments and fine-tuning experiments were conducted, resulting in a notable 7% improvement in the average performance of the network, which holds significant implications for the generalization and application of the network.

Full Text

Full text is available at the source.

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

EEG-FMCNN: A fusion multi-branch 1D convolutional neural network for EEG-based 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