Abstract
Single-trial electroencephalogram detection has been widely applied in brain-computer interface (BCI) systems. Moreover, an individual generalized model is significant for applying the dynamic visual target detection BCI system in real life because of the time jitter of the detection latency, the dynamics and complexity of visual background. Hence, we developed an unsupervised multi-source domain adaptation network (P3-MSDA) for dynamic visual target detection. In this network, a P3 map-clustering method was proposed for source domain selection. The adversarial domain adaptation was conducted for domain alignment to eliminate individual differences, and prediction probabilities were ranked and returned to guide the input of target samples for imbalanced data classification. The results showed that individuals with a strong P3 map selected by the proposed P3 map-clustering method perform best on the source domain. Compared with existing schemes, the proposed P3-MSDA network achieved the highest classification accuracy and F1 score using five labeled individuals with a strong P3 map as the source domain. These findings can have a significant meaning in building an individual generalized model for dynamic visual target detection.
Highlights
Brain-computer interface has developed a new way for human beings to communicate and control the outside world, and has a great application value and development potential in the fields of medical rehabilitation (Pan et al, 2018), recreation (Polina et al, 2018), and public safety (Ward and Obeid, 2018)
We proposed an unsupervised multi-source domain adaptation network (P3-MSDA) to develop an individual generalized model for dynamic visual target detection
Based on the excellent performance of the P3-sSDA network, we developed a P3-MSDA network, where source domain individuals are selected from the strong P3 map group
Summary
Brain-computer interface has developed a new way for human beings to communicate and control the outside world, and has a great application value and development potential in the fields of medical rehabilitation (Pan et al, 2018), recreation (Polina et al, 2018), and public safety (Ward and Obeid, 2018). Data distributions vary across individuals, restricting the generalization of computing models (Kaur et al, 2019; Lorena et al, 2019). It can be further aggravated for single-trial EEG detection in dynamic video target detection because of the absence of an explicit target onset time, time jitter of the detection latency, dynamics of visual background, and uncertainty of visual distracters (Song et al, 2020). More ERP components induced by dynamic visual targets contain P1, P2, P3, and a strong negative wave at around 500 ms All of these could further influence detection performance and enlarge individual difference for dynamic
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
