A Coincidence-Filtering-Based Approach for CNNs in EEG-Based Recognition

Gao, Zhong-Ke; Li, Yanli; Yang, Yuxuan; Dong, Na; Yang, Xiong; Grebogi, Celso

doi:10.1109/tii.2019.2955447

Cited by 43 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BCIs have drawn great attention and have been widely applied to various fields, including driver fatigue detection [3], [4], emotion recognition [5], [6], entertainment for healthy users [7], [8], and others [9], [10].…”

mentioning

confidence: 99%

“…These RBMs are trained with the frequency domain features of EEG signals, which are obtained by fast Fourier transform and wavelet packet decomposition. Gao et al [6] designed simple convolutional neural network (ConvNet) based on coincidence filtering, using fewer parameters to tune yielded higher training efficiency for EEGbased classification. Zhao et al [25] first converted the EEG signals to a sequence of 2D array, then transformed it into a 3D representation; they proposed a multi-branch 3D convolutional neural network (3D ConvNet) which can preserve not only temporal features but also spatial ones.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Multiattention Adaptation Network for Motor Imagery Recognition

Chen

Gao

Yin

et al. 2022

IEEE Trans. Syst. Man Cybern, Syst.

Self Cite

View full text Add to dashboard Cite

Brain computer interface (BCI) based on motor imagery Electroencephalogram (EEG) has been widely used in various applications. Despite the previous efforts, the remained major challenges are effective feature extraction and timeconsuming calibration procedure. To address these issues, a novel Multi-Attention Adaptation Network integrating multiple attentions mechanism and transfer learning is proposed to classify the EEG signals. Firstly, the multi-attention layer is introduced to automatically capture the dominant brain regions relevant to mental tasks without incorporating any prior knowledge about the physiology. Then, a multi-attention convolutional neural network is employed to extract deep representation from raw EEG signals. Especially, a domain discriminator is applied to deep representation to reduce the differences between sessions for target subjects. The extensive experiments are conducted on three public EEG datasets (Dataset IIa and IIb of BCI Competition IV, High Gamma dataset), achieving the competitive performance with average classification accuracy of 81.48%, 82.54% and 93.97%, respectively. All the results outperform the state-of-theart algorithms demonstrate the effectiveness and robustness of the proposed method. Importantly, we confirm that it is easier and more appropriate to transfer the information from local brain regions than from the whole brain. This enhances the transfer ability of deep features and hence it improves the performance of BCI systems.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Multiattention Adaptation Network for Motor Imagery Recognition

Chen

Gao

Yin

et al. 2022

IEEE Trans. Syst. Man Cybern, Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, some novel CSP-based algorithms based on feature selection and channel selection methods are proposed to extract effective features [31,32]. Recently, several deep learning architectures [19,[33][34][35] have been exploited to learn deep representation and classifier for EEG signals in an end-toend manner. A review of deep learning analysis of EEG signals see [36].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Joint Domain Adaptation Network for Motor Imagery Classification

Hong

Zheng

Liu

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Electroencephalogram (EEG) has been widely used in brain computer interface (BCI) due to its convenience and reliability. The EEG-based BCI applications are majorly limited by the time-consuming calibration procedure for discriminative feature representation and classification. Existing EEG classification methods either heavily depend on the handcrafted features or require adequate annotated samples at each session for calibration. To address these issues, we propose a novel dynamic joint domain adaptation network based on adversarial learning strategy to learn domain-invariant feature representation, and thus improve EEG classification performance in the target domain by leveraging useful information from the source session. Specifically, we explore the global discriminator to align the marginal distribution across domains, and the local discriminator to reduce the conditional distribution discrepancy between subdomains via conditioning on deep representation as well as the predicted labels from the classifier. In addition, we further investigate a dynamic adversarial factor to adaptively estimate the relative importance of alignment between the marginal and conditional distributions. To evaluate the efficacy of our method, extensive experiments are conducted on two public EEG datasets, namely, Datasets IIa and IIb of BCI Competition IV. The experimental results demonstrate that the proposed method achieves superior performance compared with the state-of-the-art methods.Index Terms-Deep neural network (DNN), domain adaptation, adversarial learning, electroencephalogram (EEG), motor imagery (MI), brain-computer interface (BCI).

show abstract

“…Generally speaking, researchers of EEG emotion recognition based on deep learning mostly map EEG signals into pictures to facilitate input into neural networks. They encapsulate the data into a similar image and then use a convolutional neural network to obtain higher accuracy [ 24 – 28 ].…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition Based on EEG Using Generative Adversarial Nets and Convolutional Neural Network

Pan

Wei

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Emotion recognition plays an important role in the field of human-computer interaction (HCI). Automatic emotion recognition based on EEG is an important topic in brain-computer interface (BCI) applications. Currently, deep learning has been widely used in the field of EEG emotion recognition and has achieved remarkable results. However, due to the cost of data collection, most EEG datasets have only a small amount of EEG data, and the sample categories are unbalanced in these datasets. These problems will make it difficult for the deep learning model to predict the emotional state. In this paper, we propose a new sample generation method using generative adversarial networks to solve the problem of EEG sample shortage and sample category imbalance. In experiments, we explore the performance of emotion recognition with the frequency band correlation and frequency band separation computational models before and after data augmentation on standard EEG-based emotion datasets. Our experimental results show that the method of generative adversarial networks for data augmentation can effectively improve the performance of emotion recognition based on the deep learning model. And we find that the frequency band correlation deep learning model is more conducive to emotion recognition.

show abstract

A Coincidence-Filtering-Based Approach for CNNs in EEG-Based Recognition

Cited by 43 publications

References 29 publications

Multiattention Adaptation Network for Motor Imagery Recognition

Multiattention Adaptation Network for Motor Imagery Recognition

Dynamic Joint Domain Adaptation Network for Motor Imagery Classification

Emotion Recognition Based on EEG Using Generative Adversarial Nets and Convolutional Neural Network

Contact Info

Product

Resources

About