Article Per Year (5 Year)
p-Index From 2020 - 2025
3.817
P-Index
This Author published in this journals
All Journal SMATIKA Sistemasi: Jurnal Sistem Informasi Sistem : Jurnal Ilmu-Ilmu Teknik Journal of System and Computer Engineering Syntax: Journal of Software Engineering, Computer Science and Information Technology Jurnal Abdimas Sang Buana Prosiding Konferensi Nasional PKM-CSR Jurnal Ilmiah IT CIDA : Diseminasi Teknologi Informasi Jurnal Ilmiah Edutic : Pendidikan dan Informatika The Journal of System Engineering and Technological Innovation Jurnal Pengabdian Masyarakat dan Inovasi Teknologi Jurnal Sistem Informasi dan Bisnis Cerdas Prosiding Seminar Nasional Unimus
Alven Safik Ritonga
Universitas Wijaya Putra
Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Mechanical Engineering Nursing Public Health Social Sciences Other

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of System and Computer Engineering

 1 
Aplikasi Berbasis Website Untuk Mendeteksi Status Gizi Balita Menggunakan Metode K-Nearest Neighbors (KNN) Ritonga, Alven Safik; Muhandhis, Isnaini
Journal of System and Computer Engineering Vol 5 No 1 (2024): JSCE: Januari 2024
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v5i1.1081

Abstract

Detecting the nutritional status of toddlers is important in monitoring and caring for toddlers' health. In this study, we propose the use of the K-Nearest Neighbors (KNN) method to detect the nutritional status of toddlers based on relevant attributes such as weight, height, age, gender and nutritional intake. This research involves developing a computer-based application that uses the KNN algorithm to classify the nutritional status of toddlers. Toddler data that has been collected from legitimate sources is used to train the KNN model. After training, this model can predict the nutritional status of new toddlers based on the entered attributes. In our experiments, we test and evaluate the performance of KNN models using evaluation metrics such as accuracy, precision, recall, and F1-score. In practical applications, the KNN model can be used as an aid in determining the nutritional status of toddlers and providing recommendations for appropriate action, such as increasing nutritional intake or necessary medical care. This research makes a contribution to the field of monitoring and caring for toddler nutrition by combining the KNN method as a tool for detecting nutritional status. The application developed can help medical personnel and parents monitor and take appropriate action related to toddler nutrition. The application, which has been built in the form of a website, can help detect the nutritional status of toddlers. When applying the KNN method to toddler nutritional status data, the application was successful in detecting toddler nutritional status with an accuracy of 74.73%.
Graph-Based Fraud Detection with Optimized Features and Class Balance Azizah, Anisa Nur; Ritonga, Alven Safik; Atmojo, Suryo; Widhiyanta, Nurwahyudi; Dewi, Suzana; Murdani, M Harist; Sari, Mamik Usniyah
Journal of System and Computer Engineering Vol 6 No 3 (2025): JSCE: July 2025
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v6i3.2001

Abstract

The increasing use of digital transactions also elevates the risk of fraud, particularly in credit card transactions. Fraud detection poses a challenge due to the highly imbalanced nature of the data and the complexity of relationships among entities. This study proposes a GNN-based approach, integrated with feature selection techniques and class imbalance handling through class weighting based on data distribution. Feature selection was performed using two methods: Correlation-based Feature Selection (CFS) and Random Forest Feature Importance, to obtain the most relevant features. Experimental results show that the combination of Random Forest feature selection and class weighting yielded the highest F1 Score, despite a slight decrease in accuracy. This indicates that feature selection and class weighting strategies can improve the model's ability to detect rare fraudulent transactions. This approach contributes to the development of more accurate and adaptive fraud detection systems in digital transaction environments.
Co-Authors Anisa Nur Azizah, Anisa Nur Dwi Setyo Wibisono Fernando, Ferdianus Fitrah Hilmi Ghifari Harianto Putra, Ahan Budiarta Isnaini Muhandhis Mubarokah, Solton Muhammad Harist Murdani Muhammad Shubhan Muhandhis, Isnaini Ni'matul Ichsan, Muchammad Ragil Nugroho, Alfi Ong Andre Wahyu Riyanto, Ong Andre Wahyu Purwaningsih, Endah Supeni Putra, Candra Novaliandi Pranata Rachmadian Dwi Anggara Reyhan Rizqi, Muhammad Sari, Mamik Usniyah siswadi siswadi siswadi Suharni Suharni Sujani, Sujani Suryo Atmojo, Suryo Suzana Dewi Syahputra, Adhe Rifqi Wahyu Nugroho Wasil, Mohammad Wibisono, Dwi Setyo Widhiyanta, Nurwahyudi Wijaya, Nicholas