Xin Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xin Gao has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Dingguo Zhang
Department of Electronic and Electrical Engineering, University of Bath, Bath, U.K.
3 shared publications Benjamin Metcalfe
Department of Electronic and Electrical Engineering, University of Bath, Bath, U.K.
1 shared publication- Benjamin Metcalfe
University of Bath
1 shared publication Guangye Li
School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
1 shared publication- Hui Zhou
School of Automation, Nanjing University of Science and Technology, Nanjing, Jiangsu, China
1 shared publication Ibrahim Khalil
School of Automation, Nanjing University of Science and Technology, Nanjing, Jiangsu, China
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 7 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 50167-50187
Advancement in Graph Neural Networks for EEG Signal Analysis and Application: A Review
Electroencephalography (EEG) can non-invasivey measure neuronal events and reflect brain activity at different locations on the scalp. Early studies for EEG signal processing have focused more on extracting EEG temporal features and considered the topology of EEG channels less due to the limitation of rich spatial information. Graph neural networks (GNNs), as a new kind of deep learning method, can use EEG signals as graph vertices, capturing the hidden topological connections between signals. GNNs have made great progress in EEG studies due to the advantage. In this overview, we review the very new and fundamental models of GNNs and their modifications, such as graph regularized neural networks, graph convolutional neural networks, spatial-temporal graph neural networks, graph attention networks, and their variants in EEG signal analysis fields. The applications of GNNs are summarized in the domains of emotion detection, epilepsy seizure detection, stroke rehabilitation, Alzheimer’s disease diagnosis, motor imagery detection, neurological disease diagnosis, major depressive disorder, and driving fatigue detection. We employed a Systematic Literature Review (SLR) approach to select 79 papers for a comprehensive review. The current state is analyzed and forecasts are provided based on the available difficulties. We conclude by suggesting potential directions for future research in this rapidly developing topic.
- 7 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 50167-50187
Top Cited PapersOpen AccessAdvancement in Graph Neural Networks for EEG Signal Analysis and Application: A Review
Electroencephalography (EEG) can non-invasivey measure neuronal events and reflect brain activity at different locations on the scalp. Early studies for EEG signal processing have focused more on extracting EEG temporal features and considered the topology of EEG channels less due to the limitation of rich spatial information. Graph neural networks (GNNs), as a new kind of deep learning method, can use EEG signals as graph vertices, capturing the hidden topological connections between signals. GNNs have made great progress in EEG studies due to the advantage. In this overview, we review the very new and fundamental models of GNNs and their modifications, such as graph regularized neural networks, graph convolutional neural networks, spatial-temporal graph neural networks, graph attention networks, and their variants in EEG signal analysis fields. The applications of GNNs are summarized in the domains of emotion detection, epilepsy seizure detection, stroke rehabilitation, Alzheimer’s disease diagnosis, motor imagery detection, neurological disease diagnosis, major depressive disorder, and driving fatigue detection. We employed a Systematic Literature Review (SLR) approach to select 79 papers for a comprehensive review. The current state is analyzed and forecasts are provided based on the available difficulties. We conclude by suggesting potential directions for future research in this rapidly developing topic.
- Open Access
- 22 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3343-3355
Effects of Different Preprocessing Pipelines on Motor Imagery-Based Brain-Computer Interfaces
In recent years, brain-computer interfaces (BCIs) leveraging electroencephalography (EEG) signals for the control of external devices have garnered increasing attention. The information transfer rate of BCI has been significantly improved by a lot of cutting-edge methods. The exploration of effective preprocessing in brain-computer interfaces, particularly in terms of identifying suitable preprocessing methods and determining the optimal sequence for their application, remains an area ripe for further investigation. To address this gap, this study explores a range of preprocessing techniques, including but not limited to independent component analysis, surface Laplacian, bandpass filtering, and baseline correction, examining their potential contributions and synergies in the context of BCI applications. In this extensive research, a variety of preprocessing pipelines were rigorously tested across four EEG data sets, all of which were pertinent to motor imagery-based BCIs. These tests incorporated five EEG machine learning models, working in tandem with the preprocessing methods discussed earlier. The study's results highlighted that baseline correction and bandpass filtering consistently provided the most beneficial preprocessing effects. From the perspective of online deployment, after testing and time complexity analysis, this study recommends baseline correction, bandpass filtering and surface Laplace as more suitable for online implementation. An interesting revelation of the study was the enhanced effectiveness of the surface Laplacian algorithm when used alongside algorithms that focus on spatial information. Using appropriate processing algorithms, we can even achieve results (92.91% and 88.11%) that exceed the SOTA feature extraction methods in some cases. Such findings are instrumental in offering critical insights for the selection of effective preprocessing pipelines in EEG signal decoding. This, in turn, contributes to the advancement and refinement of brain-computer interface technologies.
