Data fusion in different uncertain environment

The concept of knowledge (data) is closely related to the concept of uncertainty. Uncertainty is the capacity to reveal some lack of knowledge, and knowledge is the capacity to reduce uncertainty. One of the ways to reduce the lack of information is to take advantage of the presence of different sources in the environment. Using data aggregation techniques, the results obtained by combining the results from more than one source will be healthier, richer and more sensitive than the information that a single independent source can obtain. In this thesis, three aggregation operators based on Bonferroni mean are proposed for picture fuzzy sets. It has been proven that the results obtained by these operators are also a picture fuzzy number, and they also provide some desirable properties of the aggregation operators. A decision making model for picture fuzzy information has been developed and the applicability of the operators has been demonstrated and compared with the existing operators in literature. There are different approaches to addressing uncertainty, which is a way of demonstrating a lack of knowledge. In this thesis, taking into consideration Zadeh's principle of consistency, "for an event to be probable, it must be possible", interval possibility structures are proposed, where the upper limit is physical possibility and the lower limit is epistemic possibility. A transformation method, in which probability information is obtained from the proposed new uncertainty approach, is introduced. It has been exemplified by an application by proving that the transformation method provides the desired properties in the literature. The feasibility of the methods has been demonstrated by solving a numerical example of real-life problem in which the interval possiblity information in the environment is combined with the proposed aggregation operator, and the interval posibilities are converted into probability information with the proposed transformation method.