Individual Compositional Cluster Analysis
Mika Sato‐Ilic · Procedia Computer Science · 2016
This paper proposes an Individual Compositional Cluster Analysis with the aids of conventional individual difference scaling (INDSCAL) model. Our target data is 3-way data which consists of objects, variables, and subjects and we treat the case when the number of objects is relatively large. The purpose of this method is to show the difference of individual subjects visually in a lower dimensional space including the feature of objects with respect to variables as clusters. Numerical examples using sensor data obtained from several subjects show a better performance.