The Study of Crop Pest Forecasting Using GP
Miao Li, Tao Sun, Jian Zhang · 2005
In this paper, two models for insect pests forecasting have been developed. A traditional linear regression model and a Genetic Programming (GP) based model are proposed. Two of the key issues in the improvement of GP are: 1) set a logical variable isOld for the attribute of each individual in the population; 2) take into account not only the performance of individuals, but also the depth of individuals. Using statistical and economical measures to estimate the results, we show that the GP model could give more reliable results. Keyword: Genetic Programming, Linear Regression, Pest Forecasting