Article Per Year (5 Year)
p-Index From 2021 - 2026
1.152
P-Index
This Author published in this journals
All Journal JUTI: Jurnal Ilmiah Teknologi Informasi JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Jurnal Tekno Insentif Journal of Computer Networks, Architecture and High Performance Computing Malcom: Indonesian Journal of Machine Learning and Computer Science
Roni Andarsyah
Universitas Logistik dan Bisnis Internasional
Computer Science & IT Dentistry Education Engineering Library & Information Science

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Optimizing Blockchain Network Creation: Automation with Ansible on Private Blockchain Hyperledger Fabric Using Simplified RAFT Consensus Method Muhammad Rizal Supriadi Rizal; Roni Andarsyah; M. Yusril Helmi Setyawan
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 7 No. 1 (2023): Issues July 2023
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v7i1.10035

Abstract

In the rapidly evolving world of blockchain technology, efficient and reliable blockchain network creation poses a significant challenge. Manual processes in blockchain network setup often consume time, are prone to errors, and difficult to maintain. This research aims to optimize the creation of blockchain networks by leveraging Ansible automation tools on private blockchains using Hyperledger Fabric and implementing a simplified RAFT method. The approach involves configuring blockchain infrastructure with Ansible and integrating the simplified RAFT method into the private blockchain network. The test results demonstrate that the proposed approach significantly reduces the time required for blockchain network creation. In testing with a 92 Mbps internet connection, the time needed to create a blockchain network with 1 orderer and 1 peer with 44 connected channels, ready for transactions, was successfully reduced from 102.6 minutes to only 51.4 minutes. Moreover, the Ansible automation approach reduces the risk of errors and simplifies network maintenance. In conclusion, this research confirms the effectiveness of the proposed approach in optimizing the blockchain network creation process, reducing the required time, and enhancing efficiency and ease of maintenance. The proposed solution provides a valuable contribution to the development of efficient private blockchain infrastructure while minimizing errors and increasing flexibility.
Topic Modeling for Constructing Learning Profiles Using LDA and Coherence Evaluation Andika Dwi Arko; Muhamad Yusril Helmi Setyawan; Roni Andarsyah
JUTI: Jurnal Ilmiah Teknologi Informasi Vol.23, No.2, July 2025
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v23i2.a1301

Abstract

Understanding individual learning patterns is important for supporting effective learning strategies in the digital education ecosystem. This study proposes a topic modeling approach using the Latent Dirichlet Allocation (LDA) algorithm to form learning profiles based on student interaction data from EdNet-KT1. The dataset includes 153,824 interactions with 11,613 questions, which were converted into semantic tag-based pseudotexts. Modeling was performed with 20 topics, which were selected as a compromise between semantic quality (coherence score 0.6688) and model readability, although the highest coherence score appeared with a larger number of topics. Each question is linked to a dominant topic, and student accuracy is calculated to form a student-topic performance matrix. The results of the analysis show that 66% of students mastered more than five topics, reflecting a broad range of knowledge. Visualization with heat maps, radar charts, and line charts provides a detailed overview of each individual's strengths and weaknesses. Segmentation was performed using the K-Means algorithm and produced four clusters based on student performance distribution. Adaptive learning recommendations are compiled based on an accuracy threshold of < 0.5 and a number of interactions > 10. Topics_13, topics_10, and topics_12 were identified as the most challenging topics. The results of this study indicate the potential of LDA-based approaches and clustering as analytical tools for shaping more personalized and contextual learning systems. Further research could explore sequential modeling and experimental validation of the effectiveness of recommendations
Prediksi harga FCPO Bursa Malaysia Menggunakan Support Vector Regression Berbasis Particle Swarm Optimization: FCPO Malaysia Stock Exchange Price Prediction Using Particle Swarm Optimization-Based Support Vector Regression Fatwa Fatahillah Fatah; Roni Andarsyah; Cahyo Prianto
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2257

