Design and Experimental Study of Fire Warning System for Data Fusion

摘要

A fuzzy neural network based on data fusion technology applied in alarm systems is presented and utilized as a classifier. The performance of this network is compared with that of networks that employ BP and RBF as a classifier. Such comparison is conducted with a fire alarm system. To ensure the accuracy of the fire alarm system, American standard test data are employed. Results show that the proposed fusion model can provide fire warning rapidly and accurately and can effectively reduce the number of false alarms and alarm failure.