A predictor from numerical data based on fuzzy sets and rough sets
Chih-Ching Hsiao, Yi-Wei Ku · 2010
In this paper, we propose a fuzzy predictor which fuzzy rules are generated directly from numerical data pairs. Unfortunately, the fuzzy rules may be increase growing to extra numbers, especially the data pairs contain noise or outlier. The Fuzzy-rough feature selection will be introduced for those fuzzy rules reduction. To achieve good performance for this fuzzy predictor, the parameters of each fuzzy rule will be adjusted by fine tuning.