Sensor data credibility evaluation method based on multi-source heterogeneous information fusion

Abstract

The invention belongs to the technical field of information fusion, and provides a sensor data credibility evaluation method based on multi-source heterogeneous information fusion. The objective of the invention is to overcome the problem that the actual situation in the current working environment cannot be reflected because the data of the actual situation cannot be evaluated correctly and accurately when sensors are interfered manually by the existing evidence theory, Bayesian estimation and other sensor data credibility evaluation methods. According to the method, firstly, new data credibility definitions are provided, data obtained through multiple algorithms are fused to predict the data of the to-be-evaluated sensor nodes, the unicity of the algorithms is avoided, and a monitoring system is more stable and reliable; secondly, by utilizing the space-time relationship of the sensor source, the credibility index of the sensor is increased, and the real working environment can be more objectively reflected; and finally, in combination with a multi-source heterogeneous information fusion algorithm, when the sensor is artificially interfered or shielded, the sensor data can also be effectively evaluated.

Description

technical field [0001] The invention belongs to the technical field of information fusion, in particular to a sensor data credibility evaluation method based on multi-source heterogeneous information fusion. Background technique [0002] Wireless sensor networks have spread everywhere, and the reliability of sensor node data is crucial for data processing, especially for sensor network data for security monitoring. In terms of industrial safety, wireless sensor networks are used to monitor the safety status of dangerous working environments such as coal mines, oil drilling, and nuclear power plants to ensure the safety of workers. However, due to the interference of many factors, such as sensor failure, sensor aging, insufficient power supply, etc., the data collected by the sensor may not be true and credible sometimes, resulting in false alarms and missed alarms in the monitoring system, which greatly reduces the monitoring system. performance, if misinformation cannot be...

AI Technical Summary

Problems solved by technology

However, due to the interference of many factors, such as sensor failure, sensor aging, insufficient power supply, etc., the data collected by the sensor may not be true and credible sometimes, resulting in false alarms and missing alarms in the monitoring system, which greatly reduces the monitoring system. performance, if the wrong information cannot be evaluated and screened, it may even have disastrous consequences, so it is of great significance to evaluate the credibility of sensor data

[0003] Commonly used data credibility evaluation techniques include evidence theory, Bayesian estimation, etc. Evidence theory methods have the problem of explosive growth in the amount of calculations when dealing with large amounts of data; Bayesian estimation has a priori information that is difficult to obtain, and real-time Poor performance, less practical application

More importantly, none of the above methods takes into account the spatio-temporal relationship between data sources, so when artificial interference is performed on the sensor, these methods cannot correctly and accurately evaluate the data of the actual real situation, which in turn cannot reflect the current situation. Reality in the work environment

Images