Article Per Year (5 Year)
p-Index From 2021 - 2026
6.334
P-Index
This Author published in this journals
All Journal Bulletin of Electrical Engineering and Informatics Sinkron : Jurnal dan Penelitian Teknik Informatika International Journal of Artificial Intelligence Research Jurnal Teknik Informatika UNIKA Santo Thomas Jurnal Nasional Komputasi dan Teknologi Informasi J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Mantik Jusikom: Jurnal Sistem Informasi Ilmu Komputer Jurnal Sains dan Teknologi TRIDARMA: Pengabdian Kepada Masyarakat (PkM) Jurnal Teknik Informatika C.I.T. Medicom Journal of Intelligent Decision Support System (IDSS) INFOKUM Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Jurnal Sistem Informasi dan Teknologi Jaringan International Journal of Basic and Applied Science Jurnal Media Informatika J-SAKTI (Jurnal Sains Komputer dan Informatika) DISTANCE: Journal of Data Science, Technology, and Computer Science Jurnal Mandiri IT Jurnal Teknik Informatika Unika Santo Thomas (JTIUST) Jurnal Sistem Informasi Galuh Jurnal Ilmu Pendidikan dan Humaniora Jurnal Pengabdian Masyarakat Nauli Journal of Defense Technology and Engineering
Manurung, Jonson
Universitas Pertahanan Republik Indonesia, Bogor, Indonesia
Aerospace Engineering Arts Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering 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 Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Neuroscience Physics Social Sciences Transportation

Published : 49 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 49 Documents
Search

 1   2   3   4   5 
Optimization of quicksort algorithm for real-time data processing in IoT systems with random pivot division and tail recursion Laia, Firdaus; Wau, Ferdinand Tharorogo; Manurung, Jonson
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.401

Abstract

Real-time data processing in Internet of Things (IoT) systems requires efficient sorting algorithms to handle large and ever-increasing volumes of data. The QuickSort algorithm is often used due to its speed and efficiency, but on large pre-sorted datasets, this algorithm can experience performance degradation due to poor pivot selection and the use of regular recursion. This study aims to optimize the QuickSort algorithm through random pivot selection and the application of tail recursion to improve sorting efficiency on IoT datasets. Experiments were conducted by comparing the standard QuickSort version and the optimized version, using synthetic and real-time IoT datasets from temperature and humidity sensors. Performance evaluation was based on execution time and memory usage metrics. The results show that QuickSort with random pivot and tail recursion can reduce execution time by up to 27% and memory usage by up to 18% compared to the standard QuickSort implementation. These findings indicate that the proposed algorithm is more efficient for IoT applications that require real-time data processing, and has the potential to be applied in distributed data systems and parallel processing for large-scale scenarios.
Optimizing the performance of the K-Nearest Neighbors algorithm using grid search and feature scaling to improve data classification accuracy Manurung, Jonson; Saragih, Hondor; Prabukusumo, Muhammad Azhar; Firdaus, Eryan Ahmad
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.466

Abstract

The performance of distance-based classification algorithms such as K-Nearest Neighbors (KNN) is highly dependent on proper feature scaling and optimal parameter selection. Without systematic optimization, KNN may experience decreased accuracy due to feature scale disparities and suboptimal k-values. This study aims to enhance the performance of the KNN algorithm through the integration of Feature Scaling and Grid Search Cross-Validation as a parameter optimization strategy. The research employs the Breast Cancer Wisconsin Dataset, divided into 80% training and 20% testing data. Feature normalization was performed using StandardScaler, while Grid Search was applied to determine the optimal combination of parameters, including the number of neighbors (k), weighting function (weights), and distance metric (metric). The optimized KNN configuration with k = 9, weights = distance, and metric = manhattan achieved an average accuracy of 97.19%, outperforming the baseline accuracy of 93.86%. A paired t-test confirmed that the improvement was statistically significant (p < 0.05). These findings demonstrate that the synergy between feature scaling and parameter tuning can substantially improve both the accuracy and stability of KNN models. The scientific novelty of this study lies in the systematic integration of normalization and parameter optimization through Grid Search, providing an empirical framework that enhances KNN’s robustness across datasets with heterogeneous feature distributions. The proposed approach is recommended for medical data classification and can be adapted to other domains with heterogeneous numerical feature distributions.
Optimization of XGBoost hyperparameters using grid search and random search for credit card default prediction Firdaus, Eryan Ahmad; Manurung, Jonson; Saragih, Hondor; Prabukusumo, Muhammad Azhar
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.468

