Article Per Year (5 Year)
p-Index From 2021 - 2026
2.686
P-Index
This Author published in this journals
All Journal Scientific Journal of Informatics JURNAL MEDIA INFORMATIKA BUDIDARMA Abdimas Umtas : Jurnal Pengabdian kepada Masyarakat Mobile and Forensics Jurnal Informatika dan Rekayasa Perangkat Lunak Jurnal Abdi Insani Journal of Innovation Information Technology and Application (JINITA) Jurnal Ilmiah Edutic : Pendidikan dan Informatika Scientific Journal of Informatics IJMST SainsTech Innovation Journal Scientific Journal of Computer Science Methods in Science and Technology Studies Breakthroughs in Informatics, Networking, Algorithms, Research, and Yield (BINARY)
Syahrani Lonang
Universitas Qamarul Huda Badaruddin Bagu
Religion Agriculture, Biological Sciences & Forestry Arts Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Neuroscience Social Sciences

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Benchmarking Model Machine Learning untuk Prediksi Data Berdasarkan Akurasi dan Error Syahrani Lonang; Danang Tejo Kumoro; M. Dermawan Mulyodiputro; Ardhana, Valian Yoga Pudya
SainsTech Innovation Journal Vol. 8 No. 2 (2025): SIJ VOLUME 8 NOMOR 2 TAHUN 2025
Publisher : LPPM Universitas Qamarul Huda Badaruddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37824/sij.v8i2.2025.1141

Abstract

Perkembangan machine learning mendorong pemanfaatan berbagai model regresi untuk melakukan prediksi data secara akurat dan efisien. Namun, perbedaan karakteristik dataset menyebabkan kinerja setiap model bervariasi, sehingga diperlukan proses benchmarking untuk menentukan model yang paling optimal. Penelitian ini bertujuan untuk membandingkan kinerja beberapa model machine learning dalam tugas prediksi data berbasis regresi tanpa melakukan pengembangan aplikasi. Model yang dievaluasi meliputi Linear Regression, Decision Tree Regression, Random Forest Regression, Support Vector Regression, dan K-Nearest Neighbor Regression. Dataset yang digunakan merupakan dataset publik dengan variabel numerik yang telah melalui tahap praproses data, meliputi pembersihan data, normalisasi, dan pembagian data latih serta data uji. Evaluasi kinerja model dilakukan menggunakan metode K-Fold Cross Validation dengan metrik Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa Random Forest Regression memberikan kinerja terbaik dengan nilai error terendah, nilai R² tertinggi, serta stabilitas model yang baik dibandingkan model lainnya. Hasil ini menunjukkan bahwa pendekatan ensemble efektif dalam meningkatkan akurasi dan kemampuan generalisasi model pada tugas prediksi data regresi.
Perancangan Sistem Fundrising Online LAZ DASI NTB Menggunakan Metode Zachman Syahrani Lonang; Yuan Sa'adati; Nuraqilla Waidha Bintang Grendis; Ahmad Fatoni Dwi Putra
SainsTech Innovation Journal Vol. 8 No. 2 (2025): SIJ VOLUME 8 NOMOR 2 TAHUN 2025
Publisher : LPPM Universitas Qamarul Huda Badaruddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37824/sij.v8i2.2025.1142

Abstract

Artikel ini membahas tentang latar belakang, metode, dan hasil penerapan Metode Zachman dalam perancangan sistem penggalangan dana online. Metode Zachman adalah kerangka kerja yang memberikan pendekatan holistik untuk desain sistem dengan mempertimbangkan perspektif yang berbeda, seperti apa, bagaimana, di mana, siapa, kapan, dan mengapa. Dengan menerapkan metode ini, pengembang sistem dapat lebih memahami kebutuhan pengguna dan merancang sistem penggalangan dana yang lebih efektif dan efisien. Artikel tersebut membahas pentingnya mengklarifikasi kebutuhan pengguna, memilih teknologi yang paling efisien, meningkatkan efektivitas jadwal dan jadwal, serta menyediakan informasi yang lebih detail untuk meningkatkan kepercayaan pengguna. Secara keseluruhan, penggunaan Metode Zachman dapat membantu pengembang sistem membuat keputusan yang lebih baik dan menciptakan sistem penggalangan dana yang lebih efektif, efisien, dan bermanfaat bagi masyarakat. Kesimpulannya, penerapan Metode Zachman dalam perancangan sistem penggalangan dana online dapat membantu pengembang sistem membuat sistem yang memenuhi kebutuhan pengguna dan tujuan penggalangan dana secara lebih efektif. Metode ini memberikan kerangka kerja yang berguna untuk membuat keputusan yang lebih baik dan mempertimbangkan perspektif yang berbeda dalam desain sistem. Sistem yang dihasilkan dapat membantu organisasi mencapai tujuan penggalangan dananya dan memberikan manfaat yang lebih besar kepada masyarakat.
Perancangan Motion Graphic Sebagai Media Edukasi Pencegahan Hiv/Aids Bagi Kalangan Dewasa Awal Al Habib; Saputra, Joni; Syahrani Lonang
SainsTech Innovation Journal Vol. 8 No. 2 (2025): SIJ VOLUME 8 NOMOR 2 TAHUN 2025
Publisher : LPPM Universitas Qamarul Huda Badaruddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37824/sij.v8i2.2025.1144

