Due to advances in technology, high volumes of valuable data can be produced at high velocity in many real-life applications. Hence, efficient data mining techniques for discovering implicit, previously unknown, and potentially useful frequent itemsets from data streams are in demand. Many existing stream mining algorithms capture important stream data and assume that the captured data can fit into main memory. However, problems arise when the available memory is so limited that such an assumption does not hold. In this paper, we present a data structure to capture important data from the streams onto the disk. In addition, we present two algorithms-which use this data structure-to mine frequent itemsets from these dense (or sparse) data streams.
