Bayesian Approach for Data Fusion in Sensor Networks

We formulate the target tracking based on received signal strength in the sensor networks using Bayesian network representation. Data fusion among the same type of sensors in an active sensor neighborhood is referred to as cross-sensor fusion, conceptualized as "cooperative fusion". This data fusion is embedded in the likelihood function derivation. Fusion of signals collected by multiple types of sensors are referred to as cross-modality fusion. It is "complementary", and represented by the contribution of their likelihood functions to the state update. The tracking algorithm is implemented using particle filter. Very good experimental results are obtained using sensor data