Article Per Year (5 Year)
p-Index From 2021 - 2026
4.88
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Sistem Komputer TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Jurnal Ilmiah Kursor Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Edukasi dan Penelitian Informatika (JEPIN) JUITA : Jurnal Informatika Journal of Information Systems Engineering and Business Intelligence ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika JOIN (Jurnal Online Informatika) JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Informatika Wikrama Parahita : Jurnal Pengabdian Masyarakat Jurnal ULTIMATICS Journal of Computer Science and Informatics Engineering (J-Cosine) JURNAL CEMERLANG: Pengabdian pada Masyarakat Jurnal Rekayasa Hijau MIND (Multimedia Artificial Intelligent Networking Database) Journal KOMPUTA : Jurnal Ilmiah Komputer dan Informatika Jurnal Abdimas Berdaya : Jurnal Pembelajaran, Pemberdayaan dan Pengabdian Masyarakat Journal of Applied Data Sciences CONSEN: Indonesian Journal of Community Services and Engagement Jurnal Tera Scientific Journal of Informatics IPSSJ JuTISI (Jurnal Teknik Informatika dan Sistem Informasi) Jurnal Publikasi Teknik Informatika
Jasman Pardede
Program Studi Informatika, Institut Teknologi Nasional Bandung
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Automotive Engineering 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 Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions 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 Neuroscience Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 45 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 45 Documents
Search

 1   2   3   4   5 
The Impact of Balanced Data Techniques on Classification Model Performance Jasman Pardede; Dika Prasetia Pamungkas
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.3649

Abstract

Purpose: The aim of this study is to examine the impact of balanced data techniques on the performance of classification models. Methods: To balance the imbalanced dataset, several resampling techniques are employed: The Synthetic Minority Oversampling Technique (SMOTE), Borderline-SMOTE (B-SMOTE), and SMOTE and Edited Nearest Neighbors (SMOTE-ENN). Classification is then performed using both balanced and unbalanced datasets to evaluate the impact of resampling techniques on classification model performance. Result: This study proposes the SMOTE, B-SMOTE, and SMOTE-ENN techniques for generating synthetic data. Experimental results showed that re-sampling can improve model performance on KNN, Naive Bayes, and Decision Tree. The best-balanced data technique is the SMOTE-ENN. The second best is B-SMOTE, and the last is SMOTE. If compared to the unbalanced dataset, the SMOTE technique encourages increasing the performance of Accuracy, Precision, Recall, F1-Score, G-mean, and Curve-ROC respectively by 4.79%, 35.89%, 35.32%, 35.63%, 46.94%, and 34.89%, respectively on DT method. The B-SMOTE technique on the DT method improves the performance of Accuracy, Precision, Recall, F1-Score, G-mean, and Curve-ROC respectively by 5.62%, 36.45%, 35.88%, 36.19%, 47.40%, and 35.46% if compared to the unbalanced dataset. The SMOTE-ENN technique improves the performance of Accuracy, Precision, Recall, F1-Score, G-mean, and Curve-ROC respectively by 8.11%, 34.53%, 43.25%, 41.63%, 62.85%, and 42.91% if compared to the unbalanced dataset. Novelty: Based on the experiment results, the best-balanced data technique is the SMOTE-ENN. The SMOTE-ENN technique improves the performance of Accuracy, Precision, Recall, F1-Score, G-mean, and Curve-ROC.
UAV Imagery-Based Potential Forest Fire Detection Using YOLOv10 Jasman Pardede; Muhamad Rifki Pratama; Rizka Milandga Milenio
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1052

