Vector Time Series‐Based Radial Basis Function Neural Network Modeling of Air Quality Inside a Public Transportation Bus Using Available Software

Abstract

This software review article presents a step‐by‐step approach to the development of hybrid indoor air quality (IAQ) models by integrating the use of vector time series and radial basis function neural network (RBFNN) modeling approaches. The RBFNNs are fundamentally supervised machine learning algorithm‐based artificial neural networks that provide a flexible computational platform to integrate the conventional modeling approaches (e.g., time series) and develop hybrid environmental prediction (or forecasting) models. The hybrid vector time series‐based RBFNN IAQ prediction models developed and validated in this study using available software are based on the monitored in‐bus contaminants of carbon dioxide and carbon monoxide. © 2016 American Institute of Chemical Engineers Environ Prog, 36: 4–10, 2017