Article Per Year (5 Year)
p-Index From 2021 - 2026
5.87
P-Index
This Author published in this journals
All Journal TEKNIK INFORMATIKA TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal TIMES International Journal of Advances in Intelligent Informatics Scientific Journal of Informatics JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) BIOLINK (Jurnal Biologi Lingkungan, Industri, Kesehatan) JURNAL MEDIA INFORMATIKA BUDIDARMA JTAM (Jurnal Teori dan Aplikasi Matematika) PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Jurnal Mantik Indonesian Journal of Electrical Engineering and Computer Science Pelita Masyarakat Journal of Applied Data Sciences JUDIMAS (Jurnal Inovasi Pengabdian Kepada Masyarakat) Science in Information Technology Letters Journal of Applied Computer Science and Technology (JACOST) International Journal of Engineering, Science and Information Technology EXPLORER Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Prioritas : Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Pada Masyarakat METHABDI Jurnal Abdimastek (Pengabdian Masyarakat Berbasis Teknologi) Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Jurnal Pengabdian Masyarakat (Jubdimas)
Hartono Hartono
Department Of Magister Program In Informatics, Postgraduate School, Universitas Medan Area
Religion Agriculture, Biological Sciences & Forestry Humanities Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Physics Public Health Social Sciences Transportation

Published : 44 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 44 Documents
Search

 1   2   3   4   5 
Addressing Class Imbalance in Oil Palm Disease and Micronutrient Deficiency Detection Using Meta-Learned Transfer Metric Learning Hartono, Hartono; Ongko, Erianto
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 5 (2025): October 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i5.6857

Abstract

Class imbalance is a major challenge in oil palm disease and nutrient deficiency detection, where healthy samples dominate while diseased or deficient cases are underrepresented, often leading to biased models with high false-negative rates. To address this issue, this study proposes MetaTMLDA (Meta-Learned Transfer Metric Learning with Distribution Alignment), a hybrid framework that combines Transfer Metric Learning (TML) with MW-FixMatch. TML learns discriminative and domain-invariant features, while MW-FixMatch employs a meta-learned weighting mechanism to adaptively reweight samples, improving sensitivity to minority classes and enhancing robustness against pseudo-label noise. Experiments on four public datasets—Ganoderma Disease Detection, Palm Oil Leaf Disease, and Leaf Nutrient Detection for Boron and Magnesium—demonstrated that the proposed method consistently outperforms TML-DA, MW-FixMatch, SMOTE, Random Undersampling, and Biased SVM. On the smaller datasets (Ganoderma and Palm Oil Leaf Disease), MetaTMLDA achieved accuracy of 0.976, precision 0.951, recall 0.915, Cohen’s Kappa 0.912, and macro F1-score 0.933 for Ganoderma, and accuracy of 0.980, precision 0.972, recall 0.957, Kappa 0.911, and macro F1-score 0.964 for Palm Oil Leaf Disease. On the larger datasets (Boron and Magnesium), the model reached near-perfect accuracy of 0.995, with precision up to 0.967, recall up to 0.973, Kappa above 0.919, and macro F1-scores up to 0.969, highlighting its robustness and balanced predictive performance. These findings confirm that MetaTMLDA effectively addresses both class imbalance and domain shift, providing a scalable solution for precision agriculture through earlier and more reliable detection of oil palm health issues.
Pelatihan Penulisan Karya Ilmiah untuk Mahasiswa Teknik Informatika Sumatera Utara Rahman, Sayuti; Hartono, Hartono; Sembiring, Arnes; Ongko, Erianto; Aulia, Rachmat
Prioritas: Jurnal Pengabdian Kepada Masyarakat Vol. 6 No. 01 (2024): EDISI MARET 2024
Publisher : Universitas Harapan Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35447/prioritas.v6i01.926