Abstract

Forest fire mitigation requires an early detection system that is both fast and reliable. This study presents a real-time potential forest fire detection system based on UAV imagery using the YOLOv10 object detection model. The main objective is to enhance the accuracy of detecting fire and smoke in aerial imagery and to minimize false alarms through hyperparameter optimization and data balancing strategies. The dataset used was compiled from Roboflow Universe and Kaggle, consisting of two object classes: fire and smoke, with a slight class imbalance (1329 fire and 1024 smoke). In total, 1,691 annotated images were used, covering various lighting conditions, smoke densities, camera angles, and geographic backgrounds, and were divided into training, validation, and test sets with a ratio of approximately 75:15:10. To address the class imbalance and visual variability, data augmentation techniques such as rotation, flipping, brightness adjustment, and noise addition were applied, along with loss weighting to improve learning performance for the minority smoke class. Model training was conducted using 24 hyperparameter configurations combining six optimizers, two batch sizes, and two learning rates. The best hyperparameters are NAdam optimizer, batch_size 24, and learning_rate 0.001.The best performance of accuracy, precision, recall, F1-score, mean IoU, and mAP were achieved at 0.879, 0.8705, 0.8575, 0.863, 0.7373, and 0.870, respectively. Real-time testing using a DJI Mini 4 Pro UAV with RTMP livestream input demonstrated stable and responsive detection, displaying bounding boxes, class labels, confidence scores, and a “POTENTIAL FOREST FIRE” indicator when both fire and smoke were detected simultaneously. These findings confirm that integrating UAV and YOLOv10 technologies provides an effective and adaptive approach for real-time early detection of potential forest fires.
Web-Based Financial Management System for HKBP Cimahi Church, Sisingamangaraja Street: Sistem Keuangan Gereja HKBP Cimahi Jalan Sisingamangaraja Berbasis Website Pardede, Jasman; Premitasari, Marisa; Perdinan, Rivan Dio; Al Fauzan, Farel Anugrah; Supriyandari, Listy Nuri; Sandia, Muhammad Sakha; Ramdani, Dadan
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.v6i1.2686

Abstract

transaction tracking, and limited financial transparency. This community service program (PKM) addresses the question of how a website-based financial system can improve the efficiency and transparency of financial management at HKBP Cimahi Sisingamangaraja Church. The position of this activity lies in the implementation and development of a church financial management system as a technological solution to existing administrative challenges. The system was developed using the waterfall method, which includes requirement analysis, system design and implementation, as well as testing and evaluation stages. The results of the implementation indicate that the website-based financial system is capable of centralizing financial data management, simplifying transaction recording processes, and enhancing the transparency of church financial management. These findings demonstrate that the adoption of a web-based financial system can effectively support more accountable and efficient financial administration within church organizations.
Pembelajaran Bahasa Isyarat Berbasis Cloud dan Machine Learning di PUSBISINDO Marisa Premitasari; Caecilia Sri Wahyuning; Fifi Herni Mustofa; Jasman Pardede; Muhammad Azhari; Ardi Fajar Maulana
JURNAL CEMERLANG: Pengabdian pada Masyarakat Vol 8 No 2 (2026): JURNAL CEMERLANG: Pengabdian Pada Masyarakat
Publisher : LP4MK STKIP PGRI Lubuklinggau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31540/jpm.v8i2.4309

Abstract

Keterbatasan media pembelajaran interaktif untuk Bahasa Isyarat Indonesia (BISINDO) menyulitkan proses belajar mandiri huruf abjad isyarat (A-Z), khususnya bagi pemula yang tidak memiliki akses langsung ke pengajar atau komunitas Tuli. Kegiatan PKM ini menghasilkan aplikasi web pembelajaran BISINDO yang memungkinkan pengguna mempelajari 26 huruf abjad isyarat secara mandiri dan mempraktikkannya langsung di depan kamera, dengan umpan balik otomatis dari model pengenalan gestur tangan. Sistem dibangun dengan arsitektur client-side: model klasifikasi citra MobileNetV3-Large yang di-fine-tune dari bobot ImageNet1K diekspor ke format ONNX dan dijalankan sepenuhnya di peramban (browser) pengguna melalui ONNX Runtime Web (WebAssembly), sehingga tidak memerlukan server inferensi dan menjaga privasi video pengguna karena tidak ada gambar yang dikirim keluar perangkat. Deteksi keberadaan tangan menggunakan MediaPipe HandLandmarker sebagai gerbang (gate) sebelum citra diteruskan ke model klasifikasi, mengurangi prediksi palsu saat tidak ada tangan di depan kamera. Proses pengembangan model melalui beberapa iterasi signifikan: perbaikan skema pembagian data (split) yang semula bocor akibat duplikasi augmentasi menaikkan akurasi validasi dari 27,6% menjadi 84,0%, dan penambahan pemotongan (crop) citra pada area bounding box tangan menaikkannya lebih lanjut hingga 90,4% (validasi) dan 84,7% (uji) untuk arsitektur Large. Aplikasi diuji secara fungsional pada mode latihan interaktif, di mana pengguna diberi umpan balik visual dan audio ketika berhasil memperagakan huruf target. Hasil kegiatan ini menunjukkan bahwa kombinasi model klasifikasi ringan berbasis mobile-oriented CNN dan inferensi on-device dapat menjadi solusi pembelajaran BISINDO yang ringan, dapat diakses melalui perangkat apa pun tanpa instalasi, dan tidak bergantung pada infrastruktur cloud untuk komputasi model.
Digital Transformation of Public Asset Management via Web-Based Lifecycle System for Diskominfo Kota Bandung Jasman Pardede; Noval Rizky Nugraha; Muhammad Zaki Mahran Mufid; Muhammad Mulyawan
Wikrama Parahita : Jurnal Pengabdian Masyarakat Vol. 10 No. 2 (2026): November 2026
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jpmwp.v10i2.11830

