The Research On Granular Computing For Incomplete Multi-source Information Fusion

With the continuous development and progress of human society,the way people get data is becoming more and more diverse.When we are faced with a variety of forms,huge number,complex relationships,requiring timely processing of data,it is one of the hot research topics currently that how to get useful information and delete the redundant and how to refine the information obtained and get more accurate information.In many fields of electronic technology and network engineering,it is difficult to obtain accurate and complete information and collected data usually contain noise,fuzzy and incomplete.Then,when the collected information is fuzzy or incomplete,how to integrate the incomplete information sources has become the focus of multi-sensor information fusion technology.With the development of the scientific research,it is very important to deal with all kinds of data in different environments.Based on this background,several new rough fuzzy set models are constructed by using logical operators in the ordered information system under different environments,and the method of how to fuse multiple fuzzy or incomplete information sources is studied.The main innovations in this thesis are listed in the following.1.In ordered information systems and intuitionistic fuzzy ordered information systems,three new type of rough fuzzy set model are constructed by combining the variable precision and graded rough set model with logic operator,and the effectiveness of the proposed model is verified by a practical case.2.We studied how to carry out the information fusion method,when multiple sources are incomplete,that is,when each information system is an incomplete information system,and the corresponding algorithm is designed according to the proposed fusion method.Then,a series of experiments is designed based on the UCI data set,and the fusion method proposed in this paper is compared with the traditional fusion method,the results show that the fusion method proposed in this paper has obvious advantages in accuracy.3.The fusion method of incomplete information system is applied to fuzzy information system,a new similarity measure is defined and a similarity binary relation is constructed based on the measure.Then,the new fusion model is established according to the new binary relation.