Abstract

HIV/AIDS remains a health issue that requires serious attention, especially among early adults who have high social activity. Limited knowledge about transmission and prevention, along with persistent stigma in society, makes HIV/AIDS education less effective. This study aims to design motion graphic-based educational media so that HIV/AIDS prevention information becomes more engaging, easier to understand, and suitable for the characteristics of early adults. The methods used include a literature review, observation, and audience needs analysis, followed by concept development, storyboard creation, visual design, and production. The result is an educational motion graphic video that explains HIV/AIDS, modes of transmission, prevention strategies, and encourages healthy behavior and non-discriminatory attitudes toward people living with HIV/AIDS. This media is expected to improve early adults’ knowledge, awareness, and positive attitudes toward HIV/AIDS prevention.
Bandwidth Management Using the Hierarchical Token Bucket Method to Enhance Server Network Performance Jayadi, Ahmad; Kusnayadi, Dedi Satriawan; Lonang, Syahrani; Dahmani, Abdennasser; Driss, Zied; Sharkawy, Abdel-Nasser
Scientific Journal of Computer Science Vol. 1 No. 2 (2025): December
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjcs.v1i2.2025.40

Abstract

Villa Nomada, as an accommodation in Kuta, Central Lombok, is experiencing internet network instability due to uneven and uncontrolled bandwidth distribution, which disrupts user comfort, especially for foreign guests who require an optimal connection. The solution implemented is bandwidth management using the Hierarchical Token Bucket (HTB) method to allocate bandwidth fairly and efficiently. This research contributes to improving quality of service (QoS) by optimizing network performance through HTB. The method used is HTB configuration to allocate bandwidth based on user categories (VIP, Regular, and Office). Network performance was evaluated before and after implementation to measure improvements in speed and stability. The research results showed that HTB successfully distributed bandwidth evenly, with VIP users receiving priority, while regular and office users obtained stable connections without interruptions. Network efficiency improved, reducing congestion and increasing user satisfaction. We rated the HTB method as “Good” for optimizing network performance. In conclusion, the implementation of HTB successfully addressed the bandwidth management issues at Villa Nomada, ensuring fair distribution and optimal network performance for all users.
Machine Learning Approach for Heart Failure Patient Classification Using K-Nearest Neighbors Algorithm Masitha, Alya; Lonang, Syahrani; Reski, Julia Mega
Methods in Science and Technology Studies Vol. 1 No. 2 (2025): December
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/msts.v1i2.2025.44

Abstract

Heart failure is a cardiovascular disease with a high mortality rate and tends to increase every year. Therefore, a method is needed that can help the process of classifying heart failure quickly and accurately. This study aims to design and implement a heart failure classification system using the K-Nearest Neighbor (K-NN) machine learning method. The dataset used consists of 918 patient data with eleven input variables and two output classes, namely patients diagnosed with heart failure and patients not diagnosed with heart failure. The research stages include data loading, dividing training data and test data, implementing the K-NN algorithm with various K values, and evaluating model performance using accuracy, precision, recall, and F1-score metrics. The test results show that variations in the K value have a significant effect on the performance of the classification model. The K value = 9 produces the best performance with an accuracy of 93.48%, a recall of 96.36%, and an F1-score of 94.64%, which indicates a good balance between precision and recall. Based on these results, the K-NN method with a value of K = 9 is recommended as the optimal configuration in the classification of heart failure disease in this study.
Enhancing Early Diabetes Detection Using Tree-Based Machine Learning Algorithms with SMOTEENN Balancing Lonang, Syahrani; Putra, Ahmad Fatoni Dwi; Firdaus, Asno Azzawagama; Syuhada, Fahmi; Sa'adati, Yuan
Mobile and Forensics Vol. 8 No. 1 (2026)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/mf.v8i1.14495

