Mining fuzzy frequent trends from time series

Time-series analysis has always been an important and interesting research field due to its frequent appearance in different applications. In the past, many mining approaches were proposed to find useful patterns from time-series data. Time-series data, however, are usually quantitative values and need domain knowledge to predefine crisp intervals of categories for a mining process to proceed. In this paper, we thus propose an algorithm based on Udechukwu et al. approach to mine fuzzy frequent trends from time series. It uses fuzzy concepts to deal with the value-boundary problem and is less domain-dependent as Udechukwu’s approach was. The proposed approach first transform data values into angles, and then uses a sliding window to generate continues subsequences from angular series. The apriori-like fuzzy mining algorithm is then used to generate fuzzy frequent trends. Appropriate post-processing is also performed to remove redundant patterns. Finally, experiments are also made for different parameter settings, with experimental results showing that the proposed algorithm can actually work.