Qi Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Qi Sun has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Yuanjian Liu
School of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
3 shared publications - Shuangde Li
College of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
2 shared publications - Xia-An Bi
College of Information Science and Engineering and the Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education), School of Mathematics and Statistics, Hunan Normal University, Changsha, China
2 shared publications - Chaodong Wang
Department of Neurology & Neurobiology, Xuanwu Hospital of Capital Medical University, National Clinical Research Center for Geriatric Diseases, Beijing, China
1 shared publication - Junxia Zhao
Key Laboratory of Marine Technology and Control Engineering, Shanghai Maritime University, Shanghai 201306, China
1 shared publication - Liqin Wang
First Affiliated Hospital, Heilongjiang University of Chinese Medicine, Harbin, China
1 shared publication
Latest Publications
- Open Access
- 5 February 2024
- Published by Wiley in Journal of Sensors
- Vol. 2024, 1-15
Automatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals
Epilepsy, a neurological disease associated with seizures, affects the normal behavior of human beings. The unpredictability of epileptic seizures has caused great obstacles to the treatment of the disease. The automatic seizure detection method based on electroencephalogram (EEG) can assist experts in predicting seizures to improve treatment efficiency. Epileptic seizure detection cannot be achieved accurately using the single-view characteristics of the signals. Moreover, manual feature extraction is a time-consuming task. To design a high-performance seizure identification method, automatic learning of multi-view features becomes an indispensable part for seizure detection. Therefore, the paper proposes a multi-input deep feature learning networks (MDFLN) model, which comprehensively considers the features from the time domain and the time–frequency (TF) domain for EEG signals. The MDFLN model automatically extracts the feature information of the signals through deep learning networks. Then, the bidirectional long short-term memory (BLSTM) network is used to distinguish seizure and nonseizure events. Furthermore, the effectiveness of the proposed network structure is verified in two public datasets. The experimental results demonstrate that the classification accuracy of the proposed method based on multi-view features is at least 2.2% higher than the single-view features. The MDFLN achieves better performance on CHB-MIT and Bonn datasets with accuracy of 98.09% and 98.4%, respectively. The fine-tuned model with the validation set also improves the classification performance. Compare with the state-of-the-art seizure detection methods, the multi-input deep learning network has superior competence with high sensitivity on the CHB-MIT dataset. The proposed automatic seizure detection method can reduce time consumption and effectively assist experts in the clinical diagnosis and treatment.
- 5 February 2024
- Published by Wiley in Journal of Sensors
- Vol. 2024, 1-15
Open AccessAutomatic Seizure Detection Using Multi-Input Deep Feature Learning Networks for EEG Signals
Epilepsy, a neurological disease associated with seizures, affects the normal behavior of human beings. The unpredictability of epileptic seizures has caused great obstacles to the treatment of the disease. The automatic seizure detection method based on electroencephalogram (EEG) can assist experts in predicting seizures to improve treatment efficiency. Epileptic seizure detection cannot be achieved accurately using the single-view characteristics of the signals. Moreover, manual feature extraction is a time-consuming task. To design a high-performance seizure identification method, automatic learning of multi-view features becomes an indispensable part for seizure detection. Therefore, the paper proposes a multi-input deep feature learning networks (MDFLN) model, which comprehensively considers the features from the time domain and the time–frequency (TF) domain for EEG signals. The MDFLN model automatically extracts the feature information of the signals through deep learning networks. Then, the bidirectional long short-term memory (BLSTM) network is used to distinguish seizure and nonseizure events. Furthermore, the effectiveness of the proposed network structure is verified in two public datasets. The experimental results demonstrate that the classification accuracy of the proposed method based on multi-view features is at least 2.2% higher than the single-view features. The MDFLN achieves better performance on CHB-MIT and Bonn datasets with accuracy of 98.09% and 98.4%, respectively. The fine-tuned model with the validation set also improves the classification performance. Compare with the state-of-the-art seizure detection methods, the multi-input deep learning network has superior competence with high sensitivity on the CHB-MIT dataset. The proposed automatic seizure detection method can reduce time consumption and effectively assist experts in the clinical diagnosis and treatment.
