Study on prediction model of grain post-harvest loss

With the arrival of the information age, a great deal of data has been produced in a series of process of grain post-harvest. The rational use of these data allows us to obtain more intelligent, in-depth and valuable information. In this paper, we set up a variety of prediction models for the consumption of grain post-harvest loss, and select the appropriate classifier through comparison. On this basis, the dimension reduction is processed and the confusion matrix is used as the evaluation index to evaluate the prediction effect. Make correlation analysis of the data, obtained the main influencing factors of post-harvest consumption loss link. Finally, visualize the results of the process. (C) 2017 The Authors. Published by Elsevier B.V.