By Topic

Using flocks to drive a Geographical Analysis Engine

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
4 Author(s)

This paper describes a new method for the analysis of spatial data that can be used to solve the NP-hard problem of point pattern analysis in geographic, high-dimensional attribute data. The method builds on an established, highly developed and extensively tested methodology (GAM) and extends and combines it with concepts and methodologies found in the field of Artificial Life (Flocking and Agents). The new methodology is smart in that it is able to adapt to the characteristics of various data sources and makes intelligent use of available computational resources when the problem space becomes so large that brute-force techniques would quickly exhaust all available computer power. The system is also, by nature, comprised of multiple, discrete computational units that lend themselves to easy parallelization, thus facilitating the use of parallel, or even distributed, architectures. The inspiration for many of the intelligent aspects of the methodology came from existing research into Artificial Intelligence, Artificial Life and Multi-Agent technologies.