Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknik Informatika dan Komunikasi
Febiola Hutni Mosa
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Klasifikasi Pola Konsumsi Energi Listrik Rumah Tangga Menggunakan Metode K-Nearest Neighbor Febiola Hutni Mosa; Franki Yusuf Bisilisin
Jurnal Ilmiah Teknik Informatika dan Komunikasi Vol. 5 No. 3 (2025): November: Jurnal Ilmiah Teknik Informatika dan Komunikasi 
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juitik.v5i3.1676

Abstract

The increasing demand for electrical energy in Kupang City, particularly in the Kayu Putih Subdistrict, necessitates a system capable of efficiently and accurately identifying electricity consumption patterns. The continuously rising demand for electrical energy may lead to various problems if not properly managed, such as supply disruptions or energy wastage. Therefore, this study aims to classify household electricity consumption patterns using a data-driven approach based on the K-Nearest Neighbor (KNN) method. The KNN method was chosen for its effectiveness in classifying data with a high level of accuracy, especially for datasets with complex characteristics. The designed system categorizes household electricity consumption into three main classes: low, medium, and high. This classification considers several important factors, including the number of family members, the types of electrical appliances used, and their daily usage habits. The results of the study indicate that the KNN method successfully classified household electricity consumption patterns with good performance. Testing using a confusion matrix achieved the highest accuracy of 97% at K = 4. This model was selected for implementation in the household electricity consumption classification system using the K-Nearest Neighbor (KNN) method.
Co-Authors Franki Yusuf Bisilisin