Analysis of Massive Heterogeneous Temporal-Spatial Data with 3D Self-Organizing Map and Time Vector

TL;DR

This paper introduces a 3D self-organizing map approach that effectively clusters and analyzes massive heterogeneous temporal-spatial data, revealing physical world patterns and behaviors across multiple periods.

Contribution

It presents a novel 3D SOM method that incorporates temporal elements and handles heterogeneous data for improved clustering of temporal-spatial information.

Findings

Enhanced clustering of temporal-spatial data

Ability to track behaviors across multiple periods

Provides valuable insights for business and service applications

Abstract

Self-organizing map(SOM) have been widely applied in clustering, this paper focused on centroids of clusters and what they reveal. When the input vectors consists of time, latitude and longitude, the map can be strongly linked to physical world, providing valuable information. Beyond basic clustering, a novel approach to address the temporal element is developed, enabling 3D SOM to track behaviors in multiple periods concurrently. Combined with adaptations targeting to process heterogeneous data relating to distribution in time and space, the paper offers a fresh scope for business and services based on temporal-spatial pattern.