EEG-Based Motor Imagery Classification with Deep Multi-Task Learning

Song, Yaguang; Wang, Danli; Kang, Young Jin; Zheng, Nan; Shen, Zuo‐Jun Max

doi:10.1109/ijcnn.2019.8852362

Cited by 19 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it can yield fast learning speed and increase data efficiency for related or downstream tasks. For example, Song et al proposed an EEG classification method based on multi-task DL [11], as shown in Fig. 4.…”

Section: Discriminator Classifiermentioning

confidence: 99%

“…However, EEG classification performance deteriorates as the number of available training samples diminishes, emphasizing the need for robust DL models under more typical small sample size scenarios [10]. Transfer learning [8], multi-task learning [11] and multi-modal learning [12] have been recently proposed to address small-sample data concerns. DL models have usually assumed that the categories of the test EEG signals have been seen during training.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey

Chen,

Li,

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Electroencephalogram (EEG) decoding aims to identify the perceptual, semantic, and cognitive content of neural processing based on non-invasively measured brain activity. Traditional EEG decoding methods have achieved moderate success when applied to data acquired in static, well-controlled lab environments. However, an open-world environment is a more realistic setting, where situations affecting EEG recordings can emerge unexpectedly, significantly weakening the robustness of existing methods. In recent years, deep learning (DL) has emerged as a potential solution for such problems due to its superior capacity in feature extraction. It overcomes the limitations of defining 'handcrafted' features or features extracted using shallow architectures, but typically requires large amounts of costly, expertly-labelled data -something not always obtainable. Combining DL with domain-specific knowledge may allow for development of robust approaches to decode brain activity even with small-sample data. Although various DL methods have been proposed to tackle some of the challenges in EEG decoding, a systematic tutorial overview, particularly for open-world applications, is currently lacking. This article therefore provides a comprehensive survey of DL methods for open-world EEG decoding, and identifies promising research directions to inspire future studies for EEG decoding in real-world applications.

show abstract

Section: Discriminator Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey

Chen,

Li,

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To confirm the effectiveness and accuracy of the proposed method, we first conducted intra-subject classification using BCIIV2a and compared the accuracy of our method with that given by state-of-the-art DL-based methods [EEGNet (Lawhern et al, 2018), DeepCNN (Schirrmeister et al, 2017), M3DCNN (Zhao et al, 2019), LTICNN (Sakhavi et al, 2018), DMTLCNN (Song et al, 2019), MCCNN (Amin et al, 2019), WTL (Azab et al, 2019)]; traditional FBCSP (Ang et al, 2012) was used as a baseline method to recognize MI EEG data, and an SVM was used as the classifier. Table 4 lists the accuracy of the various methods for each subject and the corresponding average accuracy for the BCIIV2a dataset.…”

Section: Quantitative Evaluation Of Bciiv2a For Intra-subject Classifmentioning

confidence: 99%

“…Azab et al (2019) proposed a novel weighted transfer learning approach that improves the accuracy of MI classification in BCI systems. Song et al (2019) improved the classification performance with limited EEG data by combining the representation module, classification module, and reconstruction module into an end-to-end framework. Sakhavi et al (2018) introduced a new data representation using a spatial-temporal DL model architecture that is designed to learn temporal information from the original input signals.…”

Section: Introductionmentioning

confidence: 99%

Parallel Spatial–Temporal Self-Attention CNN-Based Motor Imagery Classification for BCI

et al. 2020

View full text Add to dashboard Cite

Motor imagery (MI) electroencephalography (EEG) classification is an important part of the brain-computer interface (BCI), allowing people with mobility problems to communicate with the outside world via assistive devices. However, EEG decoding is a challenging task because of its complexity, dynamic nature, and low signal-to-noise ratio. Designing an end-to-end framework that fully extracts the high-level features of EEG signals remains a challenge. In this study, we present a parallel spatial–temporal self-attention-based convolutional neural network for four-class MI EEG signal classification. This study is the first to define a new spatial-temporal representation of raw EEG signals that uses the self-attention mechanism to extract distinguishable spatial–temporal features. Specifically, we use the spatial self-attention module to capture the spatial dependencies between the channels of MI EEG signals. This module updates each channel by aggregating features over all channels with a weighted summation, thus improving the classification accuracy and eliminating the artifacts caused by manual channel selection. Furthermore, the temporal self-attention module encodes the global temporal information into features for each sampling time step, so that the high-level temporal features of the MI EEG signals can be extracted in the time domain. Quantitative analysis shows that our method outperforms state-of-the-art methods for intra-subject and inter-subject classification, demonstrating its robustness and effectiveness. In terms of qualitative analysis, we perform a visual inspection of the new spatial–temporal representation estimated from the learned architecture. Finally, the proposed method is employed to realize control of drones based on EEG signal, verifying its feasibility in real-time applications.

show abstract

“…Brain-computer-interface(BCI) technology has drawn much attention globally due to its significant meaning and extensive applications [1]. It enables their users to interact with the machine through the brain signals [2], such as the task of converting the psychological imagination of motion into a command [3], which can be utilized to help people with disabilities as a rehabilitation device [4] and could be considered the only way for people with motor disabilities to communicate [5].…”

Section: Introductionmentioning

confidence: 99%

MCGNet+: An Improved Motor Imagery Classication Based on Cosine Similarity

Zhong

Taniar

et al. 2021

Preprint

View full text Add to dashboard Cite

It has been a challenge for solving the motor imagery classification problem in the brain informatics area. Accuracy and efficiency are the major obstacles for motor imagery analysis in the past decades since the computational capability and algorithmic availability cannot satisfy complex brain signal analysis. In recent years, the rapid development of Machine Learning (ML) methods has empowered people to tackle the motor imagery classification problem with more efficient methods. Among various ML methods, the Graph neural networks(GNNs) method has shown its efficiency and accuracy in dealing with inter-related complex networks. The use of GNN provides new possibilities for feature extraction from brain structure connection. In this paper, we proposed a new model called MCGNet+, which improves the performance of our previous model MutualGraphNet. In this latest model, the mutual information of the input columns forms the initial adjacency matrix for the cosine similarity calculation between columns to generate a new adjacency matrix in each iteration. The dynamic adjacency matrix combined with the spatial temporal graph convolution network(ST-GCN) has better performance than the unchanged matrix model. The experimental results indicate that MCGNet+ is robust enough to learn the interpretable features and outperforms the current state-of-the-art methods.

show abstract

EEG-Based Motor Imagery Classification with Deep Multi-Task Learning

Cited by 19 publications

References 23 publications

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey

Parallel Spatial–Temporal Self-Attention CNN-Based Motor Imagery Classification for BCI

MCGNet+: An Improved Motor Imagery Classication Based on Cosine Similarity

Contact Info

Product

Resources

About