MI‐Mamba: A hybrid motor imagery electroencephalograph classification model with Mamba's global scanning

Jan 23, 2025Annals of the New York Academy of Sciences

A hybrid model combining global scanning and motor imagery to classify brain signals

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

MI-Mamba achieves 84.42% accuracy in a two-class motor imagery task using EEG data.

MI-Mamba combines convolutional neural networks with a state space model for improved EEG decoding.
The model processes EEG signals through a single convolutional layer to capture local spatial features.
A state space model module is utilized to analyze global temporal features in the data.
MI-Mamba reduces the parameter count by nearly six times compared to previous advanced models.
Evaluations on public datasets demonstrate MI-Mamba's effectiveness in motor imagery decoding.

AI simplified

Deep learning has revolutionized electroencephalograph (EEG) decoding, with convolutional neural networks (CNNs) being a predominant tool. However, CNNs struggle with long-term dependencies in sequential EEG data. Models like long short-term memory and transformers improve performance but still face challenges of computational efficiency and long sequences. Mamba, a state space model-based method, excels in modeling long sequences. To overcome the limitations of existing EEG decoding models and exploit Mamba's potential in EEG analysis, we propose MI-Mamba, a model integrating CNN with Mamba for motor imagery (MI) data decoding. MI-Mamba processes multi-channel EEG signals through a single convolutional layer to capture spatial features in the local temporal domain, followed by a Mamba module that processes global temporal features. A fully connected, layer-based classifier is used to derive classification results. Evaluated on two public MI datasets, MI-Mamba achieves 80.59% accuracy in the four-class MI task of the BCI Competition IV 2a dataset and 84.42% in the two-class task of the BCI Competition IV 2b dataset, while reducing parameter count by nearly six times compared to the most advanced previous models. These results highlight MI-Mamba's effectiveness in MI decoding and its potential as a new backbone for general EEG decoding.

Full Text

Full text is available at the source.

View full text ↗

MI‐Mamba: A hybrid motor imagery electroencephalograph classification model with Mamba's global scanning

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