Abstract

This study explores the optimization of the Extreme Gradient Boosting (XGBoost) algorithm for credit card default prediction through systematic hyperparameter tuning using Grid Search and Random Search methodologies. Utilizing the publicly available Default of Credit Card Clients dataset from the UCI Machine Learning Repository, the research focuses on enhancing model performance by fine-tuning critical parameters such as learning rate, maximum tree depth, number of estimators, subsample ratio, and column sampling rate. The baseline XGBoost model achieved an accuracy of 0.8118, while the tuned models using Grid Search and Random Search improved the accuracy to 0.8183 and 0.8188, respectively. Although the improvement appears modest, the optimized models exhibited enhanced balance between precision and recall, particularly in identifying defaulters within an imbalanced dataset—an essential aspect in credit risk assessment. The results demonstrate that systematic hyperparameter optimization not only improves predictive performance but also contributes to model stability and generalization. Moreover, Random Search proved to be more computationally efficient, achieving near-optimal performance with fewer evaluations than Grid Search, thereby emphasizing its practicality for large-scale financial risk modeling applications. The novelty of this study lies in the comparative evaluation of two optimization techniques within the context of financial risk prediction, providing practical insights into how efficient hyperparameter tuning can enhance the reliability and scalability of machine learning models used in real-world credit risk management systems.
Hyperparameter optimization of graph neural networks for predicting complex network dynamics using bayesian meta-learning Saragih, Hondor; Manurung, Jonson; Prabukusumo, Muhammad Azhar; Firdaus, Eryan Ahmad
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.469

Abstract

The rapid growth of graph-structured data in domains such as transportation, social networks, and biological systems has increased the demand for more adaptive and efficient Graph Neural Network (GNN) architectures. However, GNN performance remains highly sensitive to hyperparameter configurations, which are often tuned through computationally expensive manual or heuristic methods. This study proposes a novel Bayesian Meta-Learning (BML)-based framework for hyperparameter optimization of GNNs aimed at improving the prediction accuracy of complex network dynamics. The framework integrates Bayesian optimization with a meta-learning prior adaptation mechanism, enabling the model to learn optimal hyperparameter distributions across multiple graph tasks. Experimental evaluations conducted on three benchmark datasets—Cora, Citeseer, and PubMed—comprising up to 20,000 nodes with diverse structural complexities, demonstrate that the proposed BML-GNN framework achieves faster convergence, lower validation loss, and higher predictive accuracy than both baseline GNN and traditional Bayesian Optimization approaches. Quantitatively, the BML-GNN model attains an R² score exceeding 0.97 with a significant reduction in RMSE, confirming its strong generalization capability. Although the method shows notable performance improvements, its computational overhead during meta-training and reliance on well-defined prior distributions represent potential limitations. Overall, the integration of Bayesian Meta-Learning provides a robust, scalable, and uncertainty-aware optimization strategy that advances the development of reliable GNN models for complex network modeling and intelligent system design.
Swarm driven automatic feature selection and classification framework for parkinson voice data Prabukusumo, Muhammad Azhar; Saragih, Hondor; Manurung, Jonson
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.470