- Open Access
- 19 October 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (1) , 899-909
Weighted directed graph-based automatic seizure detection with effective brain connectivity for EEG signals
Epileptic seizure is one of the most common neurological disorders characterized by sudden abnormal discharge of neurons in the brain. Automated seizure detection using electroencephalograph (EEG) recordings would improve the quality of treatment and reduce medical overhead. The purpose of this paper is to design an automated seizure detection framework that can effectively identify seizure and non-seizure events by discovering connectivity between brain regions. In this work, a weighted directed graph-based method with effective brain connectivity (EBC) is proposed for seizure detection. The weighted directed graph is built by analyzing the correlation among the different regions of the brain. Then, graph theory-based measures are used to extract features for classification. Furthermore, we illustrate the ability of the proposed method to achieve seizure detection for the patient-specific model and the cross-patient model. The results show that the proposed method achieves accuracy values of 99.97% and 98.29% for the patient-specific model and the cross-patient model in the CHB-MIT dataset, respectively. These results demonstrate that the proposed method achieves an effective classification performance and can be used to provide assistance for automatic seizure detection and clinical diagnosis.
- 19 October 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (1) , 899-909
Open AccessWeighted directed graph-based automatic seizure detection with effective brain connectivity for EEG signals
Epileptic seizure is one of the most common neurological disorders characterized by sudden abnormal discharge of neurons in the brain. Automated seizure detection using electroencephalograph (EEG) recordings would improve the quality of treatment and reduce medical overhead. The purpose of this paper is to design an automated seizure detection framework that can effectively identify seizure and non-seizure events by discovering connectivity between brain regions. In this work, a weighted directed graph-based method with effective brain connectivity (EBC) is proposed for seizure detection. The weighted directed graph is built by analyzing the correlation among the different regions of the brain. Then, graph theory-based measures are used to extract features for classification. Furthermore, we illustrate the ability of the proposed method to achieve seizure detection for the patient-specific model and the cross-patient model. The results show that the proposed method achieves accuracy values of 99.97% and 98.29% for the patient-specific model and the cross-patient model in the CHB-MIT dataset, respectively. These results demonstrate that the proposed method achieves an effective classification performance and can be used to provide assistance for automatic seizure detection and clinical diagnosis.
- Open Access
- 28 October 2022
- Published by Wiley in Journal of Sensors
- Vol. 2022, 1-16
Automatic Epileptic Seizure Detection Using PSO-Based Feature Selection and Multilevel Spectral Analysis for EEG Signals
Automatic epileptic seizure detection technologies for clinical diagnosis mainly rely on electroencephalogram (EEG) recordings, which are immensely useful tools for epileptic location and identification. Currently, traditional seizure detection methods based only on single-view features have great limitations for the typical dynamic and nonlinear EEG signals. An objective of this paper is to investigate the effect of multiview feature selection and multilevel spectral analysis methods on the identification of the EEG signals for seizure detection. Here, multiview features are extracted from time domain, frequency domain, and information theory to collect adequate information of EEG signals. And a feature selection algorithm based on particle swarm optimization (PSO) is proposed for automatic seizure detection. Moreover, due to the different frequency components of the EEG signals, they are divided into four kinds of brain waves for multilevel spectral analysis. The effect of these four rhythm waves on seizure detection is compared. Three well-known classifiers are employed to classify EEG signals concerning seizure or nonseizure events. The result shows that the average accuracy, specificity, and sensitivity of classification with the CHB-MIT database are 98.14%, 98.64%, and 96.79%, respectively. The application of the PSO-based feature selection method for automatic seizure detection improves accuracy by 5.99% with the SVM classifier. Compared with the state-of-the-art methods, the proposed method has superior competence with high performance for automatic seizure detection. It is further shown that the feature selection method is an indispensable step in seizure detection. With PSO-based feature selection and multilevel spectral analysis, the wave in the frequency range of 4-7 Hz shows better performance in the identification of EEG signals and is more suitable for the proposed method. The PSO-based feature selection algorithm for automatic seizure detection can be a useful assistant tool for clinical diagnosis.
- 28 October 2022
- Published by Wiley in Journal of Sensors
- Vol. 2022, 1-16
Open AccessAutomatic Epileptic Seizure Detection Using PSO-Based Feature Selection and Multilevel Spectral Analysis for EEG Signals
Automatic epileptic seizure detection technologies for clinical diagnosis mainly rely on electroencephalogram (EEG) recordings, which are immensely useful tools for epileptic location and identification. Currently, traditional seizure detection methods based only on single-view features have great limitations for the typical dynamic and nonlinear EEG signals. An objective of this paper is to investigate the effect of multiview feature selection and multilevel spectral analysis methods on the identification of the EEG signals for seizure detection. Here, multiview features are extracted from time domain, frequency domain, and information theory to collect adequate information of EEG signals. And a feature selection algorithm based on particle swarm optimization (PSO) is proposed for automatic seizure detection. Moreover, due to the different frequency components of the EEG signals, they are divided into four kinds of brain waves for multilevel spectral analysis. The effect of these four rhythm waves on seizure detection is compared. Three well-known classifiers are employed to classify EEG signals concerning seizure or nonseizure events. The result shows that the average accuracy, specificity, and sensitivity of classification with the CHB-MIT database are 98.14%, 98.64%, and 96.79%, respectively. The application of the PSO-based feature selection method for automatic seizure detection improves accuracy by 5.99% with the SVM classifier. Compared with the state-of-the-art methods, the proposed method has superior competence with high performance for automatic seizure detection. It is further shown that the feature selection method is an indispensable step in seizure detection. With PSO-based feature selection and multilevel spectral analysis, the wave in the frequency range of 4-7 Hz shows better performance in the identification of EEG signals and is more suitable for the proposed method. The PSO-based feature selection algorithm for automatic seizure detection can be a useful assistant tool for clinical diagnosis.