Abstract

Penulisan karya ilmiah merupakan salah satu keterampilan penting yang harus dikuasai oleh mahasiswa dalam menyelesaikan studi mereka. Namun, masih banyak mahasiswa yang mengalami kesulitan dalam menghasilkan karya ilmiah yang berkualitas. Oleh karena itu, kegiatan pengabdian masyarakat ini bertujuan untuk memberikan pelatihan penulisan karya ilmiah kepada mahasiswa Teknik Informatika di Sumatera Utara. Kegiatan ini dilaksanakan dengan kerjasama antara lembaga pendidikan tinggi dan organisasi profesi, yaitu Ikatan Profesi Komputer Informatika Nusantara (IKAPKIN). Pelatihan dilakukan melalui platform Zoom dan melibatkan 81 peserta dari berbagai perguruan tinggi di Sumatera Utara. Materi pelatihan mencakup berbagai trik dan tool dalam penulisan karya ilmiah, serta panduan dalam memanfaatkan tool penelitian seperti ChatGPT, DeepL.Com, Grammarly, Quillbot, dan Mendeley. Hasil evaluasi postest menunjukkan adanya peningkatan yang signifikan dalam pemahaman peserta terhadap penggunaan tool penelitian, dengan jumlah peserta yang memahami meningkat secara signifikan. Respon positif terhadap penyampaian materi pelatihan juga tercatat. Diharapkan kegiatan ini dapat memberikan dampak positif dalam meningkatkan kualitas penulisan karya ilmiah mahasiswa Teknik Informatika di Sumatera Utara
A Comparative Analysis on the Evaluation of KNN and SVM Algorithms in the Classification of Diabetes Limas, Agus Fahmi; Rosnelly, Rika; Hartono, Hartono; Nursie, Aly
Scientific Journal of Informatics Vol 10, No 3 (2023): August 2023
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v10i3.44269

Abstract

Purpose: Diabetes has received a great deal of attention in medical research because of its profound effect on human health. Many factors cause this disease in the human body. Can be from food or drink that is often consumed by the human body. Diabetes cannot be cured and can only be controlled.Methods: In this study, using 2 data mining techniques namely Support Vector Machine and K-Nearest Neighbor were applied to predict diabetes. In this study, 768 diabetes data were used as trial data, consisting of training data that had been pre-processed data and 400 data cleaning data, 278 data testing data, and 50 diabetes data samples used as samples in the calculation.Result: The performance of each algorithm is analyzed differently, the results of each best algorithm will be analyzed to determine which algorithm can provide better results for predicting diabetes. The results obtained in this study get a value of 0 where the predicted value of the target class for new data is the negative class (Suffer).Novelty: This study compares the SVM and K-NN methods for diabetes classification. So, successfully implemented for data on the classification target
Hybrid Approach with Distance Feature for Multi-Class Imbalanced Datasets Hartono, Hartono; Ongko, Erianto
JOIV : International Journal on Informatics Visualization Vol 7, No 1 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.1.1292

Abstract

The multi-class imbalance problem has a higher level of complexity when compared to the binary class problem. The difficulty is due to the large number of classes that will present challenges related to overlapping between classes. Many approaches have been proposed to deal with these multi-class problems. One is a hybrid approach combining a data-level approach and an algorithm-level approach. This approach is done by the ensemble on the classifier and also oversampling on the minority class. SMOTE is an oversampling method that provides good performance, but this method is necessary to determine the best sample used in the interpolation process to generate new samples. The need for determining the best sample is related to the overlap between classes that always accompanies the multi-class imbalance problem. The existence of overlap requires efforts to determine the safe region to synthesize the sample in the oversampling process in SMOTE. The safe region is considered the best for synthesizing samples due to the lower tendency of overlapping. It can be done by constructing distance features to determine the safe region. The sample with the best distance and the lowest imbalance ratio will be selected as a sample in the over-sampling process with SMOTE. The main contribution of this research is the proposed method of Hybrid Approach with Distance Feature so that it can determine safe samples, with the main advantage being in addition to handling multi-class imbalances, it is also better for handling overlapping. The results of this study will be compared with Multiple Random Balance (MultiRandBal) which performs a random oversampling process. The results showed that the Augmented R-Value, Class Average Accuracy, Class Balance Accuracy, and Hamming Loss obtained in this method was better than the random oversampling process. These results also show that the Hybrid Approach with Distance Feature provides better results in handling multi-class imbalances when compared to MultiRandBal.
Avoiding Overfitting dan Overlapping in Handling Class Imbalanced Using Hybrid Approach with Smoothed Bootstrap Resampling and Feature Selection Hartono, Hartono; Ongko, Erianto
JOIV : International Journal on Informatics Visualization Vol 6, No 2 (2022)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.2.985

