Chance Discovery with Data Crystallization: A Basic Research for Discovering Unobservable Events

摘要

It is only the observable part of the real world that can be presented in data. For such a scattered, i.e., an incomplete and ill-structured data, data crystallizing aims at presenting the hidden structure by inserting dummy items corresponding to unobservable, i.e., hidden events, to the given data on past events. The existence of hidden events and their position in the environment will be visualized as a result of data crystallizing. This basic method is expected to be applicable for various real world domains to which chance-discovery methods have been applied. This project aims at developing the process of data crystallizing, with a new tool extending KeyGraph, based on the process of chance discovery. In the research, experiments will be made using artificial data obtained from simulating the target of intelligence analysis, i.e., organized crimes.