Growing Self-Organizing Map using Cross Insert for Mixed-Type Data

Wei-Shen Tai, Chung-Chian Hsu, and Jong-Chen Chen


data visualization, Self-Organizing Map (SOM), mixed-type data, dynamic structure, distance hierarchy


Self-Organizing Map (SOM) possesses effective capability for visualizing high-dimensional data. As a result, SOM has numerous applications in visualized clustering. Many growing SOMs have been proposed to overcome the constraint of having a fixed size in conventional SOMs. However, most growing SOMs lack a robust solution to process mixed-type data which may include numeric, ordinal and categorical values in a dataset. Moreover, the growing scheme has an impact on the quality of resultant maps. In this paper, we propose a Growing Mixed-type SOM (GMixSOM), combining a value representation mechanism distance hierarchy with a novel growing scheme to tackle the problem of mixed-type data and improve the quality of the projection map. Experimental results on synthetic and real-world datasets demonstrate that the proposed mechanism is feasible and the growing scheme results in maps better than the existing method.

Important Links:

Go Back