A study on intention recognition based on analysis of human brain activity

在这项研究中，我们专注于人类语言交流的基础上分析的人脑活动数据获得的脑磁图（MEG）。在2011年，我们提出了一种新的加权方法，使用多核学习（MKL）算法来定位有助于准确元音辨别的大脑区域。我们的MKL同时估计每个MEG传感器的分类边界和权重。估计的权重指示对应的传感器如何用于分类MEG响应模式。但是我们提出的使用多核学习的方法计算成本很高。在2012年，我们提出了一种新的和快速的加权方法，使用AdaBoost算法来找到有助于准确区分元音的传感器区域。然后，在2013年，我们提出了一种用于人类活动数据特征提取的随机投影。

In this study, we focused on human verbal communication based on analysis of human brain activity data obtained by magnetoencephalography (MEG). In 2011, we proposed 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. The estimated weight indicates how the corresponding sensor is useful for classifying the MEG response patterns. But our proposed method using multiple kernel learning had a high computational cost. In 2012, we proposed a novel and fast weighting method using an AdaBoost algorithm to find the sensor area contributing to the accurate discrimination of vowels. Then, in 2013, we proposed a random projection for feature extraction of human activity data.