摘要：Term weight a technique in text mining and entropy from Shannon’s information theory are both used to quantify information. In this paper they are used to develop an identity attribute metrics model. Using term weight and entropy metrics values, Sugeno-style fuzzy inference system is envisaged in the implementation of information fusion in a multimode authentication system. This is in an effort to provide a solution to the cases of identity theft and fraud. Three corpora are used to mine the identity attributes and generate the statistical information required to compose a metric model from a set of questionnaires and the application forms for the various services. Triangular and sigmoidally shaped membership functions are used in the fuzzification of the three inputs categorised as biometrics, pseudo metrics and device metrics.
关键词：identity attributes; metrics; information fusion; fuzzy logic; authentication; term weight; entropy
