Performance Improvement of Machine Learning Model Using Autoencoder to Predict Demolition Waste Generation Rate

Owing to the rapid increase in construction and demolition (C&D) waste, information of waste generation (WG) has been advantageously utilized as a strategy for C&D management. Recently, artificial intelligence (AI) strategically employed obtain accurate WG information. Thus, this study aimed manage (DW) by combining three algorithms: neural network (multilayer perceptron) (ANN-MLP), support vector regression (SVR), random forest (RF) with an autoencoder (AE) develop test hybrid machine learning (ML) models. As result study, AE technology significantly improved performance ANN model. Especially, (25 features)–ANN model was superior that other non-hybrid Compared model, 49%, 27%, 22% terms MAE, RMSE, R2, R, respectively. The using proposed showed useful results improve DWGR ML Therefore, method is considered novel advantageous approach developing Furthermore, it can be used AI models improving various fields.