Time-Interval Clustering in Sequence Pattern Recognition as Tool for Behavior Modeling

Time-interval sequential patterns provide information not only on frequently occurring items and the order in which they happen but also reveal the temporal dimension between successive items. Although time-interval data have been dealt with in the past - as single or multiple, regular or irregular, and/or with definite ranges, what we are proposing here is a data mining algorithm that allows multiple time intervals in a sequence that are irregular and more flexible by employing a clustering technique integrated in an Apriori-based algorithm. Clustering allows non-integral time values to be categorized effectively and efficiently and leads to the characterizations of time interval data. In light of our research on a smart space that aims to provide empathic support to its occupant, we aim to use our algorithm as tool when building various predictive models of human behavior. Behavior modeling is a persisting and compelling issue in the design of intelligent environments in order to anticipate user needs and provide timely system responses. Insensitive or untimely system responses solicit unfavorable user reception. As proof of concept, we used our algorithm to infer the behavior patterns of individuals in terms of their habitual paths and walk time, i.e., spots in the space that an individual would likely take coupled with walk duration intervals. Our smart space may then use these two parameters to create models of effective timely interactive support provisions.