The Study of Decoding Mental State Based Eye Tracks Using SVM
At present, it is a hot topic in applied psychology that interpreting peoples thinking from eye tracks. In this paper, research material is 4*4 sudoku. The Tobii eye tracker records subjects eye tracks when they are solving 4*4 sudouk. And then use feature values, the weighted value of the composite indicators, such as the duration, regression time of each AOI, to train SVM classifier. The experiments of two different classification tasks show that, the classification accuracy b very high, and the ability of generalization is strong. So SVM can be used for the classification of eye tracks and this method can decode different problem-solving strategies according to eye tracks.
SVM classification eye track 4*4 sudoku eye indicators
Jie Xiang Huixia Yan Junjie Chen
College of Computer and Software, Taiyuan University of Technology, Taiyuan, China
国际会议
2009 International Workshop on Information Security and Application(2009 信息安全与应用国际研讨会)
青岛
英文
568-571
2009-11-21（万方平台首次上网日期，不代表论文的发表时间）