Self-Organizing Time Map: An Abstraction of Temporal Multivariate Patterns
This provides a method for exploratory temporal structure analysis in domains like social indicators, but it is incremental as it adapts an existing technique.
The paper tackles the problem of analyzing temporal multivariate patterns by adapting Kohonen's Self-Organizing Map to create the Self-Organizing Time Map (SOTM), which preserves both time and data topology to discover temporal structural changes, and demonstrates its application on artificial data and real-world poverty indicators.
This paper adopts and adapts Kohonen's standard Self-Organizing Map (SOM) for exploratory temporal structure analysis. The Self-Organizing Time Map (SOTM) implements SOM-type learning to one-dimensional arrays for individual time units, preserves the orientation with short-term memory and arranges the arrays in an ascending order of time. The two-dimensional representation of the SOTM attempts thus twofold topology preservation, where the horizontal direction preserves time topology and the vertical direction data topology. This enables discovering the occurrence and exploring the properties of temporal structural changes in data. For representing qualities and properties of SOTMs, we adapt measures and visualizations from the standard SOM paradigm, as well as introduce a measure of temporal structural changes. The functioning of the SOTM, and its visualizations and quality and property measures, are illustrated on artificial toy data. The usefulness of the SOTM in a real-world setting is shown on poverty, welfare and development indicators.