Hartono Hartono
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hartono Hartono has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Khahfi Zuhanda
Universitas Medan Area
5 shared publications - Rahmad B. Y. Syah
Universitas Medan Area
3 shared publications - Sayuti Rahman
Universitas Medan Area
3 shared publications - Muhammad Khahfi Zuhanda
Universitas Medan Area
2 shared publications - Prana Ugiana Gio
Universitas Sumatera Utara
2 shared publications - Samsul Abdul Rahman Sidik Hasibuan
Universitas Medan Area
2 shared publications
Latest Publications
- Open Access
- 31 August 2026
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 12 (3) , 911-924
A hybrid oversampling for imbalanced data using incremental SMOTE-KMeans and cluster-structured positive class-SVM
Class imbalance remains a significant challenge in classification tasks, particularly when the minority class exhibits complex internal structures. This study proposes a unified framework that integrates Incremental SMOTE-KMeans with a cluster-structured positive class-SVM (CS-PC-SVM) to jointly address data imbalance and structural heterogeneity. The proposed method introduces structural alignment between oversampling and classification by generating synthetic samples only within reliable clusters and modeling the minority class as multiple subgroups. This design reduces noise, preserves local data structure, and enables more adaptive decision boundaries. Experimental results on five benchmark datasets demonstrate that the proposed approach achieves consistently strong and balanced performance, with Accuracy up to 0.981, G-Mean 0.969, Precision 0.967, and Recall 0.962, outperforming or remaining competitive with existing methods. These findings highlight the effectiveness of integrating structure-guided data generation with structure-aware classification for improving robustness in imbalanced learning scenarios.
- 31 August 2026
- Published by Universitas Ahmad Dahlan in International Journal of Advances in Intelligent Informatics
- Vol. 12 (3) , 911-924
Open AccessA hybrid oversampling for imbalanced data using incremental SMOTE-KMeans and cluster-structured positive class-SVM
Class imbalance remains a significant challenge in classification tasks, particularly when the minority class exhibits complex internal structures. This study proposes a unified framework that integrates Incremental SMOTE-KMeans with a cluster-structured positive class-SVM (CS-PC-SVM) to jointly address data imbalance and structural heterogeneity. The proposed method introduces structural alignment between oversampling and classification by generating synthetic samples only within reliable clusters and modeling the minority class as multiple subgroups. This design reduces noise, preserves local data structure, and enables more adaptive decision boundaries. Experimental results on five benchmark datasets demonstrate that the proposed approach achieves consistently strong and balanced performance, with Accuracy up to 0.981, G-Mean 0.969, Precision 0.967, and Recall 0.962, outperforming or remaining competitive with existing methods. These findings highlight the effectiveness of integrating structure-guided data generation with structure-aware classification for improving robustness in imbalanced learning scenarios.
- Open Access
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (3) , 2406-2416
Metaheuristic nurse scheduling with hospital clustering using flower pollination algorithm
Effective nurse scheduling is essential to ensure balanced workloads, reduce fatigue, and maintain healthcare service quality. However, the nurse scheduling problem (NSP) is complex due to constraints related to nurse skills, task requirements, and legal working-hour limits. This study proposes an integrated framework combining a mathematical optimization model with metaheuristic algorithms to generate optimal daily nurse activity schedules. Genetic algorithm (GA) and simulated annealing (SA) are employed to produce near-optimal solutions for nurse populations ranging from 3 to 50 individuals, considering skill-level compatibility, workload balance, and maximum working hours. Experimental results using real scheduling data from 30 nurses across three skill levels demonstrate that all generated schedules satisfy the imposed constraints, with no nurse exceeding the 12hour daily working limit. Comparative analysis shows that GA achieves lower scheduling costs for larger nurse populations, while SA consistently requires significantly shorter computation times, making it suitable for time-sensitive applications. In addition, the flower pollination algorithm (FPA) is used to cluster 3,155 hospitals based on bed capacity, service variety, and workforce size, supporting data-driven workforce distribution analysis. The proposed framework integrates operational scheduling optimization with hospital-level clustering, providing practical decision support for healthcare workforce planning.
