Symbolic Data Analysis With the K-Means Algorithm for User Profiling
暂无分享,去创建一个
We propose to simplify human-machine interaction by automating device settings that are normally made manually. We present here a classification scheme of user behaviours based on an adaptation of the K-means algorithm to symbolic data representing user behaviours. This classification enables a system to derive prototypical behaviours and to control device settings automatically.
[1] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.
[2] E. Diday. An Introduction to symbolic data analysis , 1993 .
[3] Anil K. Jain,et al. Algorithms for Clustering Data , 1988 .
[4] André Hardy,et al. An examination of procedures for determining the number of clusters in a data set , 1994 .