Article Per Year (5 Year)
p-Index From 2021 - 2026
5.072
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi Jurnal Pengabdian UntukMu NegeRI Informatika Mulawarman: Jurnal Ilmiah Ilmu Komputer Jurnal Penelitian Pendidikan IPA (JPPIPA) Dinamisia: Jurnal Pengabdian Kepada Masyarakat MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer JURNAL PENDIDIKAN TAMBUSAI Digital Zone: Jurnal Teknologi Informasi dan Komunikasi JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Journal of Applied Engineering and Technological Science (JAETS) Jurnal Teknik Informatika (JUTIF) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Archive: Jurnal Pengabdian Kepada Masyarakat J-COSCIS : Journal of Computer Science Community Service CONSEN: Indonesian Journal of Community Services and Engagement JURNAL KARYA ILMIAH MULTIDISIPLIN INOVTEK Polbeng - Seri Informatika
Loneli Costaner
Fakultas Ilmu Komputer, Universitas Lancang Kuning
Religion Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Physics Public Health Social Sciences Other

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

Found 44 Documents
Search

 1   2   3   4   5 
Optimizing Random Forest for IoT Cyberattack Detection using SMOTE: A Study on CIC-IoT2023 Dataset Guntoro, Guntoro; Lisnawita, Lisnawita; Costaner, Loneli
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 25 No. 1 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v25i1.5382

Abstract

The growing number of Internet of Things devices has led to an increased risk of complex and diverse cyberattacks. However, a significant challenge in this domain is the imbalanced class distribution in most Internet of Things datasets, cautilizing classification algorithms to be biased towards the majority class, hindering effective threat detection. This study addresses this issue by leveraging the Random Forest algorithm optimised by the Synthetic Minority Oversampling Technique. This research aims to develop an effective model for detecting cyberattacks in Internet of Things environments by resolving class imbalance issues inside of the CIC-IoT2023 dataset. The methodology involves several stages, comprising data preprocessing and applying Synthetic Minority Oversampling Technique for data balancing. The balanced dataset was then used to train a Random Forest model, by its performance evaluated utilizing accuracy, precision, recall, F1-score, and Cohen's Kappa metrics. The results demonstrate the model's effectiveness, achieving an accuracy of 99.01%, an F1-score of 98.96%, and a Cohen's Kappa of 98.92%. This marks a notable improvement in performance, particularly in detecting minority classes, compared to the model trained devoid of Synthetic Minority Oversampling Technique, that struggled to identify several less common attack types. The outcomes suggest that combining Random Forest by Synthetic Minority Oversampling Technique can significantly enhance the development of intrusion detection systems by improving detection accuracy for all 33 attack types and reducing the risks associated by undetected threats. In conclusion, this study advances Internet of Things cybersecurity by presenting an effective and efficient method for addressing data imbalance in attack detection. Future research should focus on evaluating the model's robustness utilizing more complex datasets and enhancing its performance for real-time deployment on resource-constrained Internet of Things Devices.
Empowering Vocational School Students Through Digital Security Training to Prevent Cyber Threats: A Case Study at SMKN 7 Pekanbaru : Pemberdayaan Siswa SMK Melalui Pelatihan Keamanan Digital untuk Mencegah Ancaman Siber: Studi Kasus di SMKN 7 Pekanbaru Guntoro, Guntoro; Lisnawita , Lisnawita; Monika, Winda; Costaner, Loneli
CONSEN: Indonesian Journal of Community Services and Engagement Vol. 6 No. 1 (2026): Consen: Indonesian Journal of Community Services and Engagement
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/consen.v6i1.2326

Abstract

Digital devices now form the backbone of nearly every classroom, yet that convenience comes tangled with new cybersecurity peril. Students in vocational tracks sit at the crossroads: they click through learning modules all day but rarely receive targeted instruction on how to keep themselves safe online. Without that practical know-how, the hallways of a single school can quietly accumulate risks like data leaks, identity theft, and rogue software. In response, the present study piloted a campus-based workshop designed to meet learners exactly where they are. Courses were delivered at SMKN 7 Pekanbaru, involving thirty trade students who volunteered despite their busy schedules. Lectures spoke in plain language; hands-on exercises replayed incidents pulled from local news; quick-fire quizzes and spirited group debates stitched it all together. Student mastery was quantified by side-by-side snapshots taken before and after the event, measured against five essential security benchmarks. The opening average sat at a modest 18.7 out of 25; the closing number soared to 24.4. A paired t-test for the twenty-nine complete sets of data returned t(29) = 13.25, p < 0.0001, clearly ruling out chance. Glance at the run charts and the upward drift is obvious: every learner moved forward, and the room buzzed with confidence that had been absent hours earlier. Recent research confirms that focused, brief cybersecurity workshops can significantly boost learners grasp of online threats and the defensive habits they employ. Because the instructional framework proved practical, other institutions are well-positioned to adopt it and thereby reduce the cyber vulnerabilities that affect campus communities.
Exploring Research and Service Information System Usability by Heuristic Evaluation as a Compelement of System Usability Scale Guntoro; Lisnawita; Loneli Costaner
Jurnal Penelitian Pendidikan IPA Vol 9 No 12 (2023): December
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i12.5571

