Article Per Year (5 Year)
p-Index From 2021 - 2026
1.285
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Multimedia Jurnal Bumigora Information Technology (BITe) Journal of Information System and Artificial Intelligence SWARNA Jurnal Informatika: Jurnal Pengembangan IT Jurnal Kecerdasan Buatan dan Teknologi Informasi IJIES (International Journal of Innovation in Enterprise System)
Dading Oktaviadi Resmiranta
082144170552
Religion Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
COMPARATIVE ANALYSIS OF RANDOM FOREST AND SUPPORT VECTOR MACHINE FOR FOOD CALORIE LEVEL CLASSIFICATION Dading Oktaviadi Resmiranta; Tanwir; I Gede Yogi Pratama; Naufal Hanif; Azral Satriani; Khairan Marzuki
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 2 (2026): May 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i2.450

Abstract

The rapid escalation of global metabolic health concerns emphasizes the critical urgency for advanced technological solutions that facilitate precise and automated monitoring of daily caloric intake. This research conducts a rigorous comparative analysis to evaluate the predictive performance and computational efficiency of Random Forest (RF) and Support Vector Machine (SVM) algorithms in classifying food calorie levels. The methodology commenced with a comprehensive data preprocessing phase involving multi-strategy missing value imputation and the discretization of caloric values into ordinal categories. Feature selection was meticulously executed using linear regression coefficients to identify high-impact nutritional variables. To ensure a robust evaluation, the dataset was partitioned using an 80:20 ratio for training and testing, complemented by cross-validation to minimize bias and variance. Experimental results indicated that the Random Forest (RF) demonstrated superior classification capabilities, achieving a peak accuracy of 94.8% alongside balanced precision and recall scores. Statistical evaluation via confusion matrices further revealed that Random Forest exhibited enhanced generalization across high-dimensional nutritional features compared to the geometric approach of Support Vector Machine (SVM). Furthermore, the analysis of computational overhead provided critical insights into the real-time deployment feasibility of each model. Ultimately, the findings suggest that the Random Forest serves as a robust engine for personalized dietary management systems, offering a reliable framework for future developments in preventive digital healthcare. By successfully bridging machine learning with nutritional science, this study establishes a benchmark for high-accuracy food classification essential for modern health-centric mobile applications.
Branding and Digital Promotion to Increase Kub Ziae's Competitiveness in the Sembalun Tourism Area Ondi Asroni; Angga Radlisa Samsudin; Dading Oktaviadi Resmiranta; Muhammad Innuddin; Naufal Hanif; Muhammad Tahir
SWARNA: Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 4 (2026): SWARNA : Jurnal Pengabdian Kepada Masyarakat, April, 2026
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi 45 Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/swarna.v5i4.2000

Abstract

KUB ZIAE Sembalun Bumbung is a souvenir center located on the main tourist route of Sembalun, offering products such as black garlic, organic red rice, Rinjani coffee, and dried beans. However, this business faces challenges including weak brand identity, low visibility, and the absence of digital presence. Limited digital literacy among managers also results in reliance on conventional promotion methods. This community service program aimed to enhance KUB ZIAE’s competitiveness through two key strategies: (1) strengthening offline visual identity with signboards, banners, and product labels; and (2) developing digital assets such as Google Business Profile, Instagram, and Facebook accounts, along with content creation training. A participatory approach was applied, including needs assessment, co-design, intensive training, and on-site mentoring. The results showed improved business visibility with the installation of signboards and banners, while new product labels increased consumer trust. On the digital side, the Google Business account successfully appeared in search results, Instagram posts reached hundreds of accounts, and members gained skills in creating and managing promotional content. Although challenges remain, such as limited digital literacy and internet connectivity, the intervention effectively enhanced visibility, expanded market reach, and strengthened KUB ZIAE’s image as a leading souvenir center in the Rinjani tourism area
Optimization of Support Vector Machine Using SMOTE and Grid Search for Kidney Health Data Classification Muhammad Maulana; Zulkipli Zulkipli; Tanwir Tanwir; Dading Oktaviadi Resmiranta; Naufal Hanif; Raisul Azhar
Jurnal Teknologi Informasi dan Multimedia Vol. 8 No. 2 (2026): May
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v8i2.993

