当前位置: X-MOL 学术Front Hum Neurosci › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
P3-MSDA: Multi-source Domain Adaptation Network for the Dynamic Visual Target Detection
Frontiers in Human Neuroscience ( IF 2.4 ) Pub Date : 2021-07-07 , DOI: 10.3389/fnhum.2021.685173
Xiyu Song 1 , Ying Zeng 1, 2 , Li Tong 1 , Jun Shu 1 , Guangcheng Bao 1 , Bin Yan 1
Affiliation  

Single-trial EEG detection has been widely applied to brain-computer interface (BCI) systems. Moreover, an individual generalized model is significant for applying the dynamic visual target detection BCI system to real life due to 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 the dynamic visual target detection. In this network, a P3 map-clustering method was proposed for the 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 the 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 the existing schemes, the proposed P3-MSDA network achieved the highest classification accuracy and F1 score using five labelled individuals with a strong P3 map as the source domain. These findings can have a significant meaning in building an individual generalized model for the dynamic visual target detection.

中文翻译:

P3-MSDA:用于动态视觉目标检测的多源域自适应网络

单次脑电图检测已广泛应用于脑机接口(BCI)系统。此外,由于检测延迟的时间抖动、视觉背景的动态性和复杂性,单独的广义模型对于将动态视觉目标检测 BCI 系统应用于现实生活具有重要意义。因此,我们开发了一种用于动态视觉目标检测的无监督多源域适应网络(P3-MSDA)。在该网络中,提出了一种 P3 地图聚类方法用于源域选择。对域对齐进行对抗域自适应以消除个体差异,并对预测概率进行排序和返回,以指导目标样本的输入进行不平衡数据分类。结果表明,通过所提出的 P3 地图聚类方法选择的具有强 P3 地图的个体在源域上表现最佳。与现有方案相比,所提出的 P3-MSDA 网络使用五个具有强大 P3 映射的标记个体作为源域,实现了最高的分类准确率和 F1 分数。这些发现对于构建用于动态视觉目标检测的个体广义模型具有重要意义。
更新日期:2021-07-07
down
wechat
bug