Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Wireless And Multimedia Communications
Kurnia Festa, M Andre
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Non Linear Modeling of the Relationship Between Raw Water Turbidity, Accelerator Unit Turbidity, and Filtration Turbidity Using a Quadratic Interaction Model in a Water Treatment Plant Nelvidawati; Firdaus, firdaus; Kurnia Festa, M Andre
International Journal of Wireless And Multimedia Communications Vol. 3 No. 1 (2026): International Journal of Wireless And Multimedia Communications
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62671/jowim.v3i1.237

Abstract

This study aims to analyze the non-linear relationship between raw water turbidity, turbidity after the accelerator unit, and turbidity after the filtration unit at the Gunung Pangilun Water Treatment Plant (WTP) in Padang City using the Quadratic Interaction Model (QIM) approach. Turbidity data were collected from 1–5 June 2025 at one-hour intervals, resulting in 50 data points for each sampling location. The data processing stages included missing value inspection, outlier detection using the Interquartile Range (IQR) method, data consistency checking, relationship visualization among variables, and QIM-based modeling using Python. The results show that the QIM was unable to adequately represent the relationships among the variables, as indicated by an R-squared value of 0.145 and an adjusted R-squared of 0.048. All model parameters exhibited p-values greater than 0.05, indicating no statistically significant influence on turbidity after filtration. Model evaluation yielded an RMSE of 0.496 NTU and a MAPE of 19.34%, suggesting a moderate level of prediction accuracy. Additionally, the analysis identified 14% outliers and 9 inconsistent data points for each sampling location.
Co-Authors Firdaus Firdaus Nelvidawati