Abstract

The dataset tends to have the possibility to experience imbalance as indicated by the presence of a class with a much larger number (majority) compared to other classes(minority). This condition results in the possibility of failing to obtain a minority class even though the accuracy obtained is high. In handling class imbalance, the problems of diversity and classifier performance must be considered. Hence, the Hybrid Approach method that combines the sampling method and classifier ensembles presents satisfactory results. The Hybrid Approach generally uses the oversampling method, which is prone to overfitting problems. The overfitting condition is indicated by high accuracy in the training data, but the testing data can show differences in accuracy. Therefore, in this study, Smoothed Bootstrap Resampling is the oversampling method used in the Hybrid Approach, which can prevent overfitting. However, it is not only the class imbalance that contributes to the decline in classifier performance. There are also overlapping issues that need to be considered. The approach that can be used to overcome overlapping is Feature Selection. Feature selection can reduce overlap by minimizing the overlap degree. This research combined the application of Feature Selection with Hybrid Approach Redefinition, which modifies the use of Smoothed Bootstrap Resampling in handling class imbalance in medical datasets. The preprocessing stage in the proposed method was carried out using Smoothed Bootstrap Resampling and Feature Selection. The Feature Selection method used is Feature Assessment by Sliding Thresholds (FAST). While the processing is done using Random Under Sampling and SMOTE. The overlapping measurement parameters use Augmented R-Value, and Classifier Performance uses the Balanced Error Rate, Precision, Recall, and F-Value parameters. The Balanced Error Rate states the combined error of the majority and minority classes in the 10-Fold Validation test, allowing each subset to become training data. The results showed that the proposed method provides better performance when compared to the comparison method
Analisis Komparatif CNN Ringan untuk Klasifikasi Penyakit Daun Tomat Menggunakan Visualisasi Grad-CAM Rahman, Sayuti; Hartono, Hartono; Sembiring, Arnes; Khahfi Zuhanda, muhammad; Aditya Pratama, Bayu; Martini, Dewi
Explorer Vol 6 No 1 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/explorer.v6i1.2601

Abstract

Tomato leaf disease classification based on digital imagery has become an important approach in supporting smart agriculture, particularly for early detection of plant disease attacks. This study aims to compare the performance of several lightweight Convolutional Neural Network (CNN) architectures, namely MobileNetV3-Small, MobileNetV2, and EfficientNet-B0, in classifying tomato leaf diseases using the PlantVillage dataset. The dataset consists of 3,628 images distributed across 10 classes (9 disease classes and 1 healthy class), with a data split scheme of 80% for training and 20% for validation. Performance evaluation was conducted using classification reports, confusion matrices, and interpretability analysis through Grad-CAM and feature map visualization. The experimental results show that all models achieved very high accuracy, exceeding 99%. EfficientNet-B0 obtained the best performance with a validation accuracy of 99.59%, followed by MobileNetV2 at 99.45% and MobileNetV3-Small at 99.04%. However, model complexity increased along with accuracy, where EfficientNet-B0 had the largest number of parameters and FLOPs. Grad-CAM analysis revealed that higher-accuracy models demonstrated more precise activation focus on leaf lesion regions. This study confirms that lightweight CNN architectures are capable of delivering excellent classification performance while offering strong potential for deployment in plant disease detection systems on resource-limited devices
MOLECULAR PHYLOGENY OF RODENTIA DERIVED FROM NRAS GENE SEQUENCES Yudi Gebri Foenna; Hartono Hartono; Imelda Maelani
BIOLINK (Jurnal Biologi Lingkungan Industri Kesehatan) Vol. 12 No. 2 (2026): Biolink February
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/biolink.v12i2.16827