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (3) , 2406-2416
Open AccessMetaheuristic nurse scheduling with hospital clustering using flower pollination algorithm
Effective nurse scheduling is essential to ensure balanced workloads, reduce fatigue, and maintain healthcare service quality. However, the nurse scheduling problem (NSP) is complex due to constraints related to nurse skills, task requirements, and legal working-hour limits. This study proposes an integrated framework combining a mathematical optimization model with metaheuristic algorithms to generate optimal daily nurse activity schedules. Genetic algorithm (GA) and simulated annealing (SA) are employed to produce near-optimal solutions for nurse populations ranging from 3 to 50 individuals, considering skill-level compatibility, workload balance, and maximum working hours. Experimental results using real scheduling data from 30 nurses across three skill levels demonstrate that all generated schedules satisfy the imposed constraints, with no nurse exceeding the 12hour daily working limit. Comparative analysis shows that GA achieves lower scheduling costs for larger nurse populations, while SA consistently requires significantly shorter computation times, making it suitable for time-sensitive applications. In addition, the flower pollination algorithm (FPA) is used to cluster 3,155 hospitals based on bed capacity, service variety, and workforce size, supporting data-driven workforce distribution analysis. The proposed framework integrates operational scheduling optimization with hospital-level clustering, providing practical decision support for healthcare workforce planning.
- Open Access
- 6 September 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 16
An adaptive clustering framework for personality prediction using enhanced seed optimization
- 6 September 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 16
Open AccessAn adaptive clustering framework for personality prediction using enhanced seed optimization
- Open Access
- 18 August 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 16
An evolutionary analytics model for enhancing food distribution through two-tier routing
- 18 August 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 16
Open AccessAn evolutionary analytics model for enhancing food distribution through two-tier routing
- Open Access
- 15 August 2025
- Published by Universitas Muhammadiyah Palangkaraya in PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
- Vol. 10 (8) , 1869-1879
Pemanfaatan Limbah Organik untuk Pakan Ikan Berbasis Serangga BSF di Desa Marindal II
This community service activity addresses two main issues in Marindal II Village, Patumbak Subdistrict, Deli Serdang Regency, North Sumatra Province: the high volume of organic waste and the need for fish feed production technology. The partner is a Women Farmers Group that manages chicken farming, goldfish and tilapia cultivation, and a banana plantation. Organic waste, particularly chicken manure, will be used as a medium for cultivating Black Soldier Fly (BSF) larvae, which produce maggots as fish feed. In addition to chicken manure, other waste such as vegetables, fruits, and kitchen scraps are also utilized. However, maggots alone are insufficient to meet the fish's nutritional needs, so an additional feed composition in pellets is required. Pellets are essential to prevent fish from being selective in their diet, thus ensuring their dietary needs are met. The community service team conducted awareness activities on waste utilization and nutritious pellet production for the partner and the community to promote the use of waste and prevent environmental pollution.
- 15 August 2025
- Published by Universitas Muhammadiyah Palangkaraya in PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
- Vol. 10 (8) , 1869-1879
Open AccessPemanfaatan Limbah Organik untuk Pakan Ikan Berbasis Serangga BSF di Desa Marindal II
This community service activity addresses two main issues in Marindal II Village, Patumbak Subdistrict, Deli Serdang Regency, North Sumatra Province: the high volume of organic waste and the need for fish feed production technology. The partner is a Women Farmers Group that manages chicken farming, goldfish and tilapia cultivation, and a banana plantation. Organic waste, particularly chicken manure, will be used as a medium for cultivating Black Soldier Fly (BSF) larvae, which produce maggots as fish feed. In addition to chicken manure, other waste such as vegetables, fruits, and kitchen scraps are also utilized. However, maggots alone are insufficient to meet the fish's nutritional needs, so an additional feed composition in pellets is required. Pellets are essential to prevent fish from being selective in their diet, thus ensuring their dietary needs are met. The community service team conducted awareness activities on waste utilization and nutritious pellet production for the partner and the community to promote the use of waste and prevent environmental pollution.
