Abstrato

An improved method on rough set theory and application in prediction of pest attack

Tiecheng Bai, Hongbin Meng, Qingsong Jiang

In order to improve the forecasting accuracy of the occurrence period of insect pests, this paper puts forward a kind of improvedmethod of attribute reduction on rough set theory based on discernibility matrix. And, the forecasting model of insect pests is established by using improved rough set and BP network. The test results show that improved algorithm can reduce the complexity of computing, the number of conditional attribute reduction and the number of condition attributes after reduction than the original algorithm has obvious advantages. the average accuracy of the forecasting model reached to 90%.