Garuda - Garba Rujukan Digital

Prototype Alat Pendeteksi Kebakaran Berbasis Internet Of Things Dengan Aktifasi Flame Sensor Menggunakan Arduino Rizky Abrar, Alridho; Mariadi Kaharmen, Herman; Nur Hakim, Iman
Jurnal Keselamatan Transportasi Jalan (Indonesian Journal of Road Safety) Vol. 7 No. 2 (2020): JURNAL KESELAMATAN TRANSPORTASI JALAN (INDONESIAN JOURNAL OF ROAD SAFETY)
Publisher : Pusat Penelitian dan Pengabdian Masyarakat (P3M)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46447/ktj.v7i2.156

Kebakaran merupakan bencana yang dapat disebabkan oleh faktor manusia, faktor teknis maupun faktor alam yang tidak dapat diperkirakan kapan terjadinya. Internet of Things, atau dikenal juga dengan singkatan (IoT) merupakan sebuah konsep yang bertujuan untuk memperluas manfaat dari konektifitas internet yang tersambung secara terus-menerus. Dengan menggabungkan konsep Internet of Things kedalam suatu alat, akan mempermudah komunikasi sehingga lebih efektif. Metode penelitian yang digunakan merupakan jenis penelitian dan pengembangan atau Research and Development (R&D). Penelitian Research and Development (R&D) pada penelitian ini merupakan metode untuk menghasilkan dan menyempurnakan produk yang pernah diteliti sebelumnya yang hanya memakai satu sensor yaitu sensor asap. Pengujian responsifitas flame sensor dilakukan untuk mengetahui kinerja sensor, dilakukan 5 kali percobaan dengan titik yang berbeda dengan jarak ± 25 cm, semakin besar api yang diuji maka tingkat ke sensitifitasan akan semakin meningkat. Responsifitas sensor untuk melakukan pendeteksian asap dengan jarak maksimal terhadap sumber asap dalam penelitian ini yaitu 25 cm membutuhkan waktu 10,2 detik ini menunjukkan penempatan sensor pada jarak 25 cm terhadap sumber masih aman. Semakin banyak dan tebal asap yang dihasilkan objek yang diuji maka jangkauan sensor MQ-2 akan semakin jauh, berarti prototype berjalan sesuai program yang telah di rancang.

IoT-Based Dual-Sensor Vehicle Security System Using Piezoelectric and Glass-Break Detectors with GPS Tracking: Design and Performance Evaluation Zaidan Wafi Rohdyawan; M. Iman Nur Hakim; Raka Pratindy; Mokhammad Rifqi Tsani
Journal of Vocational, Informatics and Computer Education Vol 4, No 1 (2026): March 2026
Publisher : Academic Bright Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66053/voice.v4i1.421

Purpose – This study aims to develop an IoT-based vehicle security system using a dual-sensor architecture that integrates piezoelectric and glass-break sensors, complemented by GPS tracking, to detect glass-break–based theft attempts rapidly, accurately, and in real time.Methods – A Research and Development (R&D) approach was employed at the functional prototype stage, involving hardware design, ESP32 programming, vibration response testing, glass-break tests on tempered and tinted glass, GPS accuracy assessment across three environmental conditions, and validation of IoT notification response time via Telegram.Findings - An IoT-based vehicle security system integrating piezoelectric and glass-break sensors demonstrated clear signal separation between normal conditions (ADC < 500) and glass-break events (ADC > 1000), with no overlapping distributions observed during testing. The system achieved real-time detection with an average IoT notification response time of approximately 1.14 seconds and showed near-zero false alarm occurrence under controlled experimental conditions.Research implications – Although the prototype exhibits high sensitivity and specificity in controlled environments, system performance remains influenced by IoT network quality and GPS signal degradation in enclosed spaces. Testing was limited to one vehicle model and two glass types; therefore, further research is required, including large-scale field validation, evaluation in dynamic environments, and the implementation of advanced IoT security protocols.Originality – The main contribution of this study lies in addressing the research gap between prior works that predominantly utilized single-sensor or limited sensor combinations without robust acoustic–mechanical differentiation. The applied integration of piezoelectric and glass-break sensors within an IoT-based architecture establishes a cross-verification mechanism that significantly reduces false alarm potential and enhances detection reliability compared to previous approaches.

