Traffic Management with Algorithm Analysis Alvin F. Casupas, Jonard Klent C. Estrella, Jeff Lendelle T. Jacob, Hosea A. Paulate and James Matthew G. Vargas

Bachelor's Thesis

College of Industrial Technology.-- Bachelor of Engineering Technology major in Computer Engineering Technology (Non-Stem) Technological University of the Philippines 2024.

Includes bibliographic references and index.

As urban traffic management becomes more complex and requires such solutions of
congestion decreasing, environmental impacts and increasing road safety, innovative
solutions are needed. The research of this thesis is presented through the development and
implementation of a Traffic Management System with Algorithm Analysis to improve the
urban mobility by optimizing the traffic flow. The system is real time traffic monitoring
and analytics using YOLOv11n, advanced machine learning algorithms, that utilize
Raspberry Pi based hardware. The most important features involve vehicle detection from
live video feeds and a data visualization web platform for the user. The system was
designed to be both scalable and integratable, that is, it was thought should work even when
running alongside other infrastructure. This work helps towards technological
advancement of infrastructure, towards sustainable and efficient urban transportation
systems which are aspired by United Nations Sustainable Development Goals (SDGs) 9
and 11. The results of evaluation showed great traffic flow efficiency improvement,
congestion reduction, and better data driven traffic management disposition for traffic
management authorities. This thesis research shows feasibility to build more intelligent
and more sustainable urban transport system with the help of Internet of Things (IoT)
devices and machine learning.
Keywords: Traffic Management System, Raspberry Pi, YOLOv11n, Machine Learning,
Internet of Things, Urban Mobility, Real-Time Monitoring, Sustainable Development
Goals, Smart Cities, Intelligent Transportation