Abstract

Parkinson’s disease (PD) severely impairs motor and vocal functions, and early detection is crucial for effective intervention. Conventional diagnostic procedures remain subjective and time-consuming, highlighting the need for automated, data-driven approaches. This study aims to develop an intelligent and fully automated framework integrating Particle Swarm Optimization (PSO)–based feature selection with ensemble machine learning classifiers for PD detection using voice data. The proposed Swarm-Driven Automatic Feature Selection and Classification Framework (SAFSCF) automates data preprocessing, adaptive feature optimization, and classification within a unified pipeline. The framework was evaluated on the Parkinson’s Speech Dataset comprising 743 numerical features. Baseline models achieved accuracies of 0.7738 (Logistic Regression), 0.8651 (Random Forest), and 0.8690 (Gradient Boosting). After PSO optimization, the feature set was reduced by nearly 50% to 382 attributes, achieving a test accuracy of 0.8421 slightly higher than the full-feature model (0.8355). Convergence plots confirmed that PSO effectively minimized the fitness function while maintaining high classification stability. Feature importance analysis revealed that the most discriminative attributes were derived from log energy, Teager Kaiser energy operators (TKEO), MFCCs, Shimmer, and entropy-based features biomarkers known to reflect Parkinsonian speech degradation. These findings demonstrate that the proposed framework enhances computational efficiency and interpretability, offering a reproducible and scalable solution for non-invasive, voice-based PD diagnosis.
Pelatihan dan Demonstrasi Antena Satelit bagi Pramuka Penegak untuk Komunikasi Tanggap Bencana di Kabupaten Pandeglang Provinsi Banten dalam Kegiatan Latsitardanus XLV Tahun 2025 Ahmad Firdaus, Eryan; Manurung, Jonson; Prabukusumo, Muhammad Azhar; Nuriansyah, Agam; Dhaifullah, Rendi Hanif
Jurnal Pengabdian Masyarakat Nauli Vol. 4 No. 1 (2025): Agustus, Jurnal Pengabdian Masyarakat Nauli
Publisher : Marcha Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/nauli.v4i1.234

Abstract

Kegiatan Latihan Integrasi Taruna Wreda Nusantara (Latsitardanus) XLV tahun 2025 di Provinsi Banten merupakan wadah pengabdian masyarakat yang berfokus pada peningkatan kapasitas generasi muda. Salah satu program yang dilaksanakan adalah pelatihan dan demonstrasi penggunaan antena satelit yang ditujukan bagi Pramuka Penegak di Kabupaten Pandeglang. Program ini bertujuan untuk membekali para anggota Pramuka dengan keterampilan komunikasi tanggap bencana, mengingat pentingnya akses komunikasi yang andal di daerah yang memiliki potensi rawan bencana. Pelatihan ini mencakup pengenalan dasar teknologi antena satelit, prosedur operasional, serta simulasi komunikasi dalam skenario darurat. Melalui demonstrasi langsung, peserta diberikan pemahaman praktis mengenai cara mendirikan dan mengoperasikan perangkat komunikasi satelit. Diharapkan, setelah mengikuti kegiatan ini, Pramuka Penegak dapat berperan aktif sebagai ujung tombak dalam sistem komunikasi darurat, baik untuk mengkoordinasikan bantuan maupun menyampaikan informasi penting saat infrastruktur komunikasi konvensional tidak berfungsi. Program ini menjadi kontribusi nyata Latsitardanus XLV/2025 dalam menciptakan kader-kader muda yang kompeten, tanggap, dan siap siaga untuk membantu masyarakat di lingkungan sekitar.
Best Cluster Optimization with Combination of K-Means Algorithm And Elbow Method Towards Rice Production Status Determination Hasugian, Paska Marto; Sinaga, Bosker; Manurung, Jonson; Al Hashim, Safa Ayoub
International Journal of Artificial Intelligence Research Vol 5, No 1 (2021): June 2021
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.292 KB) | DOI: 10.29099/ijair.v6i1.232

