Article Per Year (5 Year)
p-Index From 2021 - 2026
2.2
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Panrita Abdi - Jurnal Pengabdian pada Masyarakat Sistemasi: Jurnal Sistem Informasi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) INOVTEK Polbeng - Seri Informatika JURNAL TEKNOLOGI DAN OPEN SOURCE Digital Zone: Jurnal Teknologi Informasi dan Komunikasi J-Dinamika: Jurnal Pengabdian Kepada Masyarakat REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer Indonesian Journal of Electrical Engineering and Computer Science Bhakti Nagori (Jurnal Pengabdian kepada Masyarakat) Journal of Informatics and Electronics Engineering Jurnal Penelitian Rumpun Ilmu Teknik SATIN - Sains dan Teknologi Informasi Journal of Embedded Systems, Security and Intelligent Systems Saber: Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Jurnal Teknik Informatika dan Teknologi Informasi
Fajar Ratnawati
Politeknik Negeri Bengkalis
Agriculture, Biological Sciences & Forestry Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Multiclass IoT Intrusion Detection Based on Particle Swarm Optimization-Tuned Light Gradient Boosting Machine Fajar Ratnawati; Agus Tedyyana
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 2 (2026): June 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2612

Abstract

Purpose – This study aims to develop a robust multiclass intrusion detection system (IDS) for Internet of Things (IoT) environments by optimizing Light Gradient Boosting Machine (LightGBM) using Particle Swarm Optimization (PSO), with a focus on improving performance under severe class imbalance. Design/methods/approach – A PSO-based hyperparameter tuning framework is applied to LightGBM, where Macro F1-score is used as the fitness function to ensure balanced class performance. The model is evaluated on the RT-IoT2022 dataset using a leakage-safe stratified 70:15:15 split. Performance is assessed using Accuracy, Macro Precision, Macro Recall, Macro F1-score, Weighted F1-score, and Matthews Correlation Coefficient (MCC). Experiments are repeated across 10 runs, and statistical significance is validated using the Wilcoxon signed-rank test. Findings - The proposed PSO-LightGBM model significantly outperforms the baseline LightGBM. It achieves 99.75% accuracy, 97.10% macro F1-score, 99.75% weighted F1-score, and 99.37% MCC, compared to 85.36%, 25.44%, 84.23%, and 63.67%, respectively, for the baseline. The model demonstrates substantial improvement in minority-class detection, reducing misclassification and preventing class collapse observed in the baseline. Research implications/limitations – The findings highlight the effectiveness of Macro-F1-guided optimization for imbalanced multiclass IoT intrusion detection. However, the evaluation is limited to a single dataset and centralized experimental setting, which may affect generalizability. Originality/value – This study contributes a leakage-safe, Macro-F1-driven PSO-LightGBM framework with comprehensive evaluation, including class-wise analysis, repeated runs, and statistical testing, providing strong evidence for balanced multiclass IoT intrusion detection.
Development of a Certainty Factor-Based Expert System for Nutrition Consultation and Stunting Prevention in Coastal Areas: A Case Study of Bengkalis Regency Fajar Ratnawati; Niky Hardinata; Supendi
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4858

Abstract

This study developed a Certainty Factor (CF)–based expert system to support nutrition consultation and stunting prevention in coastal settings using Bengkalis Regency as a case study. A design science approach was employed to analyze local service constraints, acquire expert knowledge, formalize a rule base, implement an offline-first prototype (mobile client and admin dashboard), and evaluate its performance. Knowledge was elicited from nutritionists, midwives, and community health workers and encoded as IF–THEN rules with expert confidence weights; Evidence (anthropometry, infection history, infant and young child feeding, sanitation, and socioeconomic factors) was mapped to CF values ​​and combined to yield risk scores and categories with explainable rule traces. Functional testing showed all user-story scenarios passed as expected, while initial expert validation and usability checks indicated the prototype provided rapid and standardized assessments suitable for first-line services. The results suggest the CF approach is feasible for coastal contexts with limited connectivity and can accelerate early screening and referrals. Future work will expand the local knowledge base, integrate electronic records, and conduct wider field trials to measure effectiveness at scale
Swarm intelligence for intrusion detection systems in internet of things environments Apri Siswanto; Akmar Efendi; Jaroji Jaroji; Fajar Ratnawati
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 23, No 1: February 2025
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v23i1.25857