Abstract

Diabetes continues to be a critical global health issue, demanding accurate predictive systems to enable preventive interventions. Traditional diagnostic tests lack efficiency for large-scale early screening, which has led to growing interest in artificial intelligence solutions. This research proposed an effective methodology for diabetes classification based on tree-based algorithms enhanced with SMOTEENN balancing. The study employed the Kaggle Diabetes Prediction Dataset with 100,000 instances and eight medical and demographic features. Preprocessing steps included handling missing and duplicate values, encoding categorical variables, and scaling numerical attributes with Min-Max normalization. To address severe class imbalance, SMOTEENN was adopted, producing a cleaner and more balanced dataset. Model evaluation was performed using Stratified 5-Fold cross-validation on six classifiers: Decision Tree, Random Forest, Gradient Boosting, AdaBoost, XGBoost, and CatBoost. Experimental results indicated significant gains after balancing, with ensemble methods outperforming single-tree baselines. Random Forest delivered the best overall performance (98.93% accuracy, 98.96% F1-score, 99.16% recall, 99.94% AUC), followed by CatBoost and XGBoost with comparable results above 99% AUC. While Decision Tree benefited most from SMOTEENN in relative terms, it remained less competitive. Analysis of the importance of the analysis revealed HbA1c level and blood glucose level as dominant predictors, validating clinically meaningful learning. These findings suggest that integrating hybrid resampling with ensemble tree classifiers provides reliable and general predictions for diabetes risk. The approach holds promise for deployment in healthcare decision support systems.
Hybrid Feature Selection for Effective Heart Disease Detection: A Multi-Algorithm Machine Learning Approach Lonang, Syahrani; Putra, Ahmad Fatoni Dwi; Syuhada, Fahmi; Firdaus, Asno Azzawagama; Masitha, Alya
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.38815