Real-Time Intelligent IoT-Based Drum Brake Temperature Monitoring System Maulana Yusuf Alkahfi; Raka Pratindy; M. Iman Nur Hakim; Nanang Okta Widiandaru
Journal of Vocational, Informatics and Computer Education Vol 4, No 1 (2026): March 2026
Publisher : Academic Bright Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66053/voice.v4i1.601

Purpose – This study addresses brake system failures in heavy vehicles caused by excessive thermal buildup in drum brakes. Existing monitoring systems rely on single-parameter sensing and lack early warning capabilities, thereby increasing the risk of brake fade and accidents. This study aims to develop a real-time monitoring system to improve safety. Methods: A Research and Development (R&D) approach was applied, including system design, implementation, and testing. The proposed system integrates a Raspberry Pi 4 Model B, Type K thermocouple, ESP32-C3 Super Mini, and GPS NEO-6M module. The data were transmitted via the Thingspeak IoT platform and displayed on a 7-inch TFT touchscreen. Experimental validation includes thermocouple calibration, GPS speed testing, and IoT latency measurement Findings – The thermocouple achieved a mean absolute error of 7.2°C and a percentage error of 3.4% (96.6% accuracy). The GPS speed measurement showed a 2.6% error (97.4% accuracy). IoT latency ranged from 1.2–2.0 s, with 100% data transmission success. The system reliably triggered alerts when the temperature exceeded 360°C, confirming effective real-time monitoring. Research implications: Limitations include dependence on Internet connectivity, environmental effects on sensors, and scalability challenges. Future work should focus on improving robustness and integrating predictive features. Originality – The developed system demonstrates reliable performance at the prototype level. However, the validation was conducted under controlled conditions using a single sensor and without vehicle load. Therefore, further validation under varying load conditions, road gradients, and multipoint brake measurements is required before practical large-scale deployment.

Design and Build an Intelligent Vehicle Access System Using Face Recognition and RFID-Based E-SIM Viky Dwi Nugraha; M Iman Nur Hakim; Ethys Pranoto; Faris Humami
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.2617

Purpose – This study aims to design and develop an intelligent vehicle access system that enhances security through a two-factor authentication mechanism integrating face recognition and RFID-based electronic driver identification (E-SIM). Design/methods/approach – The research adopts a Research and Development (R&D) approach, including system design, implementation, and evaluation. The system is built on a Raspberry Pi 4 platform and integrates face recognition using the Histogram of Oriented Gradients (HOG) method with RFID UID verification. Additional features include GPS-based tracking and Telegram-based real-time notifications. Performance evaluation is conducted using confusion matrix metrics and experimental testing under varying environmental conditions. Findings – The proposed system achieves 95% accuracy, 95.92% precision, 94% recall, and an F1-score of 94.95%. The system demonstrates good performance in preventing unauthorized access, with only two false acceptance cases. Performance remains stable under moderate lighting and short distances but decreases under low illumination and longer distances. The GPS module provides reliable tracking with an average positioning error of approximately 5.06 meters. In terms of real-time performance, the system exhibits an average latency of approximately 6.84 seconds per authentication cycle, which remains acceptable for practical vehicle access applications. Research implications/limitations – The system demonstrates strong performance as a functional prototype; however, it remains vulnerable to face spoofing and RFID cloning due to the absence of liveness detection and encrypted communication. Environmental factors such as lighting and distance also affect recognition accuracy. Originality/value – This study contributes by integrating biometric and possession-based authentication within a standalone embedded system, enhanced with IoT features for real-time monitoring. Unlike prior single-factor approaches, the proposed system improves security robustness while maintaining practical usability.

Short-Term Prediction of Bus Station Fleet Number Using a Combination of BiLSTM Models Joko Siswanto; Ainun Rahmawati; Untung Rahardja; Nanda Dwi Putra; Muhammad Iman Nur Hakim; Tito Pinandita; Ilham Bagus Prasetyo
Automotive Experiences Vol. 8 No. 1 (2025)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/ae.13402

Predicting the number of bus station fleets requires a holistic approach, using sophisticated data analysis techniques and appropriate predictive modeling. Short-term predictions of bus station fleet numbers are proposed based on the best MAPE evaluation values ”‹”‹from the comparison of the Bi-LSTM, BiLSTM-CNN, BiLSTM-Transformer, BiLSTM-Informer, and BiLSTM-Reformer models. The dataset used is in the form of a CSV consisting of 6 types of arrivals and departures of the Giwangan City Yogyakarta type A bus station fleet from 01/01/2021 to 09/30/2023. The best prediction model was found in BiLSTM-Transformers based on a MAPE value of 0.2211 with a relatively fast time (00:00:52) compared to BiLSTM, BiLSTM-CNN, BiLSTM-Informer, and BiLSTM-Reformer. The BiLSTM-Transformer model can short-term predict 6 types of fleet arrivals and departures at the bus station in the next 30 days. The peak of the bar and curve is at 0 which means the proposed prediction model is very accurate. There is 1 strong positive correlation, 2 weak positive correlations, 2 strong negative correlations, 8 weak negative ones, and 2 uncorrelated ones. Prediction results can be used to support short-term decision making in fleet planning and management based on the dynamics of community mobility.

