Spatio-temporal pattern analysis of single-trial EEG signals recorded during visual object recognition
Spatio-temporal pattern analysis of single-trial EEG signals recorded during visual object recognition
复制标题
DOI：
10.1007/s11432-011-4507-1
复制
发表时间：
2011-12
期刊：
影响因子：
--
通讯作者：
Changming Wang;Xiaoping P. Hu;L. Yao;Shi Xiong;Jia-cai Zhang
中科院分区：
文献类型：
--
作者：
Changming Wang;Xiaoping P. Hu;L. Yao;Shi Xiong;Jia-cai Zhang
物体辨别是人脑的一项基本认知功能。在这项研究中，我们利用单次试验脑电（EEG）的分析方法来分析的时空激活模式的视觉对象在人脑中的加工，并试图将其应用于区分不同的视觉对象。分别从头皮脑电和重建的皮层源中提取空间模式，同时实验被试感知4种不同类别的视觉对象（人脸、建筑物、猫和汽车）。通过对单次脑电提取的模式进行分类，计算机可以对呈现的视觉对象进行区分，分类精度可以为评价不同视觉对象相关脑激活的空间差异提供定量指标。我们的研究结果表明，头皮和源水平的空间模式导致更高的分类精度比机会率。我们还研究了使用不同事件相关电位（ERP）组件的时间不重叠的时间间隔的分类结果。分类准确率的时间变化可以反映脑电反应中判别信息的时间分布。本模式提取和分类方法可以构成一个计算模型的单次试验EEG数据分析的时空激活模式的研究对象识别。这些脑电的时空模式可能有助于识别可区分的空间区域和时间阶段，以提高目标识别的准确性和效率。此外，研究和利用人类对物体识别的认知机制可以提高计算机对视觉信息的处理效率。
Object discrimination is a fundamental cognitive function for human brains. In this study, we utilized an analysis approach for single-trial electroencephalography (EEG) to analyze the spatio-temporal activation patterns of visual objects processing in human brains, and attempted to apply it to discriminate different visual objects. The spatial patterns were respectively extracted from scalp EEG and the reconstructed cortical sources, while the experiment participants were perceiving 4 different categories of visual objects (faces, buildings, cats and cars). By classifying the patterns extracted from single-trial EEG, the presented visual objects could be discriminated by a computer, and the classification accuracies may provide a quantitative index to evaluate the spatial differences of the brain activations related to different visual objects. Our results demonstrated that the spatial patterns on both the scalp and the sources levels resulted in higher classification accuracies than chance rate. We also examined the classification results using temporally non-overlapping time intervals of different event-related potential (ERP) components. The temporal changes of classification accuracies may reflect the temporal distribution of the discriminative information in the EEG responses. The present pattern extraction and classification methods may compose a computational model for single-trial EEG data analysis in investigations of the spatio-temporal activation patterns for object recognition. These spatio-temporal patterns in EEG may be useful to identifying the discriminative spatial areas and time stages to improve the accuracies and efficiencies of object discrimination. In addition, investigating and utilizing humans’ cognitive mechanisms of object recognition may improve computers’ processing efficiency of visual information.