Abstract

Rodentia is the most diverse mammalian order, yet phylogenetic relationships among several rodent lineages remain incompletely resolved, particularly when inferred predominantly from mitochondrial markers. This study aims to assess the potential of the nuclear NRAS (Neuroblastoma RAS viral oncogene homolog) gene for reconstructing rodent phylogeny. A total of 18 NRAS nucleotide sequences representing major rodent families were retrieved from the NCBI GenBank database, with Equus caballus and Oryctolagus cuniculus used as outgroups. Sequence alignment and model selection were performed using MEGA 12 under Maximum Likelihood criteria. Phylogenetic reconstruction was conducted using the Maximum Likelihood method with the T92+G+I substitution model and 1,000 bootstrap replicates. Pairwise genetic distances were estimated using the p-distance method and visualized through a heatmap to examine divergence patterns. The results indicated that NRAS evolution is best explained by models incorporating invariant sites and rate heterogeneity, reflecting strong functional constraints combined with lineage-specific variation. The inferred phylogeny is largely congruent with established rodent systematics, and genetic distance patterns independently support the recovered topology. These findings suggest that NRAS represents a reliable nuclear marker that offers complementary phylogenetic information alongside mitochondrial data in Rodentia phylogenetic studies.
Analisis Regresi Linear Terhadap Tingkat Pengangguran Terbuka Menurut Provinsi Periode 2021-2025 Iqbal Giffari Ritonga; Hartono; Peniel Sam Putra Sitorus
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.858

Abstract

Pengangguran terbuka merupakan salah satu faktor yang berkontribusi terhadap kemiskinan dan ketimpangan sosial-ekonomi di Indonesia. Penelitian ini bertujuan untuk menganalisis hubungan antara Tingkat Pengangguran Terbuka (TPT) bulan Februari sebagai variabel independen dengan TPT bulan Agustus sebagai variabel dependen menggunakan regresi linear sederhana, serta memprediksi TPT antar provinsi periode 2021–2025. Data yang digunakan meliputi TPT 38 provinsi, dengan analisis regresi menghasilkan persamaan . Hasil analisis menunjukkan koefisien (R²) sebesar 97%, MSE 2,29, dan RMSE 1,51, yang mengindikasikan bahwa model regresi mampu menjelaskan sebagian besar variasi TPT dan menghasilkan prediksi yang akurat. Penelitian ini menegaskan adanya hubungan positif yang kuat antara TPT bulan Februari dan Agustus, sehingga nilai TPT bulan Februari dapat dijadikan indikator untuk memprediksi TPT bulan Agustus.
Hybrid Approach for Class Imbalance Handling using Adaptive Weighted Oversampling and Instance Hardness-Based Undersampling Hartono Hartono; Erianto Ongko; Muhammad Khahfi Zuhanda
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 10, No 3 (2026): July
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v10i3.36972

Abstract

Class imbalance remains a major challenge in multi-class classification, where existing hybrid resampling methods often combine oversampling and undersampling in a loosely coupled manner, without explicitly coordinating minority enrichment and majority reduction. In this experimental study, we propose a novel hybrid resampling method, Adaptive Weighted Oversampling and Instance Hardness-Based Undersampling (AWO-IHU), which differs from existing hybrid approaches by explicitly aligning boundary-aware minority oversampling with instance hardness-based majority undersampling. Rather than independently applying oversampling and undersampling, the proposed method integrates both processes through a coordinated design guided by classification difficulty to improve decision boundary quality. Methodologically, AWO-IHU first applies adaptive weighted oversampling to emphasize informative minority instances near class boundaries, followed by instance hardness-based undersampling that selectively removes redundant majority samples using an ensemble-based difficulty estimation. The experimental evaluation is conducted using multiple benchmark datasets with varying numbers of instances, attributes, and classes. Classification performance is evaluated using Accuracy, Precision, Recall, and Cohen’s Kappa, enabling a comprehensive assessment of overall correctness, minority sensitivity, and agreement beyond chance under class imbalance. Experimental results show that AWO-IHU consistently outperforms SMOTE, Random Undersampling, and conventional hybrid sampling methods. In particular, the proposed method achieves perfect or near-perfect Recall values up to 1.0, while maintaining high Precision values above 0.89 and producing the highest Cohen’s Kappa values up to 0.86. These findings demonstrate that explicitly coordinating minority enrichment with difficulty-aware majority reduction yields more reliable decision boundary learning and improved generalization in imbalanced multi-class classification. 
Predicting Burnout in Start-Up Environments: A Multivariate Risk Scoring Approach for Early Managerial Intervention Nos Sutrisno; Maricha Elveny; Andre Hasudungan Lubis; Rahmad Syah; Hartono Hartono; Sabina Krisdayanti
International Journal of Engineering, Science and Information Technology Vol 5, No 4 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i4.1663

