An efficient algorithm for mining time interval-based patterns in large database

摘要: Most studies on sequential pattern mining are mainly focused time point-based event data. Few research efforts have elaborated patterns from interval-based However, in many real applications, usually persists for an interval of time. Since the relationships among intervals intrinsically complex, large database is really a challenging problem. In this paper, novel approach, named as incision strategy and new representation, called coincidence representation proposed to simplify processing complex relations intervals. Then, efficient algorithm, CTMiner (Coincidence Temporal Miner) developed discover frequent time-interval based patterns. The algorithm also employs two pruning techniques reduce search space effectively. Furthermore, experimental results show that not only scalable but outperforms state-of-the-art algorithms.