Abstract

Fuzzy temporal association rules can take into account the temporal requirements of the user which tend to be ill-defined or uncertain. However, fuzzy temporal association rules still have some shortcomings: firstly, neglecting the effect of all kinds of potential negative examples that affect its expression capability; secondly, probably showing no practical significance or even misleading even if it possesses high confidence and support. In this paper, the relativity-based interest measure value is introduced based on the fuzzy calendar-based temporal association rules, and a fuzzy calendar-based temporal association rules mining algorithm with interest measure is also proposed. Finally, this algorithm was applied to the prediction of telemetry data from the power system of small satellite. It was proved that this algorithm has a good effect and feasibility.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call