Frequent Items Mining on Data Stream Based on Time Fading Factor

Most of the existing algorithms for mining frequent items on data stream do not emphasis the importance of the recent data items. We present an algorithm using a fading factor to detect the data items with frequency counts exceeding a user-specified threshold. Our algorithm can detect ¿-approximate frequent data items on data stream using O(¿^-1) memory space and the processing time for each data item and a query is O(¿^-1). Experimental results on several artificial datasets and real datasets show our algorithm has higher precision, requires less memory and consumes less computation time than other similar methods.