Abstract

The rise of the internet of things (IoT) technology has brought new security challenges, necessitating robust intrusion detection systems (IDS). This research applies swarm intelligence (SI) principles, specifically the pigeon inspired optimization (PIO) algorithm, to enhance IDS effectiveness in IoT environments. Drawing on the behavior of social species, SI fosters decentralized control and emergent behavior from simple rules. These principles guide the PIO algorithm, making it apt for optimizing IDS. We utilize two comprehensive IoT datasets – the Canadian Institute for Cybersecurity (CIC) IoT dataset 2023 and the IoT dataset for IDS, aiming to boost the IDS’s capability to detect illicit attacks. By adapting the PIO algorithm, our IDS learns from the environment, adapts to evolving threats, and mitigates false-positive rates. Preliminary tests show that our SI-based IDS outperforms traditional systems’ accuracy, speed, and adaptability. This research advances SI applications in IoT security, contributing to developing more resilient IDS and ultimately enhancing IoT network security against a range of cyber threats.
PENERAPAN APLIKASI KONSULTASI GIZI UNTUK PENCEGAHAN DINI STUNTING DI POSKESDES PENAMPI Niky Hardinata; Fajar Ratnawati; Supendi Supendi
BHAKTI NAGORI (Jurnal Pengabdian kepada Masyarakat) Vol. 5 No. 2 (2025): BHAKTI NAGORI (Jurnal Pengabdian kepada Masyarakat) Desember 2025
Publisher : LPPM UNIKS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/bhakti_nagori.v5i2.4949

Abstract

Stunting masih menjadi permasalahan kesehatan serius di Indonesia, khususnya di wilayah kerja Poskesdes desa Penampi, kabupaten Bengkalis, provinsi Riau. Hal ini diakibatkan kurangnya pemahaman gizi masyarakat dan keterbatasan tenaga ahli di tingkat desa. Prevalensi stunting di Bengkalis berada pada tingkat 12,%. Hal ini mengalami penurunan dari sebelumnya yang berada pada tingkat 17,9%. Menjawab tantangan tersebut dan membantu pemerintah menurunkan tingkat stunting, maka dilaksanakan kegiatan pengabdian kepada masyarakat berupa penerapan aplikasi konsultasi gizi berbasis digital yang mampu membantu petugas kesehatan dan masyarakat dalam menilai status gizi, diagnosa awal stunting serta memberikan rekomendasi asupan yang tepat, khususnya bagi ibu hamil dan ibu balita. Melalui pelatihan dan pendampingan kader kesehatan serta tenaga medis, program ini tidak hanya meningkatkan kapasitas layanan gizi berbasis teknologi informasi tetapi juga mempercepat upaya pencegahan stunting sejak dini, sekaligus mendorong kesadaran masyarakat akan pentingnya pemenuhan gizi keluarga sebagai wujud nyata sinergi perguruan tinggi dan fasilitas kesehatan dalam penerapan IPTEK untuk solusi permasalahan lokal.
Sistem Rekomendasi Peran Karir Mahasiswa Rekayasa Perangkat Lunak Dengan Metode Simple Multi Attribute Rating Technique Exploiting Rank (SMARTER) Nofia Zuriatin; Fajar Ratnawati
Journal of Informatics and Electronics Engineering Vol. 6 No. 01 (2026): Juni 2026
Publisher : Unit Penelitian dan Pengabdian kepada Masyarakat Politeknik TEDC Bandung Jl. Pesantren Km 2 Cibabat Cimahi Utara – Cimahi 40513 Jawa Barat – Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70428/jiee.v6i01.1583

Abstract

Mahasiswa Program Studi Rekayasa Perangkat Lunak (RPL) sering mengalami kesulitan dalam menentukan peran karir yang sesuai dengan minat dan kemampuan yang dimiliki. Permasalahan ini disebabkan oleh keterbatasan informasi serta belum tersedianya sistem pendukung keputusan yang mampu memberikan rekomendasi secara objektif dan terukur. Penelitian ini bertujuan untuk merancang dan membangun sistem rekomendasi peran karir bagi mahasiswa RPL menggunakan metode Simple Multi Attribute Rating Technique Exploiting Rank (SMARTER) dengan pembobotan Rank Order Centroid (ROC). Sistem rekomendasi dikembangkan berdasarkan empat kriteria utama dengan total 33 subkriteria, enam alternatif peran karir, serta melibatkan 30 responden mahasiswa. Pengujian sistem dilakukan menggunakan metode black box testing dan pengujian hasil metode SMARTER berdasarkan preferensi mahasiswa. Hasil penelitian menunjukkan bahwa sistem yang dibangun mampu memberikan rekomendasi peran karir yang sesuai dengan minat mahasiswa dengan tingkat akurasi sebesar 83%. Sistem ini diharapkan dapat membantu mahasiswa RPL dalam menentukan peran karir secara objektif, sistematis, dan terarah.
LightGBM for Liver Disease Detection with Hybrid Hyperparameter Optimization Fajar Ratnawati; Agus Tedyyana; Johny Custer
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i4.7357

