A study on artificial neural networks-based fever patient number forecast

The abstract should summarize the contents of the paper and should contain at least 70 and at most 150 words. It should be set in 9-point font size and should be inset 1.0 cm from the right and left margins. There should be two blank (10-point) lines before and after the abstract. This document is in the required format. The number of fever patient increases in winter, this research aimed at advancing BP neural network´s precision in forecast of fever patient number. The method of forecast of fever patient number was based on double-layers BP neural network. The method was used to predict the fever patient number of Shandong Chest Hospital. The hospital can increase doctor number according to the results. The results of the computer simulation showed that the method was applicable, the average relative tolerance was 8.76%. The BP neural network can be used for forecast of fever patient number.