Assessing the Impact of Adaptive Traffic Signals on Manhattan’s Traffic Pattern Using Origin-Destination Analysis and YOLOv8 Real-Time Detection Model
DOI:
https://doi.org/10.62051/z8djjw91Keywords:
Adaptive Traffic Signals; Traffic Volume Redistribution; Origin–Destination Analysis; YOLOv8; Urban Mobility; Manhattan; Smart Transportation Systems.Abstract
Adaptive Traffic Signal Systems (ATS) have been implemented in Manhattan in an effort to reduce congestion and enhance roadway efficiency, yet their broader impacts on redistributions of traffic have been insufficiently explored. This research estimates the long-term effects of ATS by leveraging the combined application of three supporting methodologies: (1) a comparison of traffic volumes between 2011 and 2018, (2) an Origin–Destination (O-D) examination of trip distributions, and (3) in real-time vehicle detection via the YOLOv8 deep learning algorithm. This research finds a systematic shift and redistribution in traffic volumes between 2011 and 2018. Notably decreased volumes were observed in central north–south corridors like 5th and 6th Avenues, while coastal highways, such as the FDR Drive and West Side Highway, showed considerable increases. O-D analysis put these changes into context by demonstrating that origins have steadily concentrated in outer boroughs while destinations shifted from Lower Manhattan to Midtown West. Finally, YOLOv8-based examination of 2024 traffic data verified that these patterns continue to exist in the mature ATS network.
Downloads
References
[1] S. Maadi, S. Stein, J. Hong, and R. Murray-Smith, “Real-time adaptive traffic signal control in a connected and automated vehicle environment: Optimisation of Signal Planning with Reinforcement Learning Under Vehicle Speed Guidance,” Sensors, vol. 22, no. 19, Oct. 2022. DOI: https://doi.org/10.3390/s22197501
[2] M. T. Rafique, A. Mustafa, and H. Sajid, “Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion,” arXiv preprint arXiv:2408.15751, 2024.
[3] I. Kington, “Deploying advanced traffic signal controllers and an adaptive decision support system for 110 blocks of New York City led to a 10 percent decrease in travel times.,” New York Minutes: NYC’s Adaptive Congestion Management System, 2012.
[4] New York City Department of Transportation (NYC DOT), “Automated Traffic Volume Counts: NYC open data,” Automated Traffic Volume Counts | NYC Open Data, https://data.cityofnewyork.us/Transportation/Automated-Traffic-Volume-Counts/7ym2-wayt/about_data (accessed Oct. 22, 2024).
[5] TransCore, “New York City Launches Nation’s Most Sophisticated Active Traffic Management System Powered by TransCore’s TransSuite® Traffic Management Software and RFID Technology,” TransCore, 2022. [Online]. Available: https://transcore.com/new-york-city-launches-nations-most-sophisticated-active-traffic-management-system-powered-by-transcores-transsuite-traffic-management-software-and-rfid-technology.html.
[6] A. Amar and R. Khashashina, “TransSuite Traffic Control System: A Case Study of New York City,” presentation, NYCDOT, 2018. [Online]. Available: https://lynda-kinns-abrp.squarespace.com/s/Ali_Amar_and_Rami_Khashashina_Presentation_Updated_5-23pptx.pdf.
[7] D. Correa and J. C. Falcocchio, “A data-driven case study following the implementation of an Adaptive Traffic Control System in Midtown Manhattan,” Journal of Transportation Engineering, Part A: Systems, vol. 148, no. 4, Apr. 2022. DOI: https://doi.org/10.1061/JTEPBS.0000645
[8] J. C. Falcocchio and E. Prassas, “Development of traffic performance metrics using real-time traffic data: University Transportation Research Center,” Development of Traffic Performance Metrics Using Real-time Traffic Data | University Transportation Research Center, https://www.utrc2.org/research/projects/development-traffic-performance-metrics-using-real-time-traffic-data (accessed Oct. 7, 2024).
[9] B. Khalili and A. W. Smyth, “SOD-yolov8—enhancing yolov8 for small object detection in aerial imagery and traffic scenes,” Sensors, vol. 24, no. 19, p. 6209, Sep. 2024. DOI: https://doi.org/10.3390/s24196209
[10] A. Nasri, C. Carrion, L. Zhang, and B. Baghaei, “Using propensity score matching technique to address self-selection in transit-oriented development (TOD) areas,” Transportation, vol. 47, no. 1, pp. 359 – 371, May 2018. DOI: https://doi.org/10.1007/s11116-018-9887-2
[11] F. Dai, M. Diao, and T. F. Sing, “A two-dimensional propensity score matching approach to estimating the treatment effect of urban rail transit lines on Vehicle Travel,” Transportation, vol. 51, no. 3, pp. 853 – 873, Nov. 2022. DOI: https://doi.org/10.1007/s11116-022-10360-2
[12] X. Ma, A. Karimpour, and Y.-J. Wu, “Eliminating the impacts of traffic volume variation on before and after studies: A causal inference approach,” Journal of Intelligent Transportation Systems, pp. 1 – 15, Aug. 2023. DOI: https://doi.org/10.1080/15472450.2023.2245327
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Transactions on Engineering and Technology Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
