Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (32): 193-196.DOI: 10.3778/j.issn.1002-8331.2009.32.061

• 工程与应用 • Previous Articles     Next Articles

Time complexity optimization of clustering for fMRI feature reconstruction

LIN Wei1,2,HE Hua-can2,AI Li-rong2,LI Mei2   

  1. 1.College of Computer and Information Technology,Henan Normal University,Xinxiang,Henan 453007,China
    2.School of Computer Science and Engineering,Northwestern Polytechnical University,Xi’an 710072,China
  • Received:2009-05-25 Revised:2009-06-25 Online:2009-11-11 Published:2009-11-11
  • Contact: LIN Wei

脑fMRI特征重建的分层快速聚类方法

林 卫1,2,何华灿2,艾丽蓉2,李 梅2   

  1. 1.河南师范大学 计算机与信息技术学院,河南 新乡 453007
    2.西北工业大学 计算机学院,西安 710072
  • 通讯作者: 林 卫

Abstract: To solve the problem of reconstructing features of functional Region of Interest(fROI) from extracted voxels,Hierarchical Fast Clustering method(HFC) is proposed.Compared with the existing K-means clustering methods,this method saves more than 62% running time on condition of ensuring regression ability.

Key words: functional Magnetic Resonance Imaging(fMRI), Region of Interest(ROI), hierarchical clustering, K-means, feature reconstruction

摘要: 在对大脑fMRI感兴趣区域的分析中,利用特征选择所得到的筛选属性进行特征重建问题上,提出了分层快速聚类的分析方法,同已有K-均值聚类方法相比,在聚类有效性得到提高的前提下,总体降低了聚类的时间代价,并为后续的回归分析处理提供了精确保证。

关键词: 功能核磁共振成像, 感兴趣区域, 层次聚类, K-均值聚类, 特征重建

CLC Number: