Emitter recognition algorithm based on interval number and evidence theory

Abstract

The invention discloses an emitter recognition algorithm based on interval number and the evidence theory, and aims at the multi-sensor target recognition problem. According to the algorithm, the interval theory is used for describing uncertainty of parameters of a radiation source, basic probability assignment (BPA) of interval evidence is constructed through weighted similarity, then fusion calculation is performed according to the evidence combination rule, BPA of characteristic parameters of each recognized sensor target and BPA of target characteristic parameters of all recognized sensor targets are obtained sequentially, and finally, target recognition is finished by using self-adaption evidence decision criterion. The emitter recognition algorithm solves the problems that sensor detection uncertain data is difficult to process and subjectivity of BPA forming is high; meanwhile, a recognition method of self-adaption evidence decision is used, a double-threshold structure is based on the BPA, the subjectivity is avoided, and the recognition rate is increased.

Description

Technical field [0001] The invention relates to a data fusion algorithm, in particular to a multi-sensor target recognition algorithm. Background technique [0002] In the field of multi-sensor target recognition, due to the increasing complexity of the electromagnetic environment of the battlefield and the heterogeneity of sensor types, the data parameters detected by sensors are often uncertain and in various forms, which poses new challenges for sensor recognition. There are many reasons for this uncertainty, such as the development of sensor technology, which produces multiple types of radiation parameters, the inconsistent sensor types lead to inconsistent measurement data forms, and the influence of equipment measurement errors and various interference technologies. There is uncertainty in the measurement data. [0003] The current research methods to solve this uncertainty are not limited to scalar data, but use interval data that can describe the uncertainty. Interval the...

AI Technical Summary

Problems solved by technology

The interval number describing the uncertainty of the parameter is taken as a piece of evidence in the evidence theory, the mutual support degree between the evidences is obtained by normalizing the interval similarity measure as the evidence weight, and the weighted interval similarity forms the basic probability assignment of the evidence theory (Basic Probability Assignment) BPA solves the problem of difficult subjective assignment in most cases of current BPA, and then combines BPA with evidence theory combination rules, and proposes an adaptive double-threshold evidence judgment criterion based on BPA changes to judge the degree of evidence trust, and obtain judgment identification As a result, recognition of interval type parameter sensors is achieved

Images