Information fusion algorithm based on OPD-S

Abstract

The invention relates to an information fusion algorithm based on OPD-S, which is an algorithm for carrying out data fusion on disaster information, belongs to the field of data processing and machine learning, and is characterized by comprising the following steps: (1) determining a trust function of a set; (2) determining a basic probability distribution function under an open recognition framework; (3) determining credibility between evidences; (4) determining the comprehensive credibility of the evidence; (5) determining weighted average evidence; (6) carrying out information fusion on the D-S combination rule. According to the method, the problems that in the traditional disaster information fusion process, due to the fact that the background environment is complex, the noise proportion of collected information is too large, and information fusion is affected are solved, noise interference is effectively filtered out, the information fusion accuracy is greatly improved, meanwhile, the system capacity for processing uncertain information is greatly improved, the fuzzy information proportion is reasonably corrected, and the fusion efficiency is improved. And a method with relatively high fusion accuracy is provided for the field of disaster information fusion.

Description

technical field [0001] The invention relates to the fields of data processing and machine learning, and mainly relates to an algorithm for data fusion of disaster information. Background technique [0002] Disaster information fusion provides a powerful information guarantee for disaster assessment. With the continuous development of sensor technology, the types of sensors suitable for disaster information acquisition are increasing. In the face of various complex disaster scenarios, a single sensor can only understand local information and the indicators are relatively single, and cannot perceive the overall situation. Complex disaster information However, the multi-sensors increase the detection range of disaster environment and enhance the detection performance and reliability of the system. At present, researches on information fusion mainly include methods based on parameter identification, methods based on probability models, and methods based on new information fusio...

AI Technical Summary

Problems solved by technology

The method based on the probability model adopts the pre-set models and rules, so it needs the system to store prior concepts as a basis before making decisions; the algorithm based on parameter identification mainly uses pattern division and parameter estimation to process the initial information. Feature extraction, but it needs to collect a large amount of data in advance for training. The diversity of disaster situations leads to excessive data volume or incomplete data collection when training models

At the same time, due to the complexity of the disaster situation, the environmental information collected by different sensors is easily interfered by complex environmental noise signals, resulting in errors in the information fusion process

Images