- 1 January 2019
- Published by Elsevier in Mathematics and Computers in Simulation
- Vol. 155, 78-91
Branch tire packet classification algorithm based on single-linkage clustering
- 1 January 2019
- Published by Elsevier in Mathematics and Computers in Simulation
- Vol. 155, 78-91
Branch tire packet classification algorithm based on single-linkage clustering
- Open Access
- 19 June 2018
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 12, 413
Non-linear ICA Analysis of Resting-State fMRI in Mild Cognitive Impairment
Compared to linear independent component analysis (ICA), non-linear ICA is more suitable for the decomposition of mixed components. Existing studies of functional magnetic resonance imaging (fMRI) data by using linear ICA assume that the brain's mixed signals, which are caused by the activity of brain, are formed through the linear combination of source signals. But the application of the non-linear combination of source signals is more suitable for the mixed signals of brain. For this reason, we investigated statistical differences in resting state networks (RSNs) on 32 healthy controls (HC) and 38 mild cognitive impairment (MCI) patients using post-nonlinear ICA. Post-nonlinear ICA is one of the non-linear ICA methods. Firstly, the fMRI data of all subjects was preprocessed. The second step was to extract independent components (ICs) of fMRI data of all subjects. In the third step, we calculated the correlation coefficient between ICs and RSN templates, and selected ICs of the largest spatial correlation coefficient. The ICs represent the corresponding RSNs. After finding out the eight RSNs of MCI group and HC group, one sample t-tests were performed. Finally, in order to compare the differences of RSNs between MCI and HC groups, the two-sample t-tests were carried out. We found that the functional connectivity (FC) of RSNs in MCI patients was abnormal. Compared with HC, MCI patients showed the increased and decreased FC in default mode network (DMN), central executive network (CEN), dorsal attention network (DAN), somato-motor network (SMN), visual network(VN), MCI patients displayed the specifically decreased FC in auditory network (AN), self-referential network (SRN). The FC of core network (CN) did not reveal significant group difference. The results indicate that the abnormal FC in RSNs is selective in MCI patients.
- 19 June 2018
- Published by Frontiers Media SA in Frontiers in Neuroscience
- Vol. 12, 413
Open AccessNon-linear ICA Analysis of Resting-State fMRI in Mild Cognitive Impairment
Compared to linear independent component analysis (ICA), non-linear ICA is more suitable for the decomposition of mixed components. Existing studies of functional magnetic resonance imaging (fMRI) data by using linear ICA assume that the brain's mixed signals, which are caused by the activity of brain, are formed through the linear combination of source signals. But the application of the non-linear combination of source signals is more suitable for the mixed signals of brain. For this reason, we investigated statistical differences in resting state networks (RSNs) on 32 healthy controls (HC) and 38 mild cognitive impairment (MCI) patients using post-nonlinear ICA. Post-nonlinear ICA is one of the non-linear ICA methods. Firstly, the fMRI data of all subjects was preprocessed. The second step was to extract independent components (ICs) of fMRI data of all subjects. In the third step, we calculated the correlation coefficient between ICs and RSN templates, and selected ICs of the largest spatial correlation coefficient. The ICs represent the corresponding RSNs. After finding out the eight RSNs of MCI group and HC group, one sample t-tests were performed. Finally, in order to compare the differences of RSNs between MCI and HC groups, the two-sample t-tests were carried out. We found that the functional connectivity (FC) of RSNs in MCI patients was abnormal. Compared with HC, MCI patients showed the increased and decreased FC in default mode network (DMN), central executive network (CEN), dorsal attention network (DAN), somato-motor network (SMN), visual network(VN), MCI patients displayed the specifically decreased FC in auditory network (AN), self-referential network (SRN). The FC of core network (CN) did not reveal significant group difference. The results indicate that the abnormal FC in RSNs is selective in MCI patients.