Dynamic alpha factor prediction with operating data - a machine learning approach to model oxygen transfer dynamics in activated sludge

Schwarz, Marcus; Trippel, Jana; Engelhart, Markus; Wagner, Martin

doi:10.1016/j.watres.2023.119650

Cited by 7 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DF is used to explain how much variability in a factor can be attributed to its connection with other related factors, and it is expressed as a number between 0.0 (failed to model the data properly at all) and 1.0 (perfect) [41]. Then, we can find out the important factors that greatly affect it.…”

Section: A Dynamic Factor (Df)mentioning

confidence: 99%

Multi-Temporal Factors to Analyze Indonesian Government Policies regarding Restrictions on Community Activities during COVID-19 Pandemic

Fachri Pane,

Adiwijaya,

Dwi Sulistiyo

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Concerning the implementation of the government policy regarding the Restriction of Community Activities (PPKM) during the COVID-19 pandemic era, there are still discrepancies in the economic sector and population mobility. This issue emerges due to irrelevant data and information in one region of Indonesia. The data differences should be carefully solved when implementing the PPKM policy. Besides, the PPKM must also pay attention to some specific factors related to the real conditions of a region, such as the data on the epidemiology of COVID-19, economic situations, and population mobility. These three are called Multi Factors. Then, based on the data, COVID-19 has a specific spreading period that cannot be repeated and thus is called temporal. Therefore, using the Multi-Temporal Factors approach to identify their correlation with the PPKM policy by applying Machine Learning, such as the Multiple Linear Regression model and Dynamic Factors, is essential. This research aims to analyze the characteristics and correlations of the COVID-19 pandemic data and the effectiveness of the government's policy on community activities (PPKM) based on the data quality. The results show that the accuracy of the multiple linear regression models is 84%. The Dynamic Factor shows that the five most important factors are idr_close, positive, retail_recreation, station, and healing. Based on the ANOVA test, all independent variables significantly influence the dependent one. The linear multiple regression models do not display any symptoms of heteroscedasticity. Thus, based on the data quality, the implementation of PPKM by the government has a practical impact.

show abstract

Section: A Dynamic Factor (Df)mentioning

confidence: 99%