- Open Access
- 26 June 2025
- Published by Jurnal TIMES, STMIK TIME in Jurnal TIMES
- Vol. 14 (1) , 60-69
IMPROVING CYBERSECURITY TRAFFIC ANALYSIS VIA ENHANCED K-MEANS CLUSTERING WITH TRIANGLE INEQUALITY-BASED INITIALIZATION
Clustering algorithms are essential in data mining and pattern recognition for grouping unlabeled data into meaningful clusters based on similarities. Among them, K-Means is widely used due to its simplicity and efficiency but suffers from sensitivity to initial centroid selection and inability to capture feature dependencies. This study proposes an Enhanced Mutual Information-based K-Means (MIK-Means) algorithm combined with Triangle Inequality and Lower Bound (TILB) seeding to improve clustering accuracy and computational efficiency, particularly in the context of network traffic classification for cybersecurity applications. The TILB method accelerates the initialization phase by reducing redundant distance calculations using mathematical pruning techniques, thereby selecting well-distributed initial centroids efficiently. Meanwhile, MIK-Means incorporates mutual information as a similarity measure during clustering assignment, enabling the algorithm to capture complex statistical dependencies among features, which traditional Euclidean distance metrics fail to address. The combination of these two approaches results in a robust clustering framework capable of handling large-scale, high-dimensional, and noisy datasets commonly found in network intrusion detection. The proposed method was evaluated on several benchmark datasets including Darpa 1998-99, KDD Cup99, NSL-KDD, UNSW-NB15, and CAIDA. Comparative experiments with state-of-the-art algorithms such as K-Means++, K-NNDP, and DI-K-Means showed that the proposed approach consistently outperformed or matched competitors in terms of Silhouette Coefficient, Calinski-Harabasz index, and Davies-Bouldin index, indicating better cluster cohesion, separation, and compactness. Additionally, the computational efficiency gained from TILB seeding facilitates faster convergence without compromising clustering quality. Furthermore, a threshold-based cluster labeling mechanism was applied to translate clustering results into practical classifications for detecting attacks versus normal traffic, enhancing the usability of the method in real-world cybersecurity systems. Overall, this research demonstrates that the integration of TILB seeding and mutual information-based clustering provides an effective and efficient solution for network traffic classification challenges.
- 26 June 2025
- Published by Jurnal TIMES, STMIK TIME in Jurnal TIMES
- Vol. 14 (1) , 60-69
Open AccessIMPROVING CYBERSECURITY TRAFFIC ANALYSIS VIA ENHANCED K-MEANS CLUSTERING WITH TRIANGLE INEQUALITY-BASED INITIALIZATION
Clustering algorithms are essential in data mining and pattern recognition for grouping unlabeled data into meaningful clusters based on similarities. Among them, K-Means is widely used due to its simplicity and efficiency but suffers from sensitivity to initial centroid selection and inability to capture feature dependencies. This study proposes an Enhanced Mutual Information-based K-Means (MIK-Means) algorithm combined with Triangle Inequality and Lower Bound (TILB) seeding to improve clustering accuracy and computational efficiency, particularly in the context of network traffic classification for cybersecurity applications. The TILB method accelerates the initialization phase by reducing redundant distance calculations using mathematical pruning techniques, thereby selecting well-distributed initial centroids efficiently. Meanwhile, MIK-Means incorporates mutual information as a similarity measure during clustering assignment, enabling the algorithm to capture complex statistical dependencies among features, which traditional Euclidean distance metrics fail to address. The combination of these two approaches results in a robust clustering framework capable of handling large-scale, high-dimensional, and noisy datasets commonly found in network intrusion detection. The proposed method was evaluated on several benchmark datasets including Darpa 1998-99, KDD Cup99, NSL-KDD, UNSW-NB15, and CAIDA. Comparative experiments with state-of-the-art algorithms such as K-Means++, K-NNDP, and DI-K-Means showed that the proposed approach consistently outperformed or matched competitors in terms of Silhouette Coefficient, Calinski-Harabasz index, and Davies-Bouldin index, indicating better cluster cohesion, separation, and compactness. Additionally, the computational efficiency gained from TILB seeding facilitates faster convergence without compromising clustering quality. Furthermore, a threshold-based cluster labeling mechanism was applied to translate clustering results into practical classifications for detecting attacks versus normal traffic, enhancing the usability of the method in real-world cybersecurity systems. Overall, this research demonstrates that the integration of TILB seeding and mutual information-based clustering provides an effective and efficient solution for network traffic classification challenges.
