DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets
<italic>Objective:</italic> Dim target detection in remote sensing images is a significant and challenging problem. In this work, we seek to explore event-related brain responses of dim target detection tasks and extend the brain-computer interface (BCI) systems to this task for efficien...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9801685/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850271932355706880 |
|---|---|
| author | Liangwei Fan Hui Shen Fengyu Xie Jianpo Su Yang Yu Dewen Hu |
| author_facet | Liangwei Fan Hui Shen Fengyu Xie Jianpo Su Yang Yu Dewen Hu |
| author_sort | Liangwei Fan |
| collection | DOAJ |
| description | <italic>Objective:</italic> Dim target detection in remote sensing images is a significant and challenging problem. In this work, we seek to explore event-related brain responses of dim target detection tasks and extend the brain-computer interface (BCI) systems to this task for efficiency enhancement. Methods: We develop a BCI paradigm named Asynchronous Visual Evoked Paradigm (AVEP), in which subjects are required to search the dim targets within satellite images when their scalp electroencephalography (EEG) signals are simultaneously recorded. In the paradigm, stimulus onset time and target onset time are asynchronous because subjects need enough time to confirm whether there are targets of interest in the presented serial images. We further propose a Domain adaptive and Channel-wise attention-based Time-domain Convolutional Neural Network (DC-tCNN) to solve the single-trial EEG classification problem for the AVEP task. In this model, we design a multi-scale CNN module combined with a channel-wise attention module to effectively extract event-related brain responses underlying EEG signals. Meanwhile, domain adaptation is proposed to mitigate cross-subject distribution discrepancy. Results: The results demonstrate the superior performance and better generalizability of this model in classifying the single-trial EEG data of AVEP task in contrast to typical EEG deep learning networks. Visualization analyses of spatiotemporal features also illustrate the effectiveness and interpretability of our proposed paradigm and learning model. Conclusion: The proposed paradigm and model can effectively explore ambiguous event-related brain responses on EEG-based dim target detection tasks. Significance: Our work can provide a valuable reference for BCI-based image detection of dim targets. |
| format | Article |
| id | doaj-art-2da92ff4fdc34e61b7c0fcf60527f506 |
| institution | OA Journals |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-2da92ff4fdc34e61b7c0fcf60527f5062025-08-20T01:52:02ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102022-01-01301727173610.1109/TNSRE.2022.31847259801685DC-tCNN: A Deep Model for EEG-Based Detection of Dim TargetsLiangwei Fan0https://orcid.org/0000-0002-0874-3947Hui Shen1https://orcid.org/0000-0002-5582-4555Fengyu Xie2Jianpo Su3https://orcid.org/0000-0001-7653-914XYang Yu4https://orcid.org/0000-0002-8967-0427Dewen Hu5https://orcid.org/0000-0001-7357-0053College of Intelligence Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha, China<italic>Objective:</italic> Dim target detection in remote sensing images is a significant and challenging problem. In this work, we seek to explore event-related brain responses of dim target detection tasks and extend the brain-computer interface (BCI) systems to this task for efficiency enhancement. Methods: We develop a BCI paradigm named Asynchronous Visual Evoked Paradigm (AVEP), in which subjects are required to search the dim targets within satellite images when their scalp electroencephalography (EEG) signals are simultaneously recorded. In the paradigm, stimulus onset time and target onset time are asynchronous because subjects need enough time to confirm whether there are targets of interest in the presented serial images. We further propose a Domain adaptive and Channel-wise attention-based Time-domain Convolutional Neural Network (DC-tCNN) to solve the single-trial EEG classification problem for the AVEP task. In this model, we design a multi-scale CNN module combined with a channel-wise attention module to effectively extract event-related brain responses underlying EEG signals. Meanwhile, domain adaptation is proposed to mitigate cross-subject distribution discrepancy. Results: The results demonstrate the superior performance and better generalizability of this model in classifying the single-trial EEG data of AVEP task in contrast to typical EEG deep learning networks. Visualization analyses of spatiotemporal features also illustrate the effectiveness and interpretability of our proposed paradigm and learning model. Conclusion: The proposed paradigm and model can effectively explore ambiguous event-related brain responses on EEG-based dim target detection tasks. Significance: Our work can provide a valuable reference for BCI-based image detection of dim targets.https://ieeexplore.ieee.org/document/9801685/Asynchronous visual evoked paradigm (AVEP)brain-computer interface (BCI)channel-wise attentiondim target detectiondomain adaptationelectroencephalography (EEG) |
| spellingShingle | Liangwei Fan Hui Shen Fengyu Xie Jianpo Su Yang Yu Dewen Hu DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets IEEE Transactions on Neural Systems and Rehabilitation Engineering Asynchronous visual evoked paradigm (AVEP) brain-computer interface (BCI) channel-wise attention dim target detection domain adaptation electroencephalography (EEG) |
| title | DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets |
| title_full | DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets |
| title_fullStr | DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets |
| title_full_unstemmed | DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets |
| title_short | DC-tCNN: A Deep Model for EEG-Based Detection of Dim Targets |
| title_sort | dc tcnn a deep model for eeg based detection of dim targets |
| topic | Asynchronous visual evoked paradigm (AVEP) brain-computer interface (BCI) channel-wise attention dim target detection domain adaptation electroencephalography (EEG) |
| url | https://ieeexplore.ieee.org/document/9801685/ |
| work_keys_str_mv | AT liangweifan dctcnnadeepmodelforeegbaseddetectionofdimtargets AT huishen dctcnnadeepmodelforeegbaseddetectionofdimtargets AT fengyuxie dctcnnadeepmodelforeegbaseddetectionofdimtargets AT jianposu dctcnnadeepmodelforeegbaseddetectionofdimtargets AT yangyu dctcnnadeepmodelforeegbaseddetectionofdimtargets AT dewenhu dctcnnadeepmodelforeegbaseddetectionofdimtargets |