Kusum Sharma, Asha Ambhaikar
Abstract: An important purpose of sequence analysis is to find the distinguishing characteristics of sequence classes. Given in one set of sequence pattern we introduce the problem of gapped subsequences and purpose is to find efficient patterns and provide a classification for these patterns. Since every pattern has a class label so we find these labels. Sequence is an ordered list of events, the pattern we would like to mine is called repeated gapped subsequences which is a subsequence (possibly occurred with some gaps within two successive sequences). To find the patterns we introduce the concept of frequent support to measure how frequently a pattern repeats in a sequence. As compare to other sequence pattern mining problems repeated supports captures not only repetition of patterns in other sequences but also repetition within sequence. Here we present a classification methodology for sequence classification based on these gapped frequent patterns.
Keywords: Gapped subsequences, frequent support, sequence classification, sequential pattern mining