Notice of RetractionA fire rescue plan generation algorithm based on BP neural network

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

The outputs of the BP neural network when used to generate fire rescue plan represent the amounts of various rescue resources which are generally called fire rescue plan. This paper assumes that the total losses the expected(i.e. the best) rescue plan causes is zero, and that the losses a rescue resource causes are mainly fire losses due to its shortage, resource waste losses due to its surplus or zero. The total losses of a rescue plan are the sum of the losses of all rescue resources. Because it is difficult to get the expected rescue plan, the purpose of the fire rescue plan generation algorithm based on BP neural network is to make the total losses of the obtained rescue plans as little as possible. This paper first analyzes the characteristics of the traditional BP neural network and concludes that it can´t guarantee the total losses of a rescue plan as little as possible. Therefore, this paper puts forward an improved BP neural network to generate rescue plan. Experimental results show that the improvement can realize the purpose of decreasing the total losses to the lowest point.