Neural Networks for Classification and Regression Applied to Public Lighting Project

Abstract

This paper explores using neural networks to evaluate public lighting projects according to Brazilian Standard 5101/2018. Employing Multilayer Perceptron (MLP) models, the study performs regression to predict illuminance, uniformity, and classification to assess compliance with the standard. The regression model achieved a mean squared error (MSE) of 0.002. The classification model attained an accuracy of 97.26%, with a precision of 97.0%, a recall of 96.5%, and an F1-score of 96.7%. These results underscore the effectiveness of MLP networks in improving compliance evaluation and optimizing public lighting projects.