SUMMARY
The prediction of time series has been widely applied to many fields suchas enrollments, stocks, weather and so on. In this paper, a new prediction methodbased on fuzzy cognitive map with information granules is proposed, in which fuzzy cmeansclustering algorithm is used to automatically abstract information granules andtransform the original time series into granular time series, and subsequently fuzzycognitive map is used to describe these granular time series and perform prediction.two benchmark time series are used to validate feasibility and effectiveness of proposedmethod. The experimental results show that the proposed prediction method canreach better prediction accuracy. Additionally, the proposed method is also able toprecess the modeling and prediction of large-scale time series.