Abstract

Start-up organisations operate under fast timelines, lean staffing, and constantly shifting priorities, exposing employees to chronic workload pressure and emotional strain. Unmanaged burnout in these settings threatens individual well-being, talent retention, and long-term execution capacity. This study proposes a multivariate burnout risk scoring approach that aims to identify and prioritise employees at elevated risk before full deterioration occurs, enabling early managerial intervention rather than reactive recovery. The proposed pipeline integrates principal component analysis (PCA), Random Forest, and Support Vector Machine (SVM). PCA is first applied to reduce redundancy across workplace indicators, yielding five principal components (PC1–PC5) that together explain 88% of the total variance in self-reported stress level, job satisfaction, emotional exhaustion, work-life balance, performance, and social interaction. These components are then used as predictors in two supervised classification models, Random Forest and SVM, to estimate the likelihood that each employee belongs to a high-burnout-risk class. The Random Forest model achieved an accuracy of 88%, and the SVM model achieved an accuracy of 86%, demonstrating strong predictive capability in distinguishing higher-risk employees from lower-risk employees. The resulting predicted probability is interpreted as an individualised burnout risk score, which can be mapped to action categories such as workload redistribution, role clarification, targeted supervisory check-ins, or temporary protection from critical-path tasks. In this way, the framework operationalises burnout prediction not only as a detection task but also as an actionable decision-support signal for leaders. The study therefore offers both a quantitative method for forecasting burnout in start-up environments and a practical structure for translating prediction into preventive intervention.
Co-Authors Aditya Pratama, Bayu Ammar Yasir Nasution Andi Rahmadsyah Andik Bintoro Andre Hasudungan Lubis Andriasan Sudarso Arnes Sembiring Asmah Indrawati B. Herawan Hayadi B. Herawan Hayadi Brilliant Handyman Manalu Citra Rahmadhani Cut Ita Erliana Dadan Ramdan Dahlan Abdullah Dedi Sahputra Desniarti Dian Maya Sari Elvie Maria Erianto Ongko Erianto Ongko Erianto Ongko Erianto Ongko Erianto Ongko Erianto Ongko Erianto Ongko Erianto Ongko Erna Budhiarti Nababan Faadhil, Faadhil Finta Aramita Firman Syahputra Firman Syahputra Gio, Prana Ugiana Habib Satria Imelda Maelani Iqbal Giffari Ritonga Irwan Daniel Jaka Kusuma Jaka Kusuma Khairul Fadhli Margolang Limas, Agus Fahmi Maricha Elveny Marischa Elveny, Marischa Martini, Dewi Meli Handayani Mendarissan Aritonang Muhammad Ikhwani Muhammad Khahfi Zuhanda Muhammad Sadikin Muhammad Zarlis Muhammad Zulkarnain Lubis Mulkan Andika Situmorang N. Nazaruddin Nadapdap, Kristanty M. N. Nadra Ideyani Vita Nasution, Mahyuddin K.M Nos Sutrisno Nur Anzelina Nur Azelina Harahap Nursie, Aly Nurwijayanti Opim Salim Sitompul Prana Ugi Rachmat Aulia, Rachmat Rahmad B.Y Syah Rahmad Syah, Rahmad Rahman, Sayuti Rana Fathinah Ananda Retna Astuti Kuswardani Rezzy Eko Caraka Ria Wuri Andary Rika Rosnelly Rika Rosnelly Rika Rosnelly Rika Rosnelly Rika Rosnelly, Rika Rohima Rohima Rubianto Sabina Krisdayanti Samsul A Rahman Sidik Hasibuan Sembiring, Arnes Silvia Lestari Silvia Lestari Siti Aisyah Sitorus, Peniel Sam Putra Sugeng Riyadi suswati suswati Suswati Suswati Syah, Rahmad B.Y Tulus Tulus Wanayumini Wulan Dari Yeni Risyani Yudi Gebri Foenna Zakarias Situmorang