Abstract

The Research and Community Service Information System of LPPM University Lancang Kuning is a web-based application designed to facilitate research and community service activities at the university. This study incorporated two methodologies: a descriptive approach with qualitative analysis for heuristic data collection, and the System Usability Scale (SUS) method, employing quantitative analysis. The research process included stages of problem analysis, literature review, data collection, data analysis, and formulating recommendations based on the findings and discussions. The heuristic evaluation, the first method applied, revealed that aspects H1, H3, and H4 scored 1 when rounded, indicating these were merely cosmetic issues not requiring immediate attention unless spare time was available. Conversely, aspects H2, H5, H6, H7, H8, H9, and H10 scored 2 when rounded, categorizing them as minor usability issues needing resolution, albeit with low priority, to prevent potential user difficulties. Recommendations for these seven heuristic aspects scoring 2 encompassed improvements in system information clarity, feedback processes, image utilization, color selection, grammar quality, and writing consistency. The second method, the SUS, indicated that most users demonstrated adequate skills in terms of learnability, efficiency, memorability, error management, and overall satisfaction with their system usage experience.
A Parallel Comparative Multi-Scenario Framework For Diabetic Retinopathy Detection Using Three-Tiered Feature Selection Loneli Costaner; Nor Hazlyna Harun
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 2 (2026): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/xtfckd08

Abstract

Early detection of Microaneurysms (MAs) is vital for diagnosing Diabetic Retinopathy, yet standard deep learning models often struggle with high false-negative rates and overfitting on limited medical datasets. Objective: This study proposes a Parallel Comparative Multi-Scenario Framework to identify the most robust configuration for MA detection. The framework evaluates independent 1D vectorized feature descriptors, each initialized as a high-dimensional 16,384-feature baseline, to avoid the redundancy inherent in feature fusion. Methodology: The system systematically processes six independent descriptors LBP, GLCM, Gabor, Wavelet, Fractal, and LMR across three selection tiers (Filter, Wrapper/RFE, and Embedded). These optimized vectors, reduced from the initial 16,384 dimensions to the most discriminative "Best Subsets," serve as uniform inputs for six classifiers: five traditional Machine Learning (ML) models and a proposed representation-consistent 1D-CNN architecture, resulting in 128 experimental scenarios. Results: Experimental evaluation was conducted on a balanced dataset of 740 fundus images derived from two distinct sources: the publicly available MESSIDOR dataset and a clinically acquired dataset from Hospital Universiti Sains Malaysia (HUSM). The model was trained on MESSIDOR data and subsequently evaluated on an independent HUSM test set to assess generalization performance. The results reveal a significant performance gap. The independent LBP-RFE-SVM scenario achieved the highest performance with an accuracy, recall, and precision of 91.00%. In contrast, the best Deep Learning (DL) configuration, Gabor-ANOVA-1DCNN, reached 87.00% accuracy. Notably, while the 1D-CNN maintained a "performance floor" of 60%, ML demonstrated extreme volatility, dropping to 51.00% with global statistical features. The optimal framework significantly minimized the False Negative Rate (FNR) to 6.76%, missing only 5 out of 74 cases.
Co-Authors Abdullah Abdullah Ahmad Zamsuri, Ahmad Alfarasy, Febrizal Alyauma Hajjah Antonius Fernando Bakar, Juhaida Abu Bayu Febriadi, Bayu Chan, Andhi Darmanta Sukrianto Deny Jollyta Dwi Oktarina Guntoro Guntoro, Guntoro Gusrianty Gusrianty Gustientiedina Hadi Dwi Putra Hutri Rizkiyah Alda Johan Johan Johar, Olivia Anggie Lisnawita Lisnawita , Lisnawita Lisnawita Lisnawita Lisnawita Lisnawita Lucky Lhaura Van FC, Lucky Lhaura Mariza Devega Mhd. Arief Hasan, Mhd. Arief Musfawati Mustika Mustika Nor Hazlyna Harun Pandu Pratama Putra, Pandu Pratama Rasli, Ruziana Mohamad Samsudin, Samsudin Sutejo Sutejo Wahyu Joni Kurniawan Wenni Syafitri Wenny Syafitri Yitro Amazihono Yogi Yunefri, Yogi Yuhelmi Yuhelmi