| Popis: |
The article is devoted to the use of neural networks to predict changes in the structure of waste depending on the level of well-being of the population. To predict the dependence of gross national income on municipal solid waste, a neural network was built based on the MultiLayer Perceptron (MLP), which predicts the time series. MLP is based on sigmoidal neurons. It was found that, based on a fuzzy model, in countries with a middle high-income population, the share of organic waste in MSW decreases, while the share of recyclable fractions increases. Based on statistical data, a fuzzy model was compiled for the classification of municipal solid waste depending on the level of well-being of the population and a methodology for teaching the fuzzy model algorithm was developed. |
