{"id":{"repo_id":"alabama","oai_identifier":"oai:ir.ua.edu:123456789/15380"},"canonical_url":"https://search.dev.ndltd.org/etd/alabama/oai:ir.ua.edu:123456789/15380","repository":{"repo_id":"alabama","name":"University of Alabama","base_url":"https://ir-api.ua.edu/oai/request"},"display":{"title":"Advances in Traffic Signal Operations Management: Machine Learning Measurement and Transition Improvements Through High-Resolution Data","abstract":"Traffic signal management plays a crucial role in optimizing traffic flow, reducing congestion, and improving travel time reliability at signalized intersections. This dissertation focuses on three key areas of research that aim to enhance the efficiency of traffic signal operations through the integration of advanced technologies and data-driven approaches. First, the study compares traditional traffic delay measurement methods, specifically the Highway Capacity Manual (HCM) methodology, with a Machine Learning Vision System (MLVS). This comparison acknowledges the HCM's reliability in traffic analysis while highlighting the potential of MLVS in capturing nuanced traffic patterns and improving signal performance metrics. Second, the dissertation explores the use of Signal Performance Measures (SPM) data combined with machine learning models to estimate turning movement counts at intersections. Various models were tested, and XGBoost emerged as the most effective, demonstrating higher accuracy than the other models. This novel approach offers a practical solution for traffic engineers seeking to obtain turning movement count data at an intersection for analysis with limited data collection infrastructure. Third, the research introduces a mathematical framework for optimizing signal transitions across coordinated intersections. By adjusting collective offsets at multiple intersections, the framework reduced total time to coordination by over 60%, after it was validated through virtual traffic signal controller simulations. This optimization contributes to smoother traffic flow and reduced delays during signal transitions, addressing a key inefficiency in current traffic management practices. The study also highlights the adaptability of the proposed methodology, demonstrating its potential for application across various types of traffic signal controllers. Collectively, these findings offer innovative, practical solutions for advancing traffic signal management. This research provides a solid foundation for future developments in adaptive and data-driven traffic control systems.","abstract_html":"Traffic signal management plays a crucial role in optimizing traffic flow, reducing congestion, and improving travel time reliability at signalized intersections. This dissertation focuses on three key areