Research on Fuzzy Temporal Event Association Mining Model and Algorithm

As traditional models and algorithms are less effective in dealing with complex irregular temporal data streams, this work proposed a fuzzy association model as well an algorithm. The core idea is to granulate fuzzify information from both the attribute state dimension dimension. After restructuring extracting features out of information, event rule mining algorithm was constructed. can fully extract at each granularity level while preserving original reducing amount computation. Furthermore, it capable efficiently possible rules underlying different streams. In experiments, by comparing analyzing stock trading granularities, identify events disorder trading. This not only valuable identifying anomalies, but also provides new theoretical tool for data.