Abstract

Kidney disease is a highly prevalent health problem that can seriously impact the quality of life of those affected. To improve diagnostic accuracy, machine learning methods are widely used to classify patient data. Class imbalance (imbalanced data) is one of the problems that often occurs in the classification process and can affect the performance of machine learning models, especially in detecting minority classes. This study aims to improve the performance of the Support Vector Machine (SVM) algorithm by applying the SMOTE (Synthetic Minority Over-sampling Tech-nique) and Grid Search methods in the data classification process. SMOTE is used to balance the class distribution by adding synthetic data to the minority class, while Grid Search is used to ob-tain optimal model parameters. The results show that the SVM model without handling data im-balance produces relatively low performance with an accuracy value of 51%, precision 17%, re-call 33%, and F1-score 23%. After applying the SMOTE method, the model performance increases significantly to 81% accuracy, 81% precision, 80% recall, and 81% F1-score. Furthermore, the ap-plication of Grid Search to the SVM + SMOTE model provides the best results with an accuracy of 84%, precision 82%, recall 81%, and F1-score 81% with an AUC value of 0,92. The findings of this study indicate that the combination of SMOTE and Grid Search is effective in improving the per-formance of the SVM algorithm in data classification. The novelty of this study demonstrates that data imbalance management and hyperparameter optimization play a crucial role in producing more accurate and optimal classification models.
Pengenalan Citra Wajah Menggunakan Model Hybrid Filtering dan Convolutional Neural Networks (CNN): Pengenalan Citra Wajah Menggunakan Model Hybrid Filtering dan Convolutional Neural Networks (CNN) Dading Oktaviadi Resmiranta; Bambang Krismono; Khasnur Hidjah
Journal of Information System and Artificial Intelligence Vol. 6 No. 1 (2025): Vol. 6 No.1(2025): Journal of Information System and Artificial Intelligence Vo
Publisher : Universitas Mercu Buana Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26486/jisai.v6i1.271

Abstract

The face is an important object in the biometric identification system. However, low image quality due to uneven lighting, noise, and variations in facial expressions can interfere with the accuracy of the recognition system. The study investigated the use of Convolutional Artificial Neural Network (CNN) combined with hybrid screening techniques to improve image quality, thereby improving the accuracy of facial recognition systems. Filters used include weight mean filtering, median filtering, Contrast-Limited Adaptive Histogram Equalization and gaussian filtering, wavelet filtering. The pre-processed image was then trained using image denoising measurements of the Structural Similarity Index, Mean Squared Error, and Peak Signal to Noise Ratio. The main objective of this study is to evaluate the best filtration combination to produce high accuracy in face classification. The datasets used were 55 classes and 100 images per class. The inceptionV3 architecture model is used for classifications with a number of epochs of 10. Evaluation was carried out on a facial data set with an 80%:20% scheme. The results of the experiment showed that the hybrid method produced the best performance with 94.5% validation accuracy, 94.2% precision, and 94.6% recall, an increase of +1.4% compared to baseline. The (original) baseline itself recorded 93.1% validation accuracy, 92.8% precision, and 93.2% recall. In addition, the loss graph shows that the pre-process model has faster and more stable convergence than the non-pre-processing model. These results confirm that the application of preprocessing, especially the hybrid approach, is able to improve the accuracy and stability of the model in image classification tasks.
Peningkatan Kinerja Klasifikasi Scabies Sapi MenggunakanEdited Nearest Neighbours (ENN) pada Model Random Forestdan XGBoost M. Khaerul Ihsan; Muhammad Maulana; Tanwir Tanwir; Abi Mas’ud; Naufal Hanif; Dading Oktaviadi Resmiranta
Jurnal Bumigora Information Technology (BITe) Vol. 7 No. 2 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v7i2.6055

Abstract

Background: Scabies disease in cattle causes significant economic losses for farmers due to declines in the animals’physical condition and productivity.Objective: This study aims to evaluate the effectiveness of the Edited Nearest Neighbours (ENN) method in improvingclassification performance for scabies in cattle.Methods: This research employs machine learning methods, including Random Forest and XGBoost. A dataset of 600clinical symptom samples was converted to numerical data and cleaned of noise using the ENN technique.Result: Applying ENN significantly improved the accuracy of both the Random Forest and XGBoost models, increasing itfrom around 0.60 to 0.91. In addition, both models achieved a perfect recall of 1.00, indicating maximum capability todetect positive cases.Conclusion: This study concludes that noise reduction using ENN can produce a more accurate and reliable diagnosticsystem. This method is highly recommended to optimize the performance of classification algorithms on animal clinicaldata with high levels of inconsistency. 
Implementation Anti-Fraud Security on Smart Campus Attendance System Using Face Recognition Liveness Detection and Anti-Fake GPS Geofencing Azral Satrani; Tanwir Tanwir; Dading Oktaviadi Resminanta; Muhammad Maulana; Kartarina Augustin; Gede Yogi Pratama
Jurnal Teknologi Informasi dan Multimedia Vol. 8 No. 3 (2026): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v8i3.1057