Abstract

Crude Palm Oil (CPO) merupakan komoditas minyak nabati strategis yang harganya dipengaruhi oleh dinamika penawaran dan permintaan global serta kebijakan perdagangan. Fluktuasi yang cepat dan sulit diprediksi ini berdampak pada seluruh rantai pasok dari petani hingga industri pengolahan dan pembuat kebijakan, sehingga dibutuhkan model prediksi yang akurat dan adaptif berbasis sinyal pasar harian. Penelitian ini membangun model Support Vector Regression (SVR) yang ditingkatkan menggunakan Particle Swarm Optimization (PSO), serta membandingkannya dengan SVR tanpa optimasi. Data yang digunakan dalam penelitian ini meliputi informasi harga harian minyak sawit (FCPO) di BURSA Malaysia Derivatives dari tahun 2020 hingga 2025. Hasil menunjukkan PSO menemukan konfigurasi yang efektif, dengan biaya minimum MSE = 0,018675, dan PSO-SVR melampaui SVR default, baik secara visual maupun secara metrik. Pada skala asli diperoleh MAE = 83,939, MAPE = 1,84%, RMSE = 119,881, dan R² = 0,9818. Hasil ini menunjukkan bahwa PSO-SVR mampu meningkatkan kinerja prediksi dibandingkan dengan SVR standar. Namun, nilai R² yang sangat tinggi perlu diinterpretasikan secara hati-hati mengingat karakteristik harga CPO yang volatil serta potensi risiko overfitting. Dengan demikian, PSO-SVR dapat dipertimbangkan sebagai pendekatan pendukung untuk prediksi harga CPO berbasis data pasar harian, dengan tetap memerlukan validasi berkala sebelum diterapkan dalam pengambilan keputusan operasional.
Systematic Literature Review: Predicted Color Output in UI/UX Design Using Machine Learning Agita Nurfadillah; Roni Andarsyah
Journal of Computer Networks, Architecture and High Performance Computing Vol. 7 No. 3 (2025): Articles Research July 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v7i3.6357

Abstract

An attractive user interface (UI) design is greatly influenced by the selection of appropriate colors, but the selection process tends to be subjective. To address this challenge, this study was conducted to identify commonly used machine learning techniques and evaluate their effectiveness in recommending colors based on RGB and HSL features. The method used was a Systematic Literature Review (SLR) of 39 articles published between 2020 and 2025. The study was conducted through three main stages, namely planning, implementation, and reporting. The review results show that approaches such as K-Means are widely used in the dominant color extraction stage, while classification algorithms such as Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest are applied for color prediction and recommendation. Random Forest is one of the models that shows superior performance, especially in terms of prediction stability and the ability to handle large numbers of variables. The model development process usually begins with color quantization, followed by data labeling and model training. Based on these findings, it can be concluded that Random Forest is a reliable model in color recommendation systems, especially when supported by good data preprocessing stages and proper parameter tuning.
Microservices Integration Using CI/CD Pipelines Bagas Agung Wiyono; Fatimah Azzahra Nur Faidah; Roni Andarsyah
Jurnal Tekno Insentif Vol 20 No 1 (2026): Jurnal Tekno Insentif
Publisher : Lembaga Layanan Pendidikan Tinggi Wilayah IV

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36787/jti.v20i1.2233

Abstract

Penelitian ini mengimplementasikan pipeline Continuous Integration dan Continuous Deployment (CI/CD) pada pengembangan aplikasi web Sistem Bimbingan Online menggunakan GitHub Actions dan Google Cloud Functions untuk mengatasi permasalahan deployment manual yang lambat, tidak konsisten, dan rawan kesalahan manusia. Pipeline dirancang dengan dua workflow utama yaitu workflow Build untuk pengujian otomatis (Jest) dan analisis kualitas kode (SonarCloud), serta workflow Deployment untuk rilis otomatis ke Google Cloud Functions. Pengukuran dilakukan selama 7 minggu dengan 114 eksekusi workflow. Hasil menunjukkan tingkat keberhasilan build 79,82%, frekuensi deployment 14 kali per minggu, dan rata-rata waktu eksekusi 2 menit 47 detik. Proyek mendapatkan rating A untuk Bugs, Vulnerabilities, dan Code Smells dari SonarCloud. Implementasi CI/CD berhasil mengurangi waktu deployment dari 15–30 menit secara manual menjadi rata-rata 2–3 menit secara otomatis.
Co-Authors Agita Nurfadillah Alwizain Almas Trigreisian Andika Dwi Arko Bagas Agung Wiyono Fatimah Azzahra Nur Faidah Fatwa Fatahillah Fatah M. Yusril Helmi Setyawan Muhamad Yusril Helmi Setyawan Muhammad Rizal Supriadi Rizal Nisa Hanum Harani Prianto, Cahyo