Abstract

Public asset management at Diskominfo Kota Bandung faces challenges related to manual administrative procedures, including data inconsistencies and difficulties in asset tracking. This community service activity aimed to introduce a prototype of the "Kelola Baraya" web-based asset lifecycle management system as a digital transformation initiative to support transparency and accountability in regional property management. The activity was conducted through field observations, stakeholder interviews, system development, and prototype demonstration sessions involving representatives from Diskominfo Kota Bandung. The developed prototype integrates QR Code-based asset identification, centralized monitoring dashboards, geotagging features, and multi-role validation workflows. Evaluation through demonstration and feedback sessions indicated that the proposed features were considered relevant to organizational needs and have the potential to support more structured and efficient asset management processes. The activity successfully introduced the concept of digital asset management and laid the foundation for future system implementation within the institution.
Co-Authors Abdullah, Syadda adlan chosyiyar rochman Afis Siswantini Ahmada, Marsa Akbar, Saiful Al Fauzan, Farel Anugrah Alfyansyah, Rangga Alpriatna Malik, Yuzzar Amal M, Ichlasul Amal, Irfan Ardi Fajar Maulana Asep Nana Hermana B, Mira Musrini Benhard Sitohang Bernovaldy, Muhammad Akbar Caecilia Sri Wahyuning Chazar, Chalifa Daffa A R, Muhammad Darmawan, Dicky Dea Kurniasih Dewi, Renita Dika Prasetia Pamungkas Dina Budhi Utami Dina Budhi Utami, Dina Budhi Dwi Adi Lenggana Putra Dwianto, Rio Ekklesia, Maleakhi Fadhillah Prasetyo, Rachma Fandi Fifi Herni Mustofa Galih Swarghani Ghixandra Julyaneu Irawadi HENDRI HARDIANSAH Hermana, Asep Nana Hilwa Athifah KLEB, SYAFIQ SALIM Luqman Yudhianto Luthfi Athallah, Rifqi Marisa Premitasari, Marisa Miftahuddin, Yusup Milenio, Rizka Milandga Mira Musrini B Muhamad Rifki Pratama Muhammad Akbar Bernovaldy Muhammad Azhari MUHAMMAD FAUZAN RASPATI Muhammad Mulyawan MUHAMMAD RIFALDI BADU Muhammad Zaki Mahran Mufid Noval Rizky Nugraha Nurhasanah, Youllia Indrawaty Nurrohmah, Desita Pakpahan, Ivan Perdinan, Rivan Dio Prameswari, Anindya Putra Riyanto, Aquila Putra, Dwi Adi Lenggana Raka Gemi Ibrahim Raka Satria, Marius Rawosi, Muhammad Fadlansyah Zikri Akhiruddin RAYYAN RAYYAN Renita Dewi Ridhwana M, Fadhlan Rijal, Khairul Rizka Milandga Milenio Rizka Milandga Milenio Rizka Milandga Milenio rochman, adlan chosyiyar Sandia, Muhammad Sakha Satria Darmawan, Kevin Setyaningrum, Anisa Putri Siswantini, Afis Supriyandari, Listy Nuri Swarghani, Galih Thalita Zharifa Nathania Ungkawa, U. Uung Ungkawa Yudhianto, Luqman Yudistira, Agil Yunastrian, Kurniandha Yusuf S, Muhammad