Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Bulletin of Network Engineer and Informatics (BUFNETS)
Muhammad Ainurrohman, Muhammad Ainurrohman
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Optimization Grouping Quality MBG Program Food Uses K-Means Algorithm Based on Davies-Bouldin Index Evaluation Fitriasih, Fitriasih; Fahrudin, Fahrudin; Heny Indriani, Heny Indriani; Denny Vasanando Sabanise, Denny Vasanando Sabanise; Muhammad Ainurrohman, Muhammad Ainurrohman
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April - September 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/fqnk3355

Abstract

The evaluation of food quality in the Free Nutritious Meal Program (MBG) requires an objective and systematic approach to ensure nutritional standards and service effectiveness. This study applies a data mining technique using the K-Means clustering algorithm to classify food quality based on multiple attributes, including Calories, Protein, Fat, Carbohydrates, Freshness, Cleanliness, Serving Temperature, and Eligibility. This research utilizes RapidMiner to perform data preprocessing, involving data preprocessing through normalization, clustering with K-Means, and performance evaluation using the Davies-Bouldin Index (DBI) and Average Within Centroid Distance. Two clustering scenarios, K=3 and K=5, were evaluated to determine the optimal number of clusters.The results indicate that the K=3 model achieves a lower DBI value (0.214) compared to K=5 (0.224), indicating better cluster separation. Although K=5 produces more compact clusters, it does not improve overall clustering quality due to weaker separation. Therefore, the K=3 configuration is identified as the optimal model, as it provides a better balance between cluster separation and interpretability. These findings demonstrate that a multi-attribute clustering approach can effectively support data-driven decision-making in evaluating and improving food quality in the MBG program.
Co-Authors Denny Vasanando Sabanise, Denny Vasanando Sabanise Fahrudin Fahrudin Fitriasih, Fitriasih Heny Indriani, Heny Indriani