- Open Access
- 9 May 2025
- Published by Universitas Malikussaleh in International Journal of Engineering, Science and Information Technology
- Vol. 5 (3) , 51-57
A Hybrid GDHS and GBDT Approach for Handling Multi-Class Imbalanced Data Classification
Multiclass imbalanced classification remains a significant challenge in machine learning, particularly when datasets exhibit high Imbalance Ratios (IR) and overlapping feature distributions. Traditional classifiers often fail to accurately represent minority classes, leading to biased models and suboptimal performance. This study proposes a hybrid approach combining Generalization potential and learning Difficulty-based Hybrid Sampling (GDHS) as a preprocessing technique with Gradient Boosting Decision Tree (GBDT) as the classifier. GDHS enhances minority class representation through intelligent oversampling while cleaning majority classes to reduce noise and class overlap. GBDT is then applied to the resampled dataset, leveraging its adaptive learning capabilities. The performance of the proposed GDHS+GBDT model was evaluated across six benchmark datasets with varying IR levels, using metrics such as Matthews Correlation Coefficient (MCC), Precision, Recall, and F-Value. Results show that GDHS+GBDT consistently outperforms other methods, including SMOTE+XGBoost, CatBoost, and Select-SMOTE+LightGBM, particularly on high-IR datasets like Red Wine Quality (IR = 68.10) and Page-Blocks (IR = 188.72). The method improves classification performance, especially in detecting minority classes, while maintaining high accuracy.
- 9 May 2025
- Published by Universitas Malikussaleh in International Journal of Engineering, Science and Information Technology
- Vol. 5 (3) , 51-57
Open AccessA Hybrid GDHS and GBDT Approach for Handling Multi-Class Imbalanced Data Classification
Multiclass imbalanced classification remains a significant challenge in machine learning, particularly when datasets exhibit high Imbalance Ratios (IR) and overlapping feature distributions. Traditional classifiers often fail to accurately represent minority classes, leading to biased models and suboptimal performance. This study proposes a hybrid approach combining Generalization potential and learning Difficulty-based Hybrid Sampling (GDHS) as a preprocessing technique with Gradient Boosting Decision Tree (GBDT) as the classifier. GDHS enhances minority class representation through intelligent oversampling while cleaning majority classes to reduce noise and class overlap. GBDT is then applied to the resampled dataset, leveraging its adaptive learning capabilities. The performance of the proposed GDHS+GBDT model was evaluated across six benchmark datasets with varying IR levels, using metrics such as Matthews Correlation Coefficient (MCC), Precision, Recall, and F-Value. Results show that GDHS+GBDT consistently outperforms other methods, including SMOTE+XGBoost, CatBoost, and Select-SMOTE+LightGBM, particularly on high-IR datasets like Red Wine Quality (IR = 68.10) and Page-Blocks (IR = 188.72). The method improves classification performance, especially in detecting minority classes, while maintaining high accuracy.
- Open Access
- 1 January 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 37 (1) , 590-600
Bibliometric analysis of model vehicle routing problem in logistics delivery
This bibliometric analysis focuses on the vehicle routing problem (VRP) model in the field of logistics delivery. The study utilizes a comprehensive dataset of 2,000 VRP-related publications obtained from the Scopus database, spanning the years 2007 to 2023. Through the application of bibliometric methods, this research aims to uncover key insights regarding research trends, country contributions, and recent topics within the VRP research network. Various bibliometric indicators, including publication count, author productivity, relevant sources, institutional affiliation, and citation frequency, are employed to conduct the analysis. The findings shed light on the evolution and trajectory of VRP research, while also highlighting noteworthy countries and topics that have received significant attention. This study not only enhances the overall understanding of VRP but also serves as a foundation for future investigations aimed at enhancing the efficiency and effectiveness of logistics delivery.