Multimodal vehicle security system based on internet of things: integration of fingerprint authentication, face recognition, and GPS tracking Dodik Wahyu Wiratama; Muhammad Iman Nur Hakim; Helmi Wibowo; Arief Novianto
Jurnal Polimesin Vol 24, No 3 (2026): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jpl.v24i3.9032

The surge in vehicle theft in Indonesia has exposed the weaknesses of conventional security systems such as mechanical keys and immobilizers. This study aims to develop an IoT-based vehicle security system integrating fingerprint authentication, facial recognition, and GPS tracking, and evaluates its performance quantitatively. The system was tested on a Toyota Avanza with six users. Facial recognition used a MobileNetV2 CNN model trained with 1,200 local images across four classes (registered, unregistered, masked, and sunglasses) using a learning rate of 0.001, batch size of 32, and 50 epochs. Fingerprint authentication employed minutiae extraction with Euclidean distance matching. The system successfully implemented two-factor authentication. Facial recognition achieved an accuracy of 94.2%, with a False Acceptance Rate (FAR) of 2.1% and a False Rejection Rate (FRR) of 3.7%. Fingerprint authentication reached 91.5% accuracy, with FAR of 4.3% and FRR of 4.2% under dry finger conditions, while FRR increased to 18.5% for scratched fingers. The system detected unregistered users and triggered engine shutdown while sending photos and GPS coordinates through Telegram. GPS tracking achieved 99.3% positional accuracy. The results demonstrate the feasibility of multimodal IoT-based vehicle security, although performance remains sensitive to lighting conditions, face coverings, and finger surface conditions.

Stereo Camera-Based Motor Vehicle Dimension Measurement with Luxmeter-Based Light Intensity Detection Ageng Sudarma; Muhammad Iman Nur Hakim; Nurul Fitriani; Siti Shofiah; Nanang Okta Widiandaru
Building of Informatics, Technology and Science (BITS) Vol 8 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v8i1.10012

Over Dimension and Over Loading (ODOL) vehicles require accurate and efficient dimension inspection systems to support transportation safety and regulatory compliance. This study proposes an automatic motor vehicle dimension measurement system based on stereo vision integrated with YOLOv8 object detection and luxmeter-based illumination monitoring. The system was developed using a Research and Development (R&D) approach involving stereo camera calibration, hardware-software integration, experimental testing, and validation against manual measurements. Two Logitech C270 USB cameras with a fixed 50 cm baseline were calibrated using a 9 × 6 checkerboard pattern and processed using OpenCV and Python. Vehicle and wheel objects were detected using YOLOv8 models with stereo disparity estimation performed using Semi-Global Block Matching (SGBM) and triangulation methods to calculate Overall Length (OAL), Front Overhang (FOH), Wheelbase (WB), Rear Overhang (ROH), and Overall Height (OAH). Environmental lighting conditions were monitored using a luxmeter under illumination ranges of 5,000-100,000 lux. Experimental results showed a stereo calibration success rate of 96% from 100 stereo image pairs. The developed system achieved average measurement accuracies of 98.58%, 98.92%, and 98.89% at testing distances of 7 m, 8 m, and 9 m, respectively, while the highest accuracy of 99.44% was obtained at the T_8M_LC configuration under stable illumination conditions. Operational efficiency analysis showed that the automatic measurement process, including image acquisition and computational processing, reduced total measurement time from 187 seconds in manual measurements to 5 seconds in the automated system, corresponding to an efficiency improvement of 97.32%. The results show that the proposed stereo vision system provides accurate, efficient, and lighting-robust vehicle dimension measurements suitable for automated motor vehicle inspection applications.

Object Detection of Motor Vehicle Suspension Systems Based on the YOLOv8 Algorithm: Supporting Sustainable Industry and Innovation (SDG 9) Helmi Wibowo; Nurul Muzakki Rihhadatul ‘Aisy; Muhammad Iman Nur Hakim; Mokhammad Rifqi Tsani; Setya Wijayanta
Journal of Current Studies in SDGs Vol. 3 No. 2 (2027): June
Publisher : Sekolah Tinggi Agama Islam Sabilul Muttaqin Mojokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63230/jocsis.3.2.192

