Attention Induced Dual Convolutional-Capsule Network (AIDC-CN): A deep learning framework for motor imagery classification

In recent times, Electroencephalography (EEG)-based motor imagery (MI) decoding has garnered significant attention due to its extensive applicability in healthcare, including areas such as assistive robotics and rehabilitation engineering. Nevertheless, the decoding of EEG signals presents considera...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computers in biology and medicine Ročník 183; s. 109260
Hlavní autori: Chowdhury, Ritesh Sur, Bose, Shirsha, Ghosh, Sayantani, Konar, Amit
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Elsevier Ltd 01.12.2024
Elsevier Limited
Predmet:
Algorithms
Attention
Attention - physiology
Brain
Brain - physiology
Brain-Computer Interfaces
Capsule network
Classification
Convolution
Decoding
Deep Learning
EEG
Electroencephalography
Electroencephalography (EEG)
Electroencephalography - methods
Error analysis
Feature extraction
Humans
Imagery
Imagination - physiology
Internal Medicine
Machine learning
Mental task performance
Modules
Motor imagery
Motor skill learning
Motor task performance
Neural networks
Neural Networks, Computer
Other
Robotics
Signal Processing, Computer-Assisted
Signal to noise ratio
Deep learning
Motor imagery
Electroencephalography (EEG)
Capsule network
ISSN:0010-4825, 1879-0534, 1879-0534
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In recent times, Electroencephalography (EEG)-based motor imagery (MI) decoding has garnered significant attention due to its extensive applicability in healthcare, including areas such as assistive robotics and rehabilitation engineering. Nevertheless, the decoding of EEG signals presents considerable challenges owing to their inherent complexity, non-stationary characteristics, and low signal-to-noise ratio. Notably, deep learning-based classifiers have emerged as a prominent focus for addressing the EEG signal decoding process. This study introduces a novel deep learning classifier named the Attention Induced Dual Convolutional-Capsule Network (AIDC-CN) with the specific aim of accurately categorizing various motor imagination class labels. To enhance the classifier’s performance, a dual feature extraction approach leveraging spectrogram and brain connectivity networks has been employed, diversifying the feature set in the classification task. The main highlights of the proposed AIDC-CN classifier includes the introduction of a dual convolution layer to handle the brain connectivity and spectrogram features, addition of a novel self-attention module (SAM) to accentuate the relevant parts of the convolved spectrogram features, introduction of a new cross-attention module (CAM) to refine the outputs obtained from the dual convolution layers and incorporation of a Gaussian Error Linear Unit (GELU) based dynamic routing algorithm to strengthen the coupling among the primary and secondary capsule layers. Performance analysis undertaken on four public data sets depict the superior performance of the proposed model with respect to the state-of-the-art techniques. The code for this model is available at https://github.com/RiteshSurChowdhury/AIDC-CN. •A deep learning paradigm to classify EEG signals of subjects during motor imagination.•A dual feature extraction strategy is used to improve the accuracy of the classifier.•Design of a novel deep learning based classifier to classify motor imagery classes.•Performance analysis undertaken depicts the efficacy of the proposed classifier.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2024.109260