A novel multi-branch hybrid neural network for motor imagery EEG signal classification

Ma, Weifeng; Xue, Hui; Sun, Xiang; Mao, Sijia; Wang, Liudi; Liu, Yang; Wang, Yuchen; Lin, Xuefen

doi:10.1016/j.bspc.2022.103718

Cited by 26 publications

(11 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Sr. no. Author Methodology Dataset Accuracy (%) 1 Dai et al 13 Transfer kernel CSP BCI III IVa 91.2 2 Taheri et al 18 CNN/ReLU BCI III IVa 96.34 3 Song et al 20 Transformer BCI IV 2a 84.2 BCI IV 2b 82.59 4 Yongkoo et al 42 CSP feature BCI III IVa 84.4 5 Ma et al 43 CNN-transformer BCI IV 2a 83.9 6 Zhang et al 44 CNN/LSTM BCI IV 2a 83 7 Proposed methodology BCI III IVa 99.5 BCI IV 2a 84 …”

Section: Resultsmentioning

confidence: 99%

Deep temporal networks for EEG-based motor imagery recognition

Sharma,

Upadhyay,

Sharma

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The electroencephalogram (EEG) based motor imagery (MI) signal classification, also known as motion recognition, is a highly popular area of research due to its applications in robotics, gaming, and medical fields. However, the problem is ill-posed as these signals are non-stationary and noisy. Recently, a lot of efforts have been made to improve MI signal classification using a combination of signal decomposition and machine learning techniques but they fail to perform adequately on large multi-class datasets. Previously, researchers have implemented long short-term memory (LSTM), which is capable of learning the time-series information, on the MI-EEG dataset for motion recognition. However, it can not model very long-term dependencies present in the motion recognition data. With the advent of transformer networks in natural language processing (NLP), the long-term dependency issue has been widely addressed. Motivated by the success of transformer algorithms, in this article, we propose a transformer-based deep learning neural network architecture that performs motion recognition on the raw BCI competition III IVa and IV 2a datasets. The validation results show that the proposed method achieves superior performance than the existing state-of-the-art methods. The proposed method produces classification accuracy of 99.7% and 84% on the binary class and the multi-class datasets, respectively. Further, the performance of the proposed transformer-based model is also compared with LSTM.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep temporal networks for EEG-based motor imagery recognition

Sharma,

Upadhyay,

Sharma

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Various kinds of deep learning models were proposed to classify EEG signals [11]- [14]. The application of a convolutional neural network (CNN) to an EEG-based BCI domain showed successful results for an end-to-end feature extraction and classification.…”

Section: Related Workmentioning

confidence: 99%

Multiscale Convolutional Transformer for EEG Classification of Mental Imagery in Different Modalities

Ahn

Lee

Jeong

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

A new kind of sequence-to-sequence model called a transformer has been applied to electroencephalogram (EEG) systems. However, the majority of EEG-based transformer models have applied attention mechanisms to the temporal domain, while the connectivity between brain regions and the relationship between different frequencies have been neglected. In addition, many related studies on imagery-based brain-computer interface (BCI) have been limited to classifying EEG signals within one type of imagery. Therefore, it is important to develop a general model to learn various types of neural representations. In this study, we designed an experimental paradigm based on motor imagery, visual imagery, and speech imagery tasks to interpret the neural representations during mental imagery in different modalities. We conducted EEG source localization to investigate the brain networks. In addition, we propose the multiscale convolutional transformer for decoding mental imagery, which applies multi-head attention over the spatial, spectral, and temporal domains. The proposed network shows promising performance with 0.62, 0.70, and 0.72 mental imagery accuracy with the private EEG dataset, BCI competition IV 2a dataset, and Arizona State University dataset, respectively, as compared to the conventional deep learning models. Hence, we believe that it will contribute significantly to overcoming the limited number of classes and low classification performances in the BCI system.

show abstract

“…Comparing MLP and LVQ, [52,53] found that LVQ and MLP perform well for high dimensional and lower dimensional inputs respectively. Some studies are reviewed by [23,43] where other deep learning algorithms such as Recurrent neural network (RNN), Long short-term memory (LSTM), Convolutional neural network (CNN) achieve relatively reasonable accuracy [54][55][56][57] in terms of large dataset, time-series prediction or image processing. However, both MLP and LVQ techniques have comparable sensitivity in terms of smaller size of training data and MLP is a faster training process.…”

Section: Related Workmentioning

confidence: 99%