Open AccessMixed Multivariate EWMA-CUSUM (MEC) Chart based on MLS-SVR Model for Monitoring Drinking Water Quality
Author(s) -
Muhammad Mashuri,
Hidayatul Khusna,
Wibawati,
Felicia Putri
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2123/1/012019
Subject(s) - ewma chart , cusum , control chart , multivariate statistics , autocorrelation , statistics , chart , statistical process control , moving average , computer science , mathematics , process (computing) , operating system
Monitoring the quality of drinking water needs to be conducted considering the important role of water in human life. Mixed Multivariate EWMA-CUSUM (MEC) chart is a multivariate control chart developed for observing the mean process. Based on the previous studies, this chart has better performance in detecting a shift in the process mean. In this research, the MEC is applied to observe the grade of drinking water. However, there is autocorrelation in drinking water data which lead to more false alarm occurred. Therefore, the Multioutput Least Square Support Vector Regression (MLS-SVR) model is employed to reduce or even remove the autocorrelation in the data. Using the optimal hyperparameter, the MLS-SVR algorithm produces the residuals of phase I with no autocorrelation. Those residuals are then used to form the MEC control charts. When the MEC is used to monitor the residual in phase I, there is no signal of out-of-control found. Further, in phase II, out-of-control observations are detected. The MEC chart can detect more signals out of control compared to the conventional Hotelling’s T 2 and Multivariate Exponentially Moving Average (MEWMA) charts.