Fuzzy relation analysis in fuzzy time series model

Fuzzy relation is a crucial connector in presenting fuzzy time series model. However, how to obtain a fuzzy relation matrix to represent a time-invariant relation is still a question. Based on the concept of fuzziness in Information Theory, the concept of entropy is applied to measure the degrees of fuzziness when a time-invariant relation matrix is derived. Finally, an example is illustrated to show that the proposed method could obtain more accurate and robust results in forecasting.