- 1 January 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 37 (1) , 590-600
Open AccessBibliometric analysis of model vehicle routing problem in logistics delivery
This bibliometric analysis focuses on the vehicle routing problem (VRP) model in the field of logistics delivery. The study utilizes a comprehensive dataset of 2,000 VRP-related publications obtained from the Scopus database, spanning the years 2007 to 2023. Through the application of bibliometric methods, this research aims to uncover key insights regarding research trends, country contributions, and recent topics within the VRP research network. Various bibliometric indicators, including publication count, author productivity, relevant sources, institutional affiliation, and citation frequency, are employed to conduct the analysis. The findings shed light on the evolution and trajectory of VRP research, while also highlighting noteworthy countries and topics that have received significant attention. This study not only enhances the overall understanding of VRP but also serves as a foundation for future investigations aimed at enhancing the efficiency and effectiveness of logistics delivery.
- Open Access
- 25 April 2024
- Published by Elsevier in ICT Express
- Vol. 10 (5) , 1094-1102
Hybrid Approach with Membership-Density Based Oversampling for handling multi-class imbalance in Internet Traffic Identification with overlapping and noise
- 25 April 2024
- Published by Elsevier in ICT Express
- Vol. 10 (5) , 1094-1102
Open AccessHybrid Approach with Membership-Density Based Oversampling for handling multi-class imbalance in Internet Traffic Identification with overlapping and noise
- Open Access
- 4 March 2023
- Published by Pusat Penelitian dan Pengabdian Pada Masyarakat Universitas Respati Yogyakarta in International Conference on Information Science and Technology Innovation (ICoSTEC)
- Vol. 2 (1) , 40-44
Classification of Basurek Batik Using Pre-Trained VGG-16 and Support Vector Machine
In the era of technology 4.0, a system is needed to support the development of a company, both in industry, education, and others to help solve problems. In this study, the authors used the Backpropagation Neural Network Algorithm in recognizing hyperthyroid disease patterns. In this study, in the recognition of hyperthyroid disease patterns. The author uses 11 data variables that will be trained using the backpropagation algorithm where the weighting is done randomly and the second data is trained using the backpropagation algorithm. In this study using Matlab application for processing. From the results of testing data derived from kaggle, namely hyperthyroid disease data above, we can see in the 2-2-1 architecture which shows that the target is reduced by the jst output that the SSE is 0.06571 which indicates that there is an increase in hyperthyroid disease activity in humans. From the data obtained, that the performance of artificial neural network calculations with the Backpropagation Algorithm is 86%. Can be seen by comparing the desired target with the prediction target.
- 4 March 2023
- Published by Pusat Penelitian dan Pengabdian Pada Masyarakat Universitas Respati Yogyakarta in International Conference on Information Science and Technology Innovation (ICoSTEC)
- Vol. 2 (1) , 40-44
Open AccessClassification of Basurek Batik Using Pre-Trained VGG-16 and Support Vector Machine
In the era of technology 4.0, a system is needed to support the development of a company, both in industry, education, and others to help solve problems. In this study, the authors used the Backpropagation Neural Network Algorithm in recognizing hyperthyroid disease patterns. In this study, in the recognition of hyperthyroid disease patterns. The author uses 11 data variables that will be trained using the backpropagation algorithm where the weighting is done randomly and the second data is trained using the backpropagation algorithm. In this study using Matlab application for processing. From the results of testing data derived from kaggle, namely hyperthyroid disease data above, we can see in the 2-2-1 architecture which shows that the target is reduced by the jst output that the SSE is 0.06571 which indicates that there is an increase in hyperthyroid disease activity in humans. From the data obtained, that the performance of artificial neural network calculations with the Backpropagation Algorithm is 86%. Can be seen by comparing the desired target with the prediction target.