Nihayatus Sa'adah
Politeknik Elektronika Negeri Surabaya

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

GPS-Based Proximity Detection System Between Ship and Buoy for Marine Navigation Muhammad Edo Listiawan; Nihayatus Sa'adah; Nailul Muna; Karimatun Nisa'; Faridatun Nadziroh
Journal of Communication Systems, Networks, and Security Vol. 1 No. 1 (2026): April
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jcsns.v1i1.52

Abstract

Maritime navigation safety remains a major concern, especially for small vessels that lack advanced navigation aids such as radar or AIS. This study proposes a proximity detection system between a ship and a buoy using GPS data, LoRa communication, and ThingsBoard visualization. The ship node periodically transmits its coordinates through LoRa. In contrast, the buoy node receives the ship position, reads its own GPS coordinates, calculates the separation distance using the Haversine formula, and determines the system status as SAFE or ALERT based on a 50 m threshold. The processed telemetry is then forwarded to a gateway and visualized in real time on ThingsBoard. Experiments were conducted at distances of 10-100 m under two scenarios, with and without an obstacle. In the open-area condition, the system achieved an average percentage error of 3.42%, a mean absolute error (MAE) of 1.82 m, and a root mean square error (RMSE) of 2.47 m. Under obstacle conditions, the average percentage error increased to 24.07%, with MAE and RMSE values of 6.36 m and 6.93 m, respectively. Communication performance remained stable, with a 200-230 ms delay, RSSI values in the good category, and packet loss between 0% and 10%. These results show that the proposed system can provide an affordable early-warning solution for ship-buoy proximity monitoring.
YOLO-Based Vehicle Detection and Classification for Multi-Lane Free Flow Systems Nihayatus Sa'adah; Faridatun Nadziroh; Rahardhita Widyatra Sudibyo; Haniah Mahmudah; Fitri Fitriah; Hari Wahjuningrat Suparno; Muhammad Hendra Syahputra
Journal of Electrical and Intelligent Systems Vol. 1 No. 2 (2026): September
Publisher : Politeknik Elektronika Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.68129/jeis.v1i2.6

Abstract

Multi-Lane Free Flow (MLFF) systems have emerged as a promising approach to reducing congestion at toll gates by enabling uninterrupted toll transactions without requiring vehicles to stop. To support this implementation, this study proposes a YOLOv9-based vehicle detection and classification system optimized using grid search and the SGD optimizer. The proposed system is designed for edge computing deployment and evaluated in a real multi-lane toll environment using an NVIDIA Jetson AGX Orin device. Experimental results show that the optimized model achieves a mean Average Precision at IoU threshold 0.50 (mAP@50) of 92.6%, an F1-score of 92.0%, and an inference time of 70.8 ms, corresponding to 14.1 FPS. These results indicate that the proposed system provides a balanced trade-off between detection accuracy and computational efficiency for edge-based MLFF applications. Unlike previous studies that primarily evaluated vehicle classification models using offline datasets, this study includes implementation and testing in a real multi-lane toll scenario. The findings demonstrate the potential of YOLO-based vehicle detection and classification to support practical MLFF deployment, although further evaluation under more diverse traffic, lighting, and environmental conditions is still required.