Data fusion based on fuzzy measures

Choquet integral based on fuzzy measure is a very popular data fusion approach.A major problem in applying the Cho- quet integral is how to determine a large number of fuzzy measures as the number of attributes increases.Theλ-fuzzy measure proposed by Sngeno is a powerful method to resolve this problem.However,the modeling ability of theλ-fuzzy measure is too limited to satisfy actual requirements.In this paper,an extendedλ-fuzzy measure is proposed using Shapley value index,and the limitation of theλ-fuzzy measure is significantly overcome under little additional computational loads.The extended fuzzy measure has stronger modeling power than theλ- fuzzy measure,straightforwardly representing interaction among attributes.We apply the extended fuzzy measure to an artificial data set and a real dataset in an iron-steel plant.The results verify the usefulness of the extended fuzzy measure compared with other main existing methods.