Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
MUHAMMAD RIZKY ERI EKO JULIANTO
Teknik Informatika
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
PERBANDINGAN ALGORITMA KNN, SVM, DAN RANDOM FOREST DALAM KLASIFIKASI KUALITAS AIR KOLAM IKAN : COMPARISON OF K-NEAREST NEIGHBORS, SUPPORT VECTOR MACHINE, AND RANDOM FOREST ALGORITHMS FOR FISH POND WATER QUALITY CLASSIFICATION MUHAMMAD RIZKY ERI EKO JULIANTO; Catur Supriyanto
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8478

Abstract

Water quality is a critical factor in the success of fish farming because it directly affects fish growth, health, and survival. Manual water quality assessment is time-consuming and requires specialized expertise, which may lead to inaccuracies in decision-making. Therefore, this study aims to compare the performance of the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest algorithms in classifying fish pond water quality. The dataset consisted of 4,300 samples with 14 physical and chemical water quality parameters and three water quality classes: Excellent, Good, and Poor. The research process included data preprocessing, Min-Max Scaling normalization, training and testing data splitting, model training, performance evaluation using accuracy, precision, recall, and F1-score, and model validation using 5-Fold Cross Validation. The results show that the Random Forest algorithm achieved the best performance with an accuracy of 99.30%, followed by SVM with 93.95% and KNN with 85.81%. Furthermore, the 5-Fold Cross Validation results indicate that Random Forest achieved the highest average accuracy of 98.85% with a standard deviation of 0.42, demonstrating excellent model stability and generalization capability. These findings indicate that the Random Forest algorithm is highly effective for fish pond water quality classification and has strong potential to support automated water quality monitoring and decision-making in aquaculture management.
Co-Authors Catur Supriyanto