Abstract

Purpose: This research aims to develop an effective early detection model for heart disease with data balancing and hybrid feature selection. The study seeks to enhance predictive accuracy and minimize errors, providing a robust model for clinical decision support systems. Methods: The study used the Heart Failure Prediction dataset derived from Kaggle. A novel hybrid framework was implemented, integrating SMOTEENN (Synthetic Minority Over-sampling Technique + Edited Nearest Neighbors) for data balancing and a Hybrid Feature Selection (HFS) method combining Chi-square and Backward Elimination. Eight machine learning algorithms, including Logistic Regression, Naïve Bayes, Decision Tree, K Nearest Neighbor, Random Forest, Gradient Boosting, Support Vector Machine, and XGBoost. Performance was assessed based on accuracy, precision, recall, f1-score, specificity, AUC Score, fallout and miss rate. Result: The proposed framework significantly improved classification performance across all algorithms. The Random Forest model emerged as the optimal classifier, achieving an accuracy of 99.44%, AUC Score of 99.98%, and a specific reduction in miss rate to 0.92% (from 10.03% baseline). The HFS method successfully reduced the feature space by 54%, identifying 'ExerciseAngina', 'FastingBS', 'ST_Slope', 'ChestPainType', and 'Sex' as the most critical predictors. The model outperformed standard approaches and recent state-of-the-art benchmarks by over 10% in accuracy. Novelty: This study introduces a synergistic integration of SMOTEENN with hybrid feature selection. The combination significantly improves model performance in early heart disease detection.
AUDIT TATA KELOLA TEKNOLOGI INFORMASI MENGGUNAKAN FRAMEWORK COBIT 5 (STUDI KASUS : DINAS PARIWISATA KABUPATEN LOMBOK TENGAH) Miftahul Jannah; AHMAD FATONI DWI PUTRA; Syahrani Lonang
Breakthroughs In Informatics, Networking, Algorithms, Research, And Yield (BINARY) Vol. 1 No. 1 (2025): Genesis of Innovation in Informatics and Networking
Publisher : Breakthroughs In Informatics, Networking, Algorithms, Research, And Yield (BINARY)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Perkembangan teknologi informasi (TI) yang pesat telah menjadikan TI sebagai faktor penting dalam mendukung operasional dan strategi organisasi, termasuk dalam sektor pemerintahan. Dinas Pariwisata Kabupaten Lombok Tengah memanfaatkan teknologi informasi untuk mengelola promosi digital melalui sistem informasi dan website resmi. Namun, belum optimalnya tata kelola TI serta masih manualnya proses audit menjadi hambatan dalam mendukung efektivitas promosi daerah dan peningkatan pelayanan publik. Penelitian ini menggunakan pendekatan kualitatif deskriptif dengan studi kasus pada bidang Promosi & Pemasaran (PP) di Dinas Pariwisata Kabupaten Lombok Tengah. Kerangka kerja yang digunakan adalah COBIT 5, dengan fokus pada tiga domain utama yaitu APO (Align, Plan, and Organize), DSS (Deliver, Service, and Support), dan MEA (Monitor, Evaluate, and Assess). Tujuan penelitian ini adalah mengevaluasi kapabilitas proses tata kelola TI serta memberikan rekomendasi perbaikan. Hasil penelitian menunjukkan bahwa tingkat kapabilitas proses tata kelola TI secara umum berada pada Level 1.3, dengan gap sebesar 1.7 untuk mencapai target Level 3. Dari ketiga domain yang dianalisis, hanya APO01 yang mencapai Level 2, sedangkan DSS03 dan MEA01 masih berada di Level 1. Rekomendasi yang diberikan meliputi penyusunan dokumen kebijakan formal, penerapan sistem pencatatan insiden, pelatihan teknis bagi SDM, serta penguatan kerja sama dengan vendor melalui kontrak dan indikator kinerja. Secara umum, tata kelola TI di Dinas Pariwisata telah berjalan namun belum sepenuhnya terdokumentasi dan distandarisasi. Peningkatan kapabilitas perlu difokuskan pada aspek dokumentasi, monitoring, serta pengembangan kapasitas SDM untuk mencapai tata kelola yang optimal dan berkelanjutan.
Assessing the Quality of a University SIM Website Through Equivalent Partitioning and System Usability Scale Puspita Rini; Syahrani Lonang; Nuraqilla Waidha Bintang Grendis
Breakthroughs In Informatics, Networking, Algorithms, Research, And Yield (BINARY) Vol. 1 No. 2 (2025): Frontiers of Intelligent Computing and Secure Systems
Publisher : Breakthroughs In Informatics, Networking, Algorithms, Research, And Yield (BINARY)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The System Information Management (SIM) website of Universitas Qamarul Huda Badaruddin BAGU serves as a digital platform designed to support academic and administrative services. This study aims to evaluate the quality of the website by combining functional testing using the Equivalent Partitioning technique and usability assessment through the System Usability Scale (SUS). Functional testing was performed on key features such as the login page, digital library (DILA), user profile, SISKA academic module, and e-money services. The results indicated that the login feature functioned as expected, while several weaknesses were identified in other modules, including the absence of input restrictions in DILA, incomplete validation in profile forms, and insufficient error handling in SISKA and e-money transactions. The usability evaluation involved 80 respondents from various study programs who completed the SUS questionnaire. The analysis yielded an average score of 46.91, corresponding to Grade D, which reflects low usability. While users appreciated the website’s visual appearance and the ease of checking payments via e-money, concerns were raised regarding navigation, error handling, and the effectiveness of learning support features. Overall, the findings suggest that although the MIS website fulfills its basic functions, significant improvements are needed in terms of input validation, interface design, and user experience. This research contributes practical insights for enhancing the reliability and usability of university information systems and provides a foundation for future development aimed at creating more efficient and user-friendly platforms.
Co-Authors Adipta, Marazaenal Afriansyah, M. Ahmad Fatoni Dwi Putra AHMAD FATONI DWI PUTRA Al Habib Anggarista, Randa Anton Yudhana Asno Azzawagama Firdaus B. Talirongan, Florence Jean Dahmani, Abdennasser Danang Tejo Kumoro Desmita, Nindri Lia Dikky Praseptian M Driss, Zied Dwi Normawati, Dwi Faiz Isnan Abdurrachman Furizal, Furizal Herman Herman Imam Riadi Insyroh, Nazaruddin Jayadi, Ahmad Joni Saputra Kumoro, Danang Tejo Kusnayadi, Dedi Satriawan Maulana, Adrian Miftahul Jannah Muhamad Yamin Muhammad Dermawan Mulyodiputro Muhammad Ilham Muhammad Kunta Biddinika Muhammad Kunta Biddinika Nuraqilla Waidha Bintang Grendis Nuraqilla Waidha Bintang Grendis Pratama, Ramadhana Agung Puspita Rini Reski, Julia Mega Sa'adati, Yuan Sharkawy, Abdel-Nasser Sherly da Costa, Apolonia Diana Shoffan Saifullah Syuhada, Fahmi Valian Yoga Pudya Ardhana Yuan Sa'adati