Jiahao Wu
Research Subjects
Jiahao Wu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Fazheng Hou
School of Information Engineering, Wuhan University of Technology, Wuhan, Hubei, China
2 shared publications - Jie Zuo
Wuhan University of Technology
2 shared publications Quan Liu
2 shared publicationsWei Meng
2 shared publications- Jingjing Kong1 shared publication
Li Ma
1 shared publication
Latest Publications
- Open Access
- 2 April 2026
- Published by Elsevier in SSRN Electronic Journal
EAMCCA: Euclidean Alignment based Multiscale Convolution and Channel Attention Network for MI-EEG Decoding
Electroencephalography (EEG)-based motor imagery (MI), as an important paradigm of brain computer interfaces (BCIs), has been explored for applications in fields like medical rehabilitation, driven by the continuous advancement of sensor and artificial intelligence technologies. However, it is still challenging to effectively utilize deep learning to obtain the most discriminative MI related EEG features. In this paper, we propose Euclidean alignment based multiscale convolution and channel attention (EAMCCA) network for MI-EEG decoding. Following EA preprocessing of raw EEG signals, the network employs two parallel branches to extract complementary features: the multiscale convolutional module that captures spatial-temporal features across different scales and the channel attention module that prioritizes features from MI-strongly relevant channels. Moreover, it utilizes the multi-head attention module, to capture the features’ contextual relationships and global temporal correlations. Finally, by capturing the two deep feature representations and modeling their interdependencies, the convolution module fuses them into highly discriminative features, which substantially enhances the performance of MI classification. We validated EAMCCA on three datasets: the BCI Competition IV-2a dataset, the BCI Competition IV-2b dataset, and the High Gamma Dataset (HGD). The experimental results indicate that EAMCCA achieves state-of the-art performance, with accuracies of 86.61%, 89.42%, and 93.61% in the respective experiments. The proposed method provides a strong reference for future personalized MI-EEG decoding with applications in rehabilitation.
- 2 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessEAMCCA: Euclidean Alignment based Multiscale Convolution and Channel Attention Network for MI-EEG Decoding
Electroencephalography (EEG)-based motor imagery (MI), as an important paradigm of brain computer interfaces (BCIs), has been explored for applications in fields like medical rehabilitation, driven by the continuous advancement of sensor and artificial intelligence technologies. However, it is still challenging to effectively utilize deep learning to obtain the most discriminative MI related EEG features. In this paper, we propose Euclidean alignment based multiscale convolution and channel attention (EAMCCA) network for MI-EEG decoding. Following EA preprocessing of raw EEG signals, the network employs two parallel branches to extract complementary features: the multiscale convolutional module that captures spatial-temporal features across different scales and the channel attention module that prioritizes features from MI-strongly relevant channels. Moreover, it utilizes the multi-head attention module, to capture the features’ contextual relationships and global temporal correlations. Finally, by capturing the two deep feature representations and modeling their interdependencies, the convolution module fuses them into highly discriminative features, which substantially enhances the performance of MI classification. We validated EAMCCA on three datasets: the BCI Competition IV-2a dataset, the BCI Competition IV-2b dataset, and the High Gamma Dataset (HGD). The experimental results indicate that EAMCCA achieves state-of the-art performance, with accuracies of 86.61%, 89.42%, and 93.61% in the respective experiments. The proposed method provides a strong reference for future personalized MI-EEG decoding with applications in rehabilitation.
- 15 May 2025
- Published by Elsevier in Neurocomputing
- Vol. 643
Emotion recognition via affective EEG signals: State of the art
- 15 May 2025
- Published by Elsevier in Neurocomputing
- Vol. 643
Emotion recognition via affective EEG signals: State of the art