SISTEM PENDUKUNG KEPUTUSAN PENGIRIMAN BUS BERBASIS AIOT MENGGUNAKAN INTEGRASI YOLOV8 DAN GOOGLE DISTANCE MATRIX API

Arinal Dzikrul Haqqy Amir; Raihan Evanza; Vitri Tundjungsari; Eric  Julianto

doi:10.31539/ywcqtg69

Authors

Arinal Dzikrul Haqqy Amir Universitas Esa Unggul
Raihan Evanza Universitas Esa Unggul
Vitri Tundjungsari Universitas Esa Unggul
Eric Julianto Universitas Esa Unggul

DOI:

https://doi.org/10.31539/ywcqtg69

Abstract

Kalkulasi penumpang dan estimasi kepadatan kerumunan yang akurat memainkan peran penting dalam sistem transportasi publik cerdas untuk meningkatkan keselamatan, kualitas layanan, dan efisiensi operasional. Pendekatan berbasis visi yang memanfaatkan model deep learning, khususnya You Only Look Once (YOLO), telah diadopsi secara luas untuk deteksi dan pelacakan penumpang secara real-time karena kecepatan deteksi dan akurasinya yang tinggi. Namun, tantangan seperti oklusi, variasi skala, dan sudut pandang kamera yang terbatas tetap menjadi kendala signifikan, terutama di halte bus yang padat dan lingkungan transportasi umum. Untuk mengatasi keterbatasan ini, studi terbaru telah mengintegrasikan arsitektur Internet of Things (IoT) dengan analitik video untuk memungkinkan pemantauan arus penumpang secara berkelanjutan. Dalam penelitian ini, deteksi kerumunan berbasis YOLO dikombinasikan dengan Google Distance Matrix API untuk mengestimasi waktu tempuh dan jarak antar halte bus, sehingga memungkinkan rekomendasi pengiriman armada otomatis berdasarkan kondisi kepadatan secara real-time. Kerangka kerja berbasis AIoT yang diusulkan mendukung pengambilan keputusan berbasis data untuk operasional bus cerdas, meningkatkan responsivitas, mengurangi penumpukan penumpang, serta mengoptimalkan penjadwalan transportasi publik.

Kata Kunci: AIoT-Enabled Public Transport Surveillance, YOLOv8, Sistem Transportasi Cerdas, Estimasi Kepadatan Kerumunan Real-Time, Google Distance Matrix API.

References

Paganelli, M. G., Gallo, M., Massenio, P. R., & Naso, D. (2025). Integrated passenger flow analysis and street-level monitoring for public transport management using deep learning and IoT. IEEE Access, 13, 143401–143413.

Qin, Y. D., Li, X. W., He, D., Zhou, Y., & Li, L. (2024). RLGS-YOLO: An improved algorithm for metro station passenger detection based on YOLOv8. Engineering Research Express, 6(4), 045095.

Pronello, C., & Garzón Ruiz, X. R. (2023). Evaluating the performance of video-based automated passenger counting systems in real-world conditions: A comparative study. Sensors, 23(18), 7719.

Rakhymova, A., Mussina, A., Aubakirov, S., & Trigo, P. (2024). Creation of a high-precision, single-board computer-based intelligent passenger counting system. Procedia Computer Science, 241, 212–219.

Kim, H., Sohn, M. K., & Lee, S. H. (2022). Development of a real-time automatic passenger counting system using head detection based on deep learning. Journal of Information Processing Systems, 18(3), 428–442.

Kim, K. H., An, T. K., & Kim, S. (2025). Estimating invisible passenger count using CCTV footage: An approach combining object detection models and machine learning. IEEE Access, 13, 152131–152147.

Votis, K. (2024). Improving passenger detection with overhead fisheye imaging. IEEE Access, 12, 66237–66247.

Hossain, S., Islam, M., & Rahman, A. (2022). Analyzing terrific traffic in urban areas: A small step towards bringing order. Computing and Informatics, 41(2), 571–589.

Abdulhameed, O. (2025). API-based dynamic programming model and optimization of vehicle routing: Cases of fluctuations in demand, traffic, capacity, and availability. Journal of Project Management, 10(4), 613–628.

Wang, F., & Xu, Y. (2011). Estimating O–D travel time matrix by Google Maps API: Implementation, advantages, and implications. Annals of GIS, 17(4), 199–209.

Chavan, P., et al. (2025). Leveraging real-time data: A location-based ambulance booking and tracking system with geofencing. Journal of Integrated Science and Technology, 13(2), 1–9.

[Author Name Missing] (2022). Near real-time spatial and temporal distribution of traffic emissions in Bangkok using Google Maps Application Program Interface.

Shibghatullah, A. S., Jalil, A., Wahab, M. H. A., Ng, J., & Soon, P. (2022). Vehicle tracking application based on real time traffic. International Journal of Electrical and Electronic Engineering & Telecommunications, 11(1), 67–73.

Terven, J., & Cordova-Esparza, D. M. (2023). A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716.

Mishra, A., & Ray, A. K. (2020). IoT cloud-based cyber-physical system for efficient solid waste management in smart cities: A novel cost function based route optimisation technique for waste collection vehicles using dustbin sensors and real-time road traffic informatics. IET Cyber-Physical Systems: Theory & Applications, 5(4), 330–341.

Kubitza, D. O., & Weßling, K. (2025). Decisions during the transition to higher education. Journal for Educational Research Online, 17(1).

Kotelnikova, E., Frahm, K. M., & Shepelyansky, D. L. (2022). Fibrosis protein-protein interactions from Google matrix analysis of MetaCore network. PLOS ONE, 17(5), e0267425.

Mancuso, N., & Sullivan, P. S. (2025). Methods for estimating public transit travel times to healthcare services as a measure of equitable healthcare access. Annals of Epidemiology, 111, 24–29.

Yang, B., Cao, J., Liu, X., Wang, N., & Lv, J. (2023). Edge computing based real-time passenger counting using a compact convolutional neural network. IEEE Transactions on Intelligent Transportation Systems.

Delzanno, G., et al. (2023). Automatic passenger counting on the edge via unsupervised clustering. Sensors, 23(15), 6821.