Here, we propose a statistical approach that exploits the advantages of PCA and those of multivariate memory monitoring schemes, like the multivariate cumulative sum (MCUSUM) and multivariate exponentially weighted moving average (MEWMA) monitoring schemes to better detect incipient anomalies.
This can be done several ways, for example Muscatello et al. [ 14] recommended using a four week moving average of laboratory notifications for monitoring.
Pirhooshyaran and Niaki (2015) proposed a double-max multivariate exponentially weighted moving average (MEWMA) control chart to monitor the parameters of the multistage processes when data are multivariate and autocorrelated.
This paper proposes an exponentially weighted moving average scheme with variable sampling intervals for monitoring linear profiles.
In this study, we applied a stochastic autoregressive integrated moving average (ARIMA) model with the objective of monitoring and short-term forecasting HFRS incidence in China.
A weighted moving average algorithm was considered in [ 8] to monitor the time-series.
The following pollutant measurements were recorded at each monitoring station (maximum 6): SO2(mean 24-hours), TSP or Black Smoke (mean 24-hours), PM10- if available-(mean 24-horrs), NO2 (maximum 1 hour, mean 24-hours), O3 (maximum 1 hour, maximum 8-hours moving average) CO (maximum 8-hour moving average).
Other univariate statistical monitoring methods, such as the exponentially weighted moving average (EWMA) control scheme, has shown better abilities to detect small faults.
Jiang, Tsui, and Woodall (2000) developed a control chart, called the autoregressive moving average (ARMA) control chart, which has been shown suitable for monitoring a series of autocorrelated data.
The exponentially weighted moving average chart of the squared deviation (EWMAS) is often applied for monitoring changes such as step shifts and linear drifts in process variation when no subgrouping is available.
