A New Multiple-Kernel-Learning Weighting Method for Localizing Human Brain Magnetic Activity
A New Multiple-Kernel-Learning Weighting Method for Localizing Human Brain Magnetic Activity
复制标题
一种新的多核学习加权方法来定位人脑磁活动
DOI：
10.1109/icassp.2012.6287995
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
and M. Kotani
中科院分区：
文献类型：
--
作者：
T. Takiguchi;T. Imada;R. Takashima;Y. Ariki;J.-F. L. Lin;P.K. Kuhl;M. Kawakatsu;and M. Kotani
研究表明，基于机器学习的模式分类方法是分析脑磁图(MEG)获得的人脑活动数据的有力工具。我们提出了一种新的加权方法，使用多核学习(MKL)算法来定位大脑区域，有助于准确地识别元音。我们的MKL同时估计每个脑磁图传感器的分类边界和权重；从每对传感器获得的脑磁图幅度是特征向量的一个元素。估计的权重表明相应的传感器对分类脑磁图反应模式有多大帮助。实验结果表明，在100~200ms的潜伏期内，大质量脑磁图传感器主要分布在大脑的语言区域，分类准确率高达73.0%。
This paper shows that pattern classification based on machine learning is a powerful tool to analyze human brain activity data obtained by magnetoencephalography (MEG). We propose a new weighting method using a multiple kernel learning (MKL) algorithm to localize the brain area contributing to the accurate vowel discrimination. Our MKL simultaneously estimates both the classification boundary and the weight of each MEG sensor; MEG amplitude obtained from each pair of sensors is an element of the feature vector. The estimated weight indicates how the corresponding sensor is useful for classifying the MEG response patterns. Our results show both the large-weight MEG sensors mainly in a language area of the brain and the high classification accuracy (73.0%) in the 100 ~ 200 ms latency range.