Self-organizing maps and symbolic data

TL;DR

This paper extends self-organizing maps to effectively analyze complex symbolic data types, enabling better knowledge discovery in non-vector data formats.

Contribution

It introduces a novel extension of self-organizing maps specifically designed for symbolic data analysis, addressing limitations of traditional methods.

Findings

Successful application on real-world symbolic data

Enhanced clustering and visualization capabilities

Demonstrated effectiveness over classical methods

Abstract

In data analysis new forms of complex data have to be considered like for example (symbolic data, functional data, web data, trees, SQL query and multimedia data, ...). In this context classical data analysis for knowledge discovery based on calculating the center of gravity can not be used because input are not $\mathbb{R}^p$ vectors. In this paper, we present an application on real world symbolic data using the self-organizing map. To this end, we propose an extension of the self-organizing map that can handle symbolic data.