An Efficient Approach for Mining Frequent Patterns over Uncertain Data Streams

Abstract

Knowledge discovery in big data is one of most interesting topics in state-of-the-art research, and frequent patterns mining is a major task. With the rapid growth of modern technology, high volumes of data—which are of different veracities (i.e., may be precise or uncertain)—are flowing at a high velocity all over the world. Properties of data temporally changes with changes in the people's interests, which make the data dynamic. Due to the uncertainty and dynamic properties of data, finding appropriate and efficient approach to ensure the efficient usage of available resources has become a great challenge. In this paper, we design a new memory-efficient data structure, called Uncertain Stream (US)-tree, which stores recent meta-data. We also develop a probabilistic, sliding window based, efficient algorithm—called Uncertain Stream Frequent Pattern (USFP)-growth—for mining frequent patterns from uncertain data streams. Our comprehensive performance evaluation shows that USFP-growth is correct and efficient when compared with recent related approaches.