Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal International Journal of Applied Sciences and Smart Technologies
Arshella, Ika Arva
Unknown Affiliation
Computer Science & IT Energy Engineering Industrial & Manufacturing Engineering

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

Found 1 Documents
Search

 1 
Improving the Accuracy of Prediction of Dissolved Oxygen and Nitrate Level Using LSTM with K-Means Clustering and Spearman Analysis Arshella, Ika Arva; Mustika, I Wayan; Nugroho, Prapto
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12361

Abstract

This study discusses how to prepare data properly before entering the learning process for prediction using Deep Learning (DL). Long Short-Term Memory (LSTM) is one of the DL methods that is often used for prediction because of its superiority in maintaining long-term information. Although LSTM has proven effective, there are issues related to low-quality data that can reduce prediction accuracy. This problem is important to discuss because accuracy is important in predicting a value while field conditions can reduce the quality of the data taken. Data merging based on the relationship of each data collection location using the Spearman analysis and the K-Means clustering method is used to improve data quality. The results of the study show that improving data quality by merging data using K-Means has been successfully applied to various dataset conditions. In this study, we used two types of datasets related to river water quality, namely Dissolved Oxygen (DO) concentration and Nitrate levels for our simulation. The first data set produced DO predictions for eight locations with an average R2 = 0.9998, MAE = 0.0007, MSE = 1,13×10-6. The second data set produced nitrate predictions for ten locations with an average R2 = 0.7337, MAE = 0.0111, MSE = 0,00029
Co-Authors I Wayan Mustika Prapto Nugroho