An Efficient Data Fusion Approach for Event Detection in Heterogeneous Wireless Sensor Networks

This paper concentrates an efficient event detection approach exploiting data fusion technology for the heterogeneous wireless sensor networks. In this type of wireless sensor networks, each sensor is equipped with multiple sensing units. Particularly, in this paper, we study on the data fusion approach based on the type of complementary heterogeneous wireless sensor networks, and the fire disaster detection is utilized as an example of event detection. The proposed event detection model is constructed of data fusion level and information fusion level. In the data fusion level, resource data are collected from the sensors which are both in the sensing field out of the sensing field. In the information fusion level, the event can be detected by computing the data fusion probabilities. For the fire disaster detection process, data collected from temperature sensors and humidity sensors are combined, and then all the measurements are supposed independent on normal random variables. Afterwards, the data fusion process is implemented utilizing genetic algorithm, by which the population is evolved through a predetermined number of consults. Therefore, for each generation of answers, a new set of artificial creatures can be calculated. Furthermore, the answers can be solved by fragments of the most suitable individuals. Finally, experiments are conducted on a series of simulations using the OMNeT++ tool. Compared with other methods, the proposed data fusion based event detection algorithm can effectively find the event through detecting the notify state and alert state, and performs better than other two methods both in the fusion quality and fusion efficiency.