Sistem Monitoring Dan Estimasi Waktu Kedatangan Kendaraan Umum Berbasis GPS Dan IoT Di Kota Bekasi

Abstrak

Advances in Global Positioning System (GPS) and Internet of Things (IoT) technologies provide opportunities to improve public transportation services by providing real-time vehicle position information and Estimated Time of Arrival (ETA). One of the problems faced by public transportation users in Bekasi City is the limited availability of information regarding vehicle positions and arrival times, which may lead to uncertainty in waiting times. This study aims to design and develop a public transportation monitoring and arrival time estimation system based on GPS and IoT. The system development method employs the Software Development Life Cycle (SDLC) using the Waterfall model, which consists of requirements analysis, system design, implementation, testing, and maintenance. The system uses a GPS device installed on the vehicle to periodically obtain location coordinates, which are then transmitted over the Internet to a server using IoT technology. The vehicle's position, speed, and route data are subsequently processed to estimate the arrival time based on the distance and vehicle speed. Testing was conducted on seven public transportation trips along several routes in Bekasi City under varying traffic conditions. ETA performance was evaluated using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE). The test results showed an MAE of 1.286 minutes, an MAPE of 10.179%, and an RMSE of 1.363 minutes, with a difference of 1–2 minutes between the estimated and actual arrival times in the tested trips. GPS testing also demonstrated that the system was capable of acquiring and displaying vehicle positions on a digital map within the application, with a distance difference of approximately 0.01 km compared with Google Maps as the reference based on the test data. These results indicate that the system is capable of providing vehicle position information and arrival time estimates for the tested trips, although the number of tests was still limited. Future research could expand the number of trips and variations in traffic conditions and integrate real-time traffic data to improve the adaptability of ETA estimation.