Structural Transformation Based on Soft Information

With the deeper and deeper influences of soft information on multiple sensor information fusion, an important problem is how to build an effective information structural transformation model and provide more fused structured soft information for computers and sensors. For the structural transformation of the soft information, i.e., text representation, this paper firstly studies the TF IDF weight based on the vector space model in the text classification technology. And then, aiming at the shortcoming of the structural transformation, both event global weight and information gain are introduced to supplement the text theme information and the item distribution information such that the structural description of soft information will be improved and implemented. Finally, the simulation results show the feasibility and effectiveness of structural transformation of soft information by the proposed method in this work.