Waste output prediction method based on multivariate information and radial basis function network

Abstract

The invention discloses a waste output prediction method based on multivariate information and a radial basis function network, which comprises the following steps of 1) drawing a waste output influence factor, 2) determining a waste output influence factor based on multiple variables, 3) initially predicting the waste output based on the radial basis function network, and 4) reversely correcting waste output prediction errors.

Description

Forecasting Method of Garbage Production Based on Multivariate Information and Radial Basis Function Network technical field The invention relates to a method for predicting garbage generation. Background technique In recent years, my country's economy has developed rapidly, and people's living consumption levels have also greatly improved. However, the amount of daily garbage in people's daily life has gradually increased with the improvement of people's living consumption levels, and even the phenomenon of "garbage siege" has appeared. The effective prediction of the amount of garbage generated can help the sanitation department to make reasonable sanitation decisions, so the prediction of the amount of garbage generated has practical significance. The determination of the influencing factors of waste generation will directly affect the prediction results of waste generation, so the determination of the influencing factors is very critical. Variable selection can often...

AI Technical Summary

Problems solved by technology

Common forecasting methods include multiple linear regression analysis, gray system model, combined forecasting method, etc. These methods do not consider the impact of changes in relevant factors on the forecasting model, resulting in low forecasting accuracy

Multiple linear regression analysis methods are prone to multicollinearity leading to prediction distortion

Images