Institute of Information Science, Academia Sinica

The present era is an era of biological sciences which has been generating a huge amount of data. Those data usually requires specialized modeling and analysis tools. In addition, for such biological data always has many features which may lead to enhanced data acquisition time and cost, more design time, more decision making time, and other increased expenditures in cost, time and effort. Hence reducing the dimensionality, if possible, is always desirable through feature selection. In this talk, I shall present an integrated mechanism for simultaneous construction of a fuzzy rule based system and selection of useful features. This proposed mechanism has two interesting concepts. First, the concept of feature modulators is introduced to help in easy selection of useful features and dismissal of indifferent and derogatory features. For each feature in such a system, an associated feature modulator (or a gate function) is equipped to act like a gate to prevent bad features from influencing the output results. Second, by integrating a penalty concept into our feature selection process, whereby a penalty is imposed on features which have high correlation to others, the good features are able to be further winnowed down to the smallest possible select group of the most highly effective features as the input. This mechanism is adapted to classification systems and regression systems. The effectiveness of these approaches is demonstrated using a set of applications.