Towards progressive querying and mining movement data

In this work we propose a research foundation for uniformly querying both movement data and patterns extracted from movement data. Our proposal is based on a formal framework, called 2W Model, that defines the knowledge discovery execution process as a progressive combination of mining and querying operators. Furthermore, a query language is proposed that extends SQL in two respects, namely a pattern definition operator and the capability to uniformly manipulate both raw data and unveiled patterns. The resulting Moving-Object data mining query language is implemented in DAEDALUS, an innovative computational engine serving as a query execution layer on top of the Hermes Moving Object Database. A qualitative evaluation of the whole system by means of a concrete case study is presented.