Abstract

In the digital era, the fingerprint-based attendance system used by University of Bumigora where considered ineffective and inefficient due to hygiene issues, physical vulnerability, the risk of for-gery, and slow processing speed during peak hours. In addition, as the digital attendance system develops, new challenges arise in the form of biometric data manipulation through presentation attacks (photos/videos/masks) and location manipulation using fake GPS applications. This dual vulnerability is a critical issue that can damage data integrity and the governance of educational institutions. To address these issues, this study proposes the design and development of a Smart Campus attendance system that integrates two anti-fraud security mechanisms, namely Face Recognition liveness  detection and Anti-Fake GPS Geofencing. Liveness Detection technology functions to detect real-life signs to distinguish real faces from fake representations, while An-ti-Fake GPS validates the signal consistency and physicality of users within a predetermined campus geographic radius (geofence). This system was developed using Agile methods to ensure adaptive and structured development. From a technological perspective, this system integrates the Vue JS framework in the user interface (UI) due to its robust performance, and the Laravel frame-work in the backend due to its advantages in Model-View-Controller (MVC) architecture, security, and high scalability. Through this approach, the study aims to evaluate the effectiveness of a lay-ered anti-fraud mechanism in preventing fraud and measure improvements in administrative effi-ciency compared to conventional fingerprint systems.
Implementation of Auto-Scaling and Load Balancing on Proxmox VE Using Python and REST API Naufal Hanif; Dading Oktaviadi Resmiranta; M. Khaerul Ihsan; Tanwir Tanwir; I Putu Hariyadi; Ondi Asroni
IJIES (International Journal of Innovation in Enterprise System) Vol 10 No 2 (2026): International Journal of Innovation in Enterprise System - Article in Press
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/ijies.v10i02.10429

Abstract

Auto-scaling and load balancing are essential for maintaining web service availability and performance under fluctuating workloads. This research implements an automated auto-scaling and load balancing system on Proxmox Virtual Environment (Proxmox VE) leveraging Proxmox REST API through Python scripts. The system monitors web container CPU usage at 5-second intervals, triggering scale-out by cloning LXC containers when average CPU exceeds 75% and scale-in when it falls below 30%, while ensuring at least one container remains active. Testing on a laboratory topology consisting of 1 template container, 1 load balancer, and 4 backend containers (IP range: 192.168.100.251-192.168.100.254) demonstrates average provisioning time of 96.0 seconds (range: 85.5-117.7s) with breakdown: API Clone (82.4s), Network Config (0.0s), Container Start (6.8s), Content Customization (3.1s), and Load Balancer Update (3.6s). Comparative analysis between always-on (4 containers) and auto-scaling scenarios reveals 36.1% CPU savings (31.66 vs 49.57 CPU-hours), idle time reduction from 54.2% to 28.3%, and efficient resource utilization with the system operating predominantly on 1 container (85% uptime). This implementation proves that Proxmox API integration with Python-based automation provides a practical auto-scaling solution for private clouds without complex orchestration platforms like Kubernetes.
Analisis Komparasi Kinerja Arsitektur MobileNetV3 dan EfficientNet-Lite untuk Klasifikasi Penyakit Padi pada Citra Resolusi Rendah Dading Oktaviadi Resmiranta
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10098

Abstract

National food security relies heavily on rapid and accurate control of rice plant diseases. However, the implementation of automatic detection technology at the farmer level is often hampered by low image quality due to the use of low-spec mobile phone cameras and data compression in areas with poor signal. This study aims to evaluate the performance of two lightweight Deep Learning architectures, MobileNetV3-Small and EfficientNet-Lite, in classifying rice diseases under low-resolution image conditions. The research method applies a simulation of resolution degradation to 128x128 pixels on a dataset consisting of four classes: Blast, Blight, Brown Spot, and Healthy. Empirical test results show that EfficientNet-Lite is significantly superior in diagnostic accuracy with an accuracy of 95.67%, a precision of 95.65%, and a recall of 95.33%. In contrast, MobileNetV3-Small achieved an accuracy of 89.00%, yet offered superior computational efficiency: a model size of only 11.97 MB (73% smaller than EfficientNet-Lite's 45.48 MB) and an inference speed of 4.67 milliseconds per image, equivalent to 214 frames per second (FPS). The study concluded that EfficientNet-Lite is recommended for high-precision diagnostic systems, while MobileNetV3-Small is the most adaptive solution for real-time applications on storage-constrained mobile devices.
Co-Authors Abi Mas’ud Angga Radlisa Samsudin Azhar, Raisul Azral Satrani Azral Satriani Bambang Krismono Gede Yogi Pratama I Gede Yogi Pratama I Putu Hariyadi Kartarina Augustin Khairan marzuki Khasnur Hidjah M. Khaerul Ihsan M. Khaerul Ihsan Muhammad Innuddin Muhammad Maulana Muhammad Tahir Naufal Hanif Ondi Asroni Tanwir Tanwir Tanwir Tanwir Tanwir Tanwir Tanwir Tanwir Tanwir Zulkipli Zulkipli