An efficient fuzzy time series forecasting model based on quantifying semantics of words

摘要: Fuzzy time series forecasting model was first introduced by Song and Chissom, in 1993. Then, Chen examined this model, 1996, applying fuzzy rules the form A i → j , where are sets associated with linguistic labels representing their corresponding values a series. Since then, many methods have been proposed to improve accuracy of results or decrease processing times. In study, we propose another approach dealing directly human words own inherent semantics. That is, assume that above X which expert describing values. Therefore, should deal so-called using semantics quantitative based on hedge algebras formalism. comparative experiment is made show usefulness model.