一种基于fMRI数据的脑功能网络构建方法*

人脑可以用复杂网络方法进行定量分析。为了研究基于功能磁共振成像数据来构建脑功能网络，首先，用标准脑模板将全脑分割成90个功能区域，每个区域定义为一个网络节点；然后，用脑区的平均时间序列来计算相关系数, 网络节点间是否有边相连取决于其相关水平；最后，生成一系列不同网络密度的无向无权图，用来分析网络统计特性。结果表明，所构建的网络具有小世界拓扑结构。该脑功能网络的构建方法可以应用在某些认知障碍的临床诊断上。

Method for constructing brain functional networks based on fMRI data

This paper proposed a new knowledge discovery and representation model for fishery, which took three steps. Firstly, it extracted static knowledge from database by SVM (support vector machine) and fuzzy classifier. Secondly, it used extension data mining method to transfer static knowledge into dynamic knowledge. Thirdly, it established an ontology knowledge base by utilizing a mapping mechanism between the dynamic knowledge and ontology. Using the proposed model building procedure, implemented a prototype system for fishery forecasting. Experimental results show that the proposed method is effective and efficient.