Abstract

In response to the growing burden of liver-related disorders, this research develops a supervised learning approach using the Light Gradient Boosting Machine (LightGBM) algorithm to support the early identification of Non-Alcoholic Fatty Liver Disease (NAFLD). The study focuses on constructing and assessing a robust classification model that differentiates individuals with NAFLD from those without the condition based on routinely collected clinical indicators and lifestyle-related characteristics. The dataset, obtained from an open-access NAFLD repository, consists of 1,700 patient records with 10 predictor variables and one binary diagnosis label. The proposed framework employs a stratified shuffle split evaluation scheme with 5-fold and 10-fold cross-validation, using out-of-fold (OOF) probabilities to compute overall performance metrics. The baseline LightGBM model already demonstrated strong performance, achieving 88.94% accuracy, 90.74% precision, 88.99% recall, 89.85% F1-score, and 92.52% AUC under 10-fold cross-validation. To further improve predictive performance, hyperparameter tuning was performed using Optuna and Bayesian Optimization. Among the evaluated approaches, Bayesian-optimized LightGBM achieved the best results, with 93.17% accuracy, 94.49% precision, 92.52% recall, 93.72% F1-score, and 93.28% AUC under 10-fold cross-validation. These findings indicate that systematic hyperparameter optimization can improve the discriminative capability of LightGBM for NAFLD detection and support its potential as a reliable decision-support tool in clinical settings.
Edge-Based Early Warning for High-Speed Boat Stability Monitoring Muhammad Asep Subandri; Jamal; Fajar Ratnawati; I Gusti Agung Putu Mahendra; Agus Tedyyana; Budhi Santoso
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 3 (2026): September 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i3.11866

Abstract

Purpose - This study aims to develop and evaluate an edge-based early warning prototype for monitoring the stability of high-speed boats using real-time motion data. Design/methods/approach – The study employs an engineering prototype validation design consisting of system requirement analysis, architecture design, implementation, and validation. The system integrates an IMU (MPU-6050) for motion sensing, a Raspberry Pi-based edge computing unit for real-time processing, rule-based classification (Normal/Warning/Critical), and an MQTT-based communication framework connected to the SHISTAMO dashboard. Prototype validation includes functional testing, platform integration, and operational monitoring using controlled scenarios and expert-labeled events. Findings - The results show that the prototype successfully performs end-to-end integration from sensing to visualization. The system achieved 90.4% classification accuracy, with high recall in detecting critical conditions (96.7%), ensuring reliable identification of high-risk events. The local alarm response time was 182 ms, while the dashboard update delay averaged 1.24 s, indicating near-real-time performance. Communication reliability was also high, with 98.8% data delivery success and 97.2% offline synchronization. Research implications/limitations – The findings demonstrate prototype-level feasibility; however, validation is limited to controlled scenarios and does not yet represent diverse sea conditions. The rule-based thresholds and comfort proxy require further calibration and validation through extended sea trials and reference instrumentation. Originality/value – This study contributes an integrated edge-based maritime monitoring prototype that combines motion sensing, offline-capable alarming, real-time telemetry, and fleet-level logging in a single system, specifically tailored to the operational needs of high-speed boats.
Perancangan Website Sistem Pakar Menentukan Tingkat Kemampuan dalam Public Speaking menggunakan Metode Extrime Programming Dila Anugrah; Fajar Ratnawati
SABER : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Vol. 2 No. 4 (2024): Oktober : Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/saber.v2i4.1744

Abstract

This research presents an expert system using the extreme programming method to determine the level of ability in public speaking. Public Speaking is an important speaking skill in many fields, but it is often difficult for individuals to evaluate their ability. The extreme programming method is used to provide a reliable level of workmanship in the public speaking system. The expert system will provide recommendations in the form of solutions, or strategies that can help individuals improve their public speaking skills. individuals in improving their public speaking skills. The solutions provided will be adjusted to the individual's ability level, so as to provide effective knowledge. The trust method used is the certainty factor method. The results displayed are information about level of public speaking ability, the level of confidence of an expert along with solutions that can be done next by website users.
Sistem Pakar Identifikasi Ras Kucing Menggunakan Metode Forward Chaining Bagus Riandi; Fajar Ratnawati; Eva Yumami
Jurnal Penelitian Rumpun Ilmu Teknik Vol. 3 No. 3 (2024): Agustus : Jurnal Penelitian Rumpun Ilmu Teknik
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juprit.v3i3.4250

Abstract

Cat breed identification is a complex process and requires an in-depth understanding of the physical and genetic characteristics of cats. In this study, a forward chaining method to identify cat breeds based on their morphological features. The forward chaining approach allows us to make logical and systematic inferences from the given facts. In this method, rules are built based on the common physical characteristics associated with each cat breed. These rules are then used to perform inference based on the given facts. This process is done iteratively until no additional rules can be applied. The results of this study show that the forward chaining method is effective in identifying cat breeds. By using the right features, cat breed identification has a high success rate. This method can be used as a tool for animal experts or cat lovers in recognizing cat breeds more accurately.
Co-Authors Agus Tedyyana, Agus Apri Siswanto Bagus Riandi Darni Kurniawati Tafanao Dila Anugrah Efendi, Akmar Elgamar Syam Fajri Profesio Putra I Gusti Agung Putu Mahendra Jamal Jaroji Jaroji Johny Custer Juniarto Muhamad Azren Muhammad Asep Subandri Nofia Zuriatin Rezki Kurniati, Rezki Rindi Devi Ruhaya Hayuni Santoso, Budhi Supendi Supendi Supendi Tengku Musri Yumami, Eva