The emergence of remote sensing, scientific simulation and other survey technologies has dramatically enhanced our capabilities to collect temporal data. However, the explosive growth in data makes the management, analysis, and use of data both difficult and expensive. Methods that characterize interesting or unusual patterns from the volumes of temporal data are needed (Roddick & Spiliopoulou, 2002; Han & Kamber, 2005). The association rule mining methods described in this chapter provide the ability to find periodic occurrences of inter-sequential factors of interest, from groups of long, non-transactional temporal event sequences. Association rule mining is well-known to work well for problems related to the recognition of frequent patterns of data (Han & Kamber, 2005). Rules are relatively easy for humans to interpret and have a long history of use in artificial intelligence for representing knowledge learned from data.
Mining association rules is typically decomposed into three sub-problems: 1) prepare the data for analysis, 2) find frequent patterns and 3) generate association rules from the sets representing those frequent patterns (Agrawal et al., 1993).