Multi-Sensor Data Fusion Method Based On Belief Degree And Neural Network

Focusing on the uncertainty of data in information gathering system, a multi-sensor data fusion method based on belief degree and neural network is proposed. A fuzzy-index belief degree function is defined to quantify the belief degree between data measured by two sensors, which are combined with the measured data as the input of the neural network.. Through the network training, the data fusion of multi-sensor is realized. Applying the proposed method to the data fusion in soil moisture content, it is demonstrated that this method, which not only can reach higher fusion precision than traditional methods, but also has excellent restraint ability against disturbance.