序列樣式的挖掘在許多應用扮演十分重要的角色，包括生物電腦研究、顧客行為分析及系統效能研究等等，但是一般的序列樣式挖掘很少考慮到時間間隔，一直到Chen, Jiang, and Ko 提出時間間隔樣式挖掘之後，我們發現只挖掘出兩兩項目之間的時間間隔是不夠的，必須找出所有項目之間的時間間隔的樣式才能幫助決策者得到詳細請足夠的支援，於是我們提出兩項演算法：MI-Apriori以及MI-PrefixSpan分別改自Apriori以及PrefixSpan演算法，其中MI-PrefixSpan的效率優於MI-Apriori，而scalablity的表現則相反。 Sequential pattern mining is of great importance in many applications including computational biology study, consumer behavior analysis, system performance analysis, etc. Recently, an extension of sequential patterns, called time-interval sequential patterns, is proposed by Chen, Jiang, and Ko, which not only reveals the order of items but also the time intervals between successive items. For example: having bought a laser printer, a customer returns to buy a scanner in three months and then a CD burner in six months. Although time-interval sequential patterns are useful in predicting when the customer would take the next step, it can not determine when the next k steps will be taken. Hence, we present two efficient algorithms, MI-Apriori and MI-PrefixSpan to solve this problem. The experimental results show that the MI-PrefixSpan algorithm is faster than the MI-Apriori algorithm but the MI-Apriori algorithm has a better scalability.
