Cargando…

P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection

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 dy...

Descripción completa

Detalles Bibliográficos
Autores principales: Song, Xiyu, Zeng, Ying, Tong, Li, Shu, Jun, Bao, Guangcheng, Yan, Bin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8381600/
https://www.ncbi.nlm.nih.gov/pubmed/34434096
http://dx.doi.org/10.3389/fnhum.2021.685173
_version_ 1783741403167195136
author Song, Xiyu
Zeng, Ying
Tong, Li
Shu, Jun
Bao, Guangcheng
Yan, Bin
author_facet Song, Xiyu
Zeng, Ying
Tong, Li
Shu, Jun
Bao, Guangcheng
Yan, Bin
author_sort Song, Xiyu
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8381600
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-83816002021-08-24 P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection Song, Xiyu Zeng, Ying Tong, Li Shu, Jun Bao, Guangcheng Yan, Bin Front Hum Neurosci Human Neuroscience 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. Frontiers Media S.A. 2021-08-09 /pmc/articles/PMC8381600/ /pubmed/34434096 http://dx.doi.org/10.3389/fnhum.2021.685173 Text en Copyright © 2021 Song, Zeng, Tong, Shu, Bao and Yan. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Human Neuroscience
Song, Xiyu
Zeng, Ying
Tong, Li
Shu, Jun
Bao, Guangcheng
Yan, Bin
P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection
title P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection
title_full P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection
title_fullStr P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection
title_full_unstemmed P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection
title_short P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection
title_sort p3-msda: multi-source domain adaptation network for dynamic visual target detection
topic Human Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8381600/
https://www.ncbi.nlm.nih.gov/pubmed/34434096
http://dx.doi.org/10.3389/fnhum.2021.685173
work_keys_str_mv AT songxiyu p3msdamultisourcedomainadaptationnetworkfordynamicvisualtargetdetection
AT zengying p3msdamultisourcedomainadaptationnetworkfordynamicvisualtargetdetection
AT tongli p3msdamultisourcedomainadaptationnetworkfordynamicvisualtargetdetection
AT shujun p3msdamultisourcedomainadaptationnetworkfordynamicvisualtargetdetection
AT baoguangcheng p3msdamultisourcedomainadaptationnetworkfordynamicvisualtargetdetection
AT yanbin p3msdamultisourcedomainadaptationnetworkfordynamicvisualtargetdetection