Abstract

Indonesia is the third-largest country in the world with rice production reaching 83,037,000 and became the highest production in southeast Asia spread in several provinces in Indonesia The problem found that such product has not been able to cover the needs of Indonesian people with a very high population so that in the research conducted information excavation to generate potential to the pile of data that has been described and analyzed by BPS with clustering topics. Clustering will help related parties, especially the ministry of agriculture, in determining land development priorities and can minimize the shortage of rice production nationally. Grouping process by involving the K-means algorithm to group rice production with a combination of the elbow method as part of determining the number of clusters that will be recommended with attributes supporting the area of harvest, productivity, and production. Method of researching with data cleaning activities, data integration, data transformation, and application of K-means with a combination of elbow and pattern evaluation. The results achieved based on the work description with a combination of K-Means and elbow provide cluster recommendations that are the best choice or the most optimal is iteration 2 which is the lowest rice production group with a total of 22 provinces, rice production with a medium category of 9 and production with the highest category with 3 regions
Implementation of gaming In the cloud through construct engine applications on heroku infrastructure Phatoni, Khaerul Imam; Adha, Rochedi Idul; Manurung, Jonson; Prabukusumo, M Azhar; Piliang, Rizqullah Aryaputra; Nasyira, Muhammad Sulthan
Jurnal Mandiri IT Vol. 14 No. 3 (2026): Jan: Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i3.478

Abstract

This study presents a performance analysis of real-time multiplayer gaming through web-based game engines deployed on cloud Platform-as-a-Service infrastructure, specifically examining Construct 3 integration with Heroku's managed deployment platform. A multiplayer Pong game was developed to evaluate the viability of browser-based gaming architectures for real-time applications, utilizing WebSocket communication protocols, room-based session management, and hybrid client-server prediction models. The implementation demonstrates five architectural components: secure WebSocket connection establishment, 60 frames-per-second server-side game state synchronization, minimal cloud deployment configuration, scalable room management supporting multiple concurrent sessions, and responsive input handling with client-side prediction. Performance evaluation with ten concurrent game instances revealed exceptional resource efficiency, consuming maximum 34 megabytes memory with dyno load averages of 0.01, validating JavaScript-based server implementations for real-time gaming applications. The results indicate that web-based game engines can achieve performance characteristics traditionally associated with dedicated server architectures while maintaining significant advantages in development velocity, deployment simplicity, and operational efficiency. The study contributes evidence supporting the democratization of multiplayer game development through accessible web technologies, demonstrating that traditional barriers between browser-based and native gaming applications are diminishing as platform capabilities mature. These findings establish benchmarks for web-based multiplayer gaming performance and provide foundation for future research in cloud-based game development paradigms.
Energy consumption prediction and optimization for Ki Hajar Dewantara student dormitory Using Extreme Gradient Boosting (XGBoost) algorithm Sinaga, Jeremia; Manurung, Jonson; Prabukusumo, M. Azhar
Jurnal Mandiri IT Vol. 14 No. 3 (2026): Jan: Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i3.482

Abstract

Energy consumption optimization in student dormitories requires accurate prediction and strategic intervention strategies. This study presents a comprehensive prediction and optimization system for energy usage at Ki Hajar Dewantara Student Dormitory, Indonesia Defense University, utilizing Extreme Gradient Boosting (XGBoost) algorithm integrated with temporal operational scheduling features a novel approach for institutional dormitory energy forecasting. The system analyzes over 3,900 electrical devices across three dormitory buildings, incorporating temporal features and operational schedules to predict hourly energy consumption. The XGBoost model demonstrates excellent prediction performance with R² = 0.9482 and MAPE = 10.24%, significantly exceeding established benchmarks for building energy forecasting. Feature importance analysis reveals working hours as the dominant factor (>85%) influencing consumption patterns, followed by occupancy rate and temperature. The analysis identifies air conditioning systems as the primary energy consumer, accounting for over 80% of total consumption. The optimization framework identifies potential energy savings of approximately 28% through strategic device replacement and schedule modifications, translating to annual cost savings of over Rp 600 million with economically viable return on investment periods. This machine learning-based approach demonstrates practical applicability for student dormitory energy management and provides a replicable methodology adaptable to diverse residential institutional buildings in tropical climates.
Decision-making model for cadet selection using the AHP TOPSIS method Tsany, Tazky; Manurung, Jonson; Prabukusumo, M. Azhar
Jurnal Mandiri IT Vol. 14 No. 3 (2026): Jan: Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i3.486

