Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Sistem Komputer dan Informatika (JSON)
Pratama, Kharis Suryandaru
Unknown Affiliation
Computer Science & IT Control & Systems Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Chicken Weight Prediction in Close House Farm Using Fuzzy Method Pratama, Kharis Suryandaru; Wardoyo, Retantyo
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 18, No 4 (2024): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.96406

Abstract

This study aims to predict the weight of chicken on a close house farm using the Fuzzy Logic method by implementing the LUKASEWICZ method. The data used in this study are the factors that affect the weight of the chicken including the number of chickens entering, the initial weight of the chicken, the temperature of the cage, the humidity of the cage, the quantity of water, the quantity of feed, and air circulation (wind speed) in the cage. The results of the calculation of Fuzzy with the łukasiEwicz method of these factors can be used to predict the chicken boboy during the harvest period and according to the weight set during the harvest period. The accuracy of the prediction value with the Absolute Percentage Error (MAPE) mean test shows the value of 5,3981%. It was concluded that the calculation of fuzzy with the łukasiewicz method can be used to predict the weight of chicken during the harvest period.
Optimasi K-Means Menggunakan Algoritma Genetika pada Metode User-based Collaborative Filtering Adilla, Axl; Suksmawati, Affi Nizar; Pertiwi, Affifah Mutiara; Pratama, Kharis Suryandaru
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 2 (2025): Desember 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i2.9382

Abstract

Collaborative filtering merupakan teknik sistem rekomendasi yang menggunakan informasi rating dari beberapa pengguna untuk memprediksi rating suatu item bagi pengguna tertentu. Namun, tidak semua pengguna memberikan rating pada seluruh item. Hal ini menyebabkan ketidakmampuan sistem dalam menentukan nearest neighborhood, sehingga rekomendasi yang dihasilkan menjadi lemah. Penelitian ini mengusulkan penggunaan Algoritma K-Means untuk mengelompokkan neighborhood yang sesuai. Penentuan awal titik pusat klaster pada Algoritma K-Means dioptimalkan menggunakan Algoritma Genetika. Evaluasi dilakukan dengan memvariasikan jumlah klaster optimal pada beberapa metode pengukuran yang digunakan, yaitu Jaccard Similarity Coefficient, Sørensen–Dice Coefficient, dan Hamming Coefficient. Hasil pengujian menggunakan pengukuran Jaccard Similarity Coefficient, Sørensen–Dice Coefficient, dan Hamming Coefficient memperoleh nilai fitness masing-masing sebesar 4.490, 4.979, dan 4.964 untuk jumlah klaster optimal 4 dan 6. Sementara itu, nilai MAPE rata-rata untuk ketiga metode pengukuran kemiripan tersebut sebesar 60%.
Co-Authors Adilla, Axl Pertiwi, Affifah Mutiara Retantyo Wardoyo Suksmawati, Affi Nizar