Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Jurnal Telkommil
Yudhi Darmawan
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
RANCANG BANGUN LESAN TEMBAK MENGGUNAKAN LASER SPOT BERBASIS IMAGE PROCESSING: Telekomunikasi Maulana Doni Handoyo; Gatut Yulisusianto; Yudhi Darmawan
Jurnal Telkommil Vol 5 No 1 (2024): Jurnal Telkommil
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54317/kom.v5i1.445

Abstract

Latihan menembak sangat penting bagi aparat penegak hukum maupun tentara. Saat ini, masih banyak latihan menembak menggunakan cara konvensional dalam perhitungan nilainya. Penelitian ini akan merancang dan mengimplementasikan sistem lesan tembak menggunakan sinar laser sebagai objek pengganti peluru. Pada penelitian ini perhitungan skor otomatis juga diterapkan menggunakan image processing. Perancangan tersebut bertujuan agar mempermudah para penembak dalam melakukan latihan menembak. Dengan menerapkan metode HSV (Hue Saturation Value) colour segmentation, penelitian ini telah berhasil mendeteksi sinar laser. Proses deteksi lingkaran penilaian guna melakukan perhitungan skor akhir pada kertas target telah dijelaskan pada penelitian ini. Hasil pengujian menunjukkan nilai yang cukup akurat dalam mendeteksi sinar laser dan menghitung skor.
Intelligent System for Real-Time Weapon and Combat Equipment Detection Based on Computer Vision for Military Base Security: Rekayasa Keamanan Siber Yudhi Darmawan; Ilyas Hasmi; Robianto Herdana Sukirno
Jurnal Telkommil Vol 6 No 2 (2025): Jurnal Telkommil
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54317/kom.v6i2.599

Abstract

This research proposes an intelligent security system based on computer vision for real-time detection of weapons and military equipment in guard posts and military bases. The primary objective is to strengthen early warning capabilities by automatically identifying objects resembling firearms, knives, or combat gear through surveillance cameras. The system employs convolutional neural networks (CNN) for object classification and detection, integrated with a real-time alert mechanism to notify security personnel when suspicious items are detected. The method includes dataset collection of various weapon and combat equipment images, preprocessing, model training using YOLOv8, and evaluation with precision, recall, and F1-score metrics. Experimental results demonstrate that the system can accurately recognize specific military-related objects with high detection speed, ensuring reliable performance in real-time monitoring scenarios. The findings highlight the potential application of artificial intelligence in enhancing situational awareness and proactive security measures in military environments. This study concludes that the implementation of computer vision-based intelligent detection systems can significantly improve the effectiveness of base and post security operations, providing timely alerts to prevent potential threats
Implementasi Sistem Konfigurasi Dasar Mikrotik Berbasis Desktop Wizard dengan Antarmuka Grafis untuk Setup Jaringan: Rekayasa Keamanan Siber dpurwanto; Yudhi Darmawan; Transisma Budiarta
Jurnal Telkommil Vol 7 No 1 (2026): Jurnal Telkommil
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The configuration of MikroTik RouterOS devices through Winbox is still done manually with a modular-technical interface, which is time-consuming, error-prone, and difficult for non-technical users. This study aims to design and implement a desktop wizard application with a graphical user interface (GUI) for basic MikroTik configuration, utilize the RouterOS API for snapshot-based automation, and compare the ease of use and efficiency between the wizard system and manual Winbox configuration. The application was developed using Python with CustomTkinter as the GUI framework and communicates with MikroTik devices via RouterOS API on TCP port 8728. The system development follows the Waterfall method, covering requirements analysis, system design, implementation, and testing phases. Testing was conducted using Black Box Testing for functionality verification and System Usability Scale (SUS) for usability measurement, along with configuration time comparison between the wizard system and manual Winbox. Black Box Testing results show that all 8 configuration modules function correctly with a 100% success rate. The SUS evaluation yielded an average score of 78.5, categorized as “Acceptable (Good).” Time comparison testing demonstrates that the wizard system reduces configuration time by an average of 58.3% compared to manual Winbox configuration. This research concludes that the desktop wizard application effectively simplifies MikroTik configuration, provides snapshot-based rollback capability, and significantly improves both ease of use and efficiency for network administrators.
Implementation Of Random Forest Algorithm On Youtube Comment Sentiment Analysis Regarding Global Conflict Issues For Early Detection Of Psychological Threats: Rekayasa Keamanan Siber jepripanjaitan; Yudhi Darmawan; Asep Suryanta
Jurnal Telkommil Vol 7 No 1 (2026): Jurnal Telkommil
Publisher : Pustaka Poltekad

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The spread of provocative narratives on social media during global tensions poses a psychological threat to national stability. This study aims to classify public sentiment regarding World War 3 issues using the Random Forest algorithm to support cyber defense readiness. Data was collected via YouTube API focusing on relevant news channels, preprocessed using TF-IDF, and classified into positive, negative, and neutral categories. The Random Forest model was configured with 100 estimators and evaluated using 5-fold cross-validation. The results show that Random Forest achieved an accuracy of [Isi % Accuracy] with higher precision compared to other methods. Negative sentiment dominated by fear and uncertainty indicates potential vulnerability to psychological operations. It is concluded that this model can serve as an early warning system for monitoring information warfare threats.
Co-Authors Asep Suryanta dpurwanto Gatut Yulisusianto Ilyas Hasmi jepripanjaitan Maulana Doni Handoyo Robianto Herdana Sukirno Transisma Budiarta