Objective: To develop an object detection system for identifying motor vehicle suspension system components using the YOLOv8 algorithm. Specifically, this study focused on improving the efficiency and accuracy of undercarriage inspection processes, which are commonly conducted manually and require technical knowledge to recognize suspension components and detect potential damage. This research contributes to automotive inspection innovation and supports the development of sustainable industrial technology in accordance with Sustainable Development Goal 9 (Industry, Innovation, and Infrastructure). Method: The study employed a computer vision-based approach using the YOLOv8 object detection algorithm for recognizing suspension system components in motor vehicles. The dataset consisted of 1000 suspension system images collected from mandatory vehicle inspection activities at motor vehicle testing facilities. Results: The results showed that the YOLOv8-based detection model could identify suspension system components with an accuracy of up to 95%. Furthermore, the trained model successfully detected oil leakage damage on shock absorber components with an accuracy of 92%. The evaluation results indicate that the proposed system can effectively recognize suspension components under different inspection conditions and provide reliable assistance for vehicle undercarriage inspection processes. Novelty: The study provides a novel implementation of the YOLOv8 deep learning algorithm for automated suspension system inspection in motor vehicles by integrating computer vision technology into the vehicle testing process. The developed system contributes to automotive technology innovation and supports the advancement of smart inspection infrastructure in line with SDG 9 (Industry, Innovation, and Infrastructure).

Pengaman Sistem Kelistrikan Arus Bolak-Balik Pada Inverter Bus Muhammad Iman Nur Hakim; Reza Stefano
RESISTOR (Elektronika Kendali Telekomunikasi Tenaga Listrik Komputer) Vol. 9 No. 1 (2026): RESISTOR (Elektronika Kendali Telekomunikasi Tenaga Listrik Komputer)
Publisher : Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/resistor.9.1.1-8

Kebakaran akibat arus pendek sistem kelistrikan dapat menimbulkan kerugian besar, terutama pada kendaraan seperti bus. Salah satu penyebab utamanya adalah penggunaan daya yang tidak sesuai dan instalasi listrik yang kurang aman. Penelitian ini mengembangkan alat pengaman sistem kelistrikan untuk mendeteksi dan mengamankan aliran listrik AC pada kendaraan, khususnya bus, guna mencegah kebakaran akibat arus pendek. Alat ini menggunakan sensor arus ACS712 yang terhubung ke mikrokontroler ESP32 dan relay, serta dilengkapi dengan LCD, LED, dan modul DFPlayer Mini sebagai sistem peringatan visual dan suara bagi pengemudi. Penelitian dilakukan dengan metode Research and Development (R&D) menggunakan model ADDIE (Analysis, Design, Development, Implementation, Evaluation). Sistem memantau arus dari tiga beban secara real-time melalui LCD. Jika arus melebihi batas yang ditentukan, maka relay akan memutus aliran listrik, LED akan menyala, dan DFPlayer Mini mengeluarkan suara peringatan. Sistem kembali normal setelah tombol reset ditekan. Pengujian dilakukan dalam dua kondisi: normal dan arus berlebih. Hasil menunjukkan alat berfungsi efektif memutus aliran saat terjadi arus lebih. Selain itu, akurasi pembacaan sensor ACS712 dibandingkan ampere meter sangat baik, dengan selisih maksimal hanya 0,02A pada suhu 25–30°C dan persentase kesalahan kurang dari 1%.

Object Detection of Motor Vehicle Suspension Systems Based on the YOLOv8 Algorithm: Supporting Sustainable Industry and Innovation (SDG 9) Helmi Wibowo; Nurul Muzakki Rihhadatul ‘Aisy; Muhammad Iman Nur Hakim; Mokhammad Rifqi Tsani; Setya Wijayanta
Journal of Current Studies in SDGs Vol. 3 No. 2 (2027): June
Publisher : Sekolah Tinggi Agama Islam Sabilul Muttaqin Mojokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63230/jocsis.3.2.192

Objective: To develop an object detection system for identifying motor vehicle suspension system components using the YOLOv8 algorithm. Specifically, this study focused on improving the efficiency and accuracy of undercarriage inspection processes, which are commonly conducted manually and require technical knowledge to recognize suspension components and detect potential damage. This research contributes to automotive inspection innovation and supports the development of sustainable industrial technology in accordance with Sustainable Development Goal 9 (Industry, Innovation, and Infrastructure). Method: The study employed a computer vision-based approach using the YOLOv8 object detection algorithm for recognizing suspension system components in motor vehicles. The dataset consisted of 1000 suspension system images collected from mandatory vehicle inspection activities at motor vehicle testing facilities. Results: The results showed that the YOLOv8-based detection model could identify suspension system components with an accuracy of up to 95%. Furthermore, the trained model successfully detected oil leakage damage on shock absorber components with an accuracy of 92%. The evaluation results indicate that the proposed system can effectively recognize suspension components under different inspection conditions and provide reliable assistance for vehicle undercarriage inspection processes. Novelty: The study provides a novel implementation of the YOLOv8 deep learning algorithm for automated suspension system inspection in motor vehicles by integrating computer vision technology into the vehicle testing process. The developed system contributes to automotive technology innovation and supports the advancement of smart inspection infrastructure in line with SDG 9 (Industry, Innovation, and Infrastructure).

Title

Found 20 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 20 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 20 Documents
Search