- 22 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3343-3355
Open AccessEffects of Different Preprocessing Pipelines on Motor Imagery-Based Brain-Computer Interfaces
In recent years, brain-computer interfaces (BCIs) leveraging electroencephalography (EEG) signals for the control of external devices have garnered increasing attention. The information transfer rate of BCI has been significantly improved by a lot of cutting-edge methods. The exploration of effective preprocessing in brain-computer interfaces, particularly in terms of identifying suitable preprocessing methods and determining the optimal sequence for their application, remains an area ripe for further investigation. To address this gap, this study explores a range of preprocessing techniques, including but not limited to independent component analysis, surface Laplacian, bandpass filtering, and baseline correction, examining their potential contributions and synergies in the context of BCI applications. In this extensive research, a variety of preprocessing pipelines were rigorously tested across four EEG data sets, all of which were pertinent to motor imagery-based BCIs. These tests incorporated five EEG machine learning models, working in tandem with the preprocessing methods discussed earlier. The study's results highlighted that baseline correction and bandpass filtering consistently provided the most beneficial preprocessing effects. From the perspective of online deployment, after testing and time complexity analysis, this study recommends baseline correction, bandpass filtering and surface Laplace as more suitable for online implementation. An interesting revelation of the study was the enhanced effectiveness of the surface Laplacian algorithm when used alongside algorithms that focus on spatial information. Using appropriate processing algorithms, we can even achieve results (92.91% and 88.11%) that exceed the SOTA feature extraction methods in some cases. Such findings are instrumental in offering critical insights for the selection of effective preprocessing pipelines in EEG signal decoding. This, in turn, contributes to the advancement and refinement of brain-computer interface technologies.
- Open Access
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 800-811
Channel Selection for Stereo- Electroencephalography (SEEG)-Based Invasive Brain-Computer Interfaces Using Deep Learning Methods
Brain-computer interfaces (BCIs) can enable direct communication with assistive devices by recording and decoding signals from the brain. To achieve high performance, many electrodes will be used, such as the recently developed invasive BCIs with channel numbers up to hundreds or even thousands. For those high-throughput BCIs, channel selection is important to reduce signal redundancy and invasiveness while maintaining decoding performance. However, such endeavour is rarely reported for invasive BCIs, especially those using deep learning methods. Two deep learning-based methods, referred to as Gumbel and STG, were proposed in this paper. They were evaluated using the Stereo-electroencephalography (SEEG) signals, and compared with three other methods, including manual selection, mutual information-based method (MI), and all channels (all channels without selection). The task is to classify the SEEG signals into five movements using channels selected by each method. When 10 channels were selected, the mean classification accuracies using Gumbel, STG (referred to as STG-10), manual selection, and MI selection were 65%, 60%, 60%, and 47%, respectively, whilst the accuracy was 59% using all channels (no selection). In addition, an investigation of the selected channels showed that Gumbel and STG have successfully identified the pre-central and post-central areas, which are closely related to motor control. Both Gumbel and STG successfully selected the informative channels in SEEG recordings while maintaining decoding accuracy. This study enables future high-throughput BCIs using deep learning methods, to identify useful channels and reduce computing and wireless transmission pressure.
- 13 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 32 (15344320) , 800-811
Open AccessChannel Selection for Stereo- Electroencephalography (SEEG)-Based Invasive Brain-Computer Interfaces Using Deep Learning Methods
Brain-computer interfaces (BCIs) can enable direct communication with assistive devices by recording and decoding signals from the brain. To achieve high performance, many electrodes will be used, such as the recently developed invasive BCIs with channel numbers up to hundreds or even thousands. For those high-throughput BCIs, channel selection is important to reduce signal redundancy and invasiveness while maintaining decoding performance. However, such endeavour is rarely reported for invasive BCIs, especially those using deep learning methods. Two deep learning-based methods, referred to as Gumbel and STG, were proposed in this paper. They were evaluated using the Stereo-electroencephalography (SEEG) signals, and compared with three other methods, including manual selection, mutual information-based method (MI), and all channels (all channels without selection). The task is to classify the SEEG signals into five movements using channels selected by each method. When 10 channels were selected, the mean classification accuracies using Gumbel, STG (referred to as STG-10), manual selection, and MI selection were 65%, 60%, 60%, and 47%, respectively, whilst the accuracy was 59% using all channels (no selection). In addition, an investigation of the selected channels showed that Gumbel and STG have successfully identified the pre-central and post-central areas, which are closely related to motor control. Both Gumbel and STG successfully selected the informative channels in SEEG recordings while maintaining decoding accuracy. This study enables future high-throughput BCIs using deep learning methods, to identify useful channels and reduce computing and wireless transmission pressure.