Online Mining of Maximal Frequent Itemsequences from Data Streams

摘要: Mining data streams often requires real-time extraction of interesting patterns from dynamic and continuously growing data. This requirement has imposed challenges on discovering outputting current useful in an instant way, commonly referred to as online streaming mining. In this paper, we present INSTANT, a novel algorithm that explores maximal frequent itemsequences fashion. We first provide operators the lattice itemsequential sets, then apply them design INSTANT. comparison with most popular methods such close-itemset based mining algorithms, INSTANT solid theoretical foundations ensure it employs more compact in-memory structures than closed itemsequences. Experimental results show our method can achieve better previous related terms both time space efficiency.