Abstract

Cadet selection in defense institutions requires a comprehensive assessment process because it must cover the academic, psychological, health, physical, and ideological integrity aspects of prospective participants. This multidimensional complexity poses challenges in producing decisions that are objective, consistent, and free from assessor bias. Therefore, a quantitative approach-based evaluation model is needed that can integrate all assessment components in a measurable manner. This study developed a cadet selection decision-making model using a combination of the Analytical Hierarchy Process (AHP) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) methods. AHP is used to determine the weight of importance of the seven main criteria: Academic Potential Test, Academic Interview, Psychological Test, Ideological Mental Test, Ideological Mental Interview, Health Test, and Physical Test, while TOPSIS is used to determine the ranking of candidates based on their proximity to the ideal profile of a cadet. The results of the study show that the integration of AHP–TOPSIS is able to provide evaluation results that are more objective, transparent, and accountable than conventional assessments. In addition to formulating a selection model, this study also discusses alternative methods in multi-criteria decision making as material for developing a selection system in the future. Overall, this model is expected to become a scientific basis for defense institutions in improving the quality and accuracy of the cadet selection process.
Co-Authors Adam Mardamsyah Adha, Rochedi Idul Agus Firmansyah Agustina Simangunsong Al Hashim, Safa Ayoub Amran Sitohang Andri Budiman, Mohammad anindito anindito Bagus Hendra Saputra Bagus Hendra Saputra Barus, Nadela Bosker Sinaga Bosker Sinaga Bosker Sinaga, Bosker Sinaga Br Sitepu, Siska Feronika Br Tarigan, Nera Mayana Dhaifullah, Rendi Hanif Erika Novianti Eryan Ahmad Firdaus Febrian Wahyu Christanto Ferdinand Tharorogo Wau Firdaus Laia Firdaus Situmorang Frainskoy Rio Naibaho Hanan, Rohman Ali Hardy Priyatno Ambarita Harpingka Sibarani Hasugian , Paska Marto Hengki Tamando Sihotang Hidayati, Ajeng Hoga Saragih Hondor Saragih I Made Aditya Pradhana Putra Jeremia Paskah Sinaga Johanes Perdamenta Sembiring Kadin Darlianto Tinambunan Kanur L. P. Situmorang Logaraj Logaraj Logaraj, Logaraj M Azhar Prabukusumo Mardamsyah, Adam Maria Siahaan Maya Theresia Br. Barus Maya Theresia Br. Barus Merlin Helentina Napitupulu Mina Kumari Mohammad Andri Budiman Muhammad Azhar Prabukusumo Muthmainnah, Ihmatull Nasyira, Muhammad Sulthan Nick Holson M. Silalahi Nuriansyah, Agam Pandiangan, Boyner Phatoni, Khaerul Imam Piliang, Rizqullah Aryaputra Poltak Sihombing Prabukusumo, M Azhar Prabukusumo, M. Azhar Prabukusumo Prabukusumo, Muhammad Azhar Pradhana Putra, I Made Aditya Putra, Muhammad Ridho Alghifari Ramen, Sethu Rinaldy Chaniago Sawaluddin Sawaluddin, Sawaluddin Sethu Ramen Sethu Ramen, Sethu Ramen Sidiq, Maulana Sigalingging, Miranda Bintang Maharani Sihombing, Agus Putra Emas Sihotang, Amran Silalahi, Monalisa Hotmauli Simangunsong, Humala Sinaga, Jeremia Sinaga, Jeremia Paska Sinaga, Ryan Fahlepy Sri Kumala Sari Tsany, Tazky Uzitha Ram Vernando, Deden