基于快速序列视觉呈现(rapid serial visual presentation,RSVP)范式的目标图像检索借助于人脑在看到目标图像时产生的事件相关电位(event-related potentials,ERP)来完成复杂目标图像检索。在应用RSVP范式进行复杂目标图像检索时存在...基于快速序列视觉呈现(rapid serial visual presentation,RSVP)范式的目标图像检索借助于人脑在看到目标图像时产生的事件相关电位(event-related potentials,ERP)来完成复杂目标图像检索。在应用RSVP范式进行复杂目标图像检索时存在跨时段甚至跨被试的问题。对此,本文提出了一种面向跨被试RSVP的多特征低维子空间嵌入的ERP检测方法,首先采用迁移学习方法中的欧式空间对齐对不同被试的数据进行对齐,其次将来自不同空间的特征分别进行有监督降维、重构。最终采用留一被试法作为检验方法、平衡准确率作为评价指标,在PhysioNetRSVP数据集以及清华RSVP数据集下共计14个长度分段中,有12个长度分段达到最优分类结果。结果表明本文提出的多特征低维子空间嵌入方法能够有效提升ERP检测时的稳定性。展开更多
In this paper,a sufficient and necessary condition is obtained to ensure that the spectrum of a class of 2n-order weighted differential operators is discrete.The proof is based on the method of certain weighted Sobole...In this paper,a sufficient and necessary condition is obtained to ensure that the spectrum of a class of 2n-order weighted differential operators is discrete.The proof is based on the method of certain weighted Sobolev spaces to be compactly embedded in weighted L^2(R).展开更多
文摘基于快速序列视觉呈现(rapid serial visual presentation,RSVP)范式的目标图像检索借助于人脑在看到目标图像时产生的事件相关电位(event-related potentials,ERP)来完成复杂目标图像检索。在应用RSVP范式进行复杂目标图像检索时存在跨时段甚至跨被试的问题。对此,本文提出了一种面向跨被试RSVP的多特征低维子空间嵌入的ERP检测方法,首先采用迁移学习方法中的欧式空间对齐对不同被试的数据进行对齐,其次将来自不同空间的特征分别进行有监督降维、重构。最终采用留一被试法作为检验方法、平衡准确率作为评价指标,在PhysioNetRSVP数据集以及清华RSVP数据集下共计14个长度分段中,有12个长度分段达到最优分类结果。结果表明本文提出的多特征低维子空间嵌入方法能够有效提升ERP检测时的稳定性。
基金This research is supported by the National Natural Science Foundation of China(No.10071048).
文摘In this paper,a sufficient and necessary condition is obtained to ensure that the spectrum of a class of 2n-order weighted differential operators is discrete.The proof is based on the method of certain weighted Sobolev spaces to be compactly embedded in weighted L^2(R).
