Data fusion is reliable in achieving the computing and service demands of the applications in diverse real-time implications. In particular, security-based trust models rely on multi-feature data from different sources to improve the consistency of the solutions. The service providing solutions are relied on using the optimal decisions by exploiting the data fusion trust. By considering the significance of the security requirement in smart city applications connected with the Internet of Things, this manuscript introduces a rational attribute-based data fusion trust model. The proposed trust model relies on different timely attributes for identifying the reputation of the available service. This reputation is computed as the accumulative factor of trust observed at different times and details. The attributes and the uncertain characteristics of the service provider in the successive sharing instances are recurrently analyzed using deep machine learning to fuse uncertain-less data. This data fusion method reduces the uncertainties in estimating the precise trust during different application responses and service dissemination. The performance of the proposed method is verified using the metrics false positive, uncertainty, data loss, computing time, and service reliability.
All Science Journal Classification (ASJC) codes
- Theoretical Computer Science
- Geometry and Topology