Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengabdian Kepada Masyarakat (Indonesian Journal of Community Engagement) Vokasi UNESA Bulletin of Engineering, Technology and Applied Science
Yonathan Ferry Hendrawan
Universitas Trunojoyo Madura
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Mechanical Engineering Transportation

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

Found 2 Documents
Search

 1 
Pembekalan Pemrograman Dasar Komputer bagi Guru TIK dan Siswa Terpilih di Tiga Mitra SMA Kabupaten Bangkalan Sri Wahyuni; Fika Hastarita Rachman; Yonathan Ferry Hendrawan
Jurnal Pengabdian kepada Masyarakat (Indonesian Journal of Community Engagement) Vol 2, No 1 (2016): September
Publisher : Direktorat Pengabdian kepada Masyarakat Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (309.747 KB) | DOI: 10.22146/jpkm.22234

Abstract

Programming is a basic skill in computing (Teknologi Informasi dan Komunikasi–TIK) feld. In our school partners located at Bangkalan, the teachers of computing course have non-computing background (physics, mathematics, biology). Tis condition means that their programming skill is not good enough. Tis is certainly a suboptimal circumstance since teacher’s mastery of a subject has a lot to do with the success of the teaching-learning process. Computer olympics (olimpiade komputer) is a programming competition for high school students. It has two kinds of tests. Tey were mathematical logic and programming problem solving. Because of the lacking in teacher’s programming skill, the preparation event focused only on mathematical logic. Tis approach had led the students to pass through frst/city selection, but it was not enough to pass the second/provincial selection. In this community service, we gave programming learning modules to the school partners and also train them about pascal programming. Te initial targets were TIK teachers who were also the preparation event coaches. Afer several considerations, we asked the schools to also send their best students as participants for the training. Te purpose were to not only prepare the current participant team, but also to support the regeneration of future teams. By the end of this activity, our partners’ teachers and students have had a better pascal programming skills. Tis result is shown in the increasing scores they get in their pre, mid, and fnal training evaluations.
Exploring Supervised Learning Methods for Predicting Cuisines from Their Ingredients Yonathan Ferry Hendrawan; Omkar Chekuri
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 1 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i1.34153

Abstract

This study explores the use of multi-class classification to predict cuisines based on ingredient list using a Kaggle dataset derived from the Yummly recipe database. The goal was to identify the most effective machine-learning techniques for classifying recipes into different cuisine regions based on their ingredients. Six supervised learning methods were examined: Backpropagation Neural Network, Support Vector Machine (SVM), Naive Bayes, Decision Tree, Random Forest, and AdaBoost. The preprocessing pipeline involvedtokenizing ingredients into numerical features, ensuring compatibility with machine-learning algorithms, and facilitating model training and evaluation. Among the models tested, the SVM and Random Forest algorithms performed the best, achieving accuracies of 76.7% and 73.2%, respectively. These results were relatively close to the top competition leaderboard accuracy of 83%. Our custom implementations oftheBackpropagation Neural Network and Decision Tree demonstrated competitive performance, though hardware limitations during experimentation prevented the full optimization of these models. The findings emphasize the critical role of factors such as parameter tuning, dataset size, and feature preprocessing in determining classification accuracy. Additionally, the study highlights how a combiningof well-selected algorithms and data preprocessing can yield meaningful improvements in prediction quality. All codesand materials used in this research are publicly available, enabling further exploration by other researchers and practitioners
Co-Authors Omkar Chekuri Rachman, Fika Hastarita Sri Wahyuni