Monitoring Air Quality using the Neural Network based Control Chart

This paper intends to develop ANN (artificial neural network) based control charts. The (ANN) is a machine learning (ML) methodology that evolved and developed from the scheme of imitating the human brain. ANN has been explained by discussing the network topology and development parameters (number of nodes, number of hidden layers, learning rules, and activated function). Among many models that deal with combining factors and data-based supervised learning classifiers, ANN has the most significant impact on air quality as air quality has nonlinear and noisy data. The best activation of a new hybrid EWMA (HEWMA) control chart is proposed by mixing two EWMA control charts to efficiently monitor the process mean. The ANN-based HEWMA scheme was a promising procedure for the detection of air quality measurements. We compare the performance of the ANN-based HEWMA control chart and the EWMA control chart based on average run lengths when the data are contaminated with the measurement error. The results revealed that the higher the temperature, the better fitting shape we obtain from air quality parameters. The ANN-based HEWMA control chart deals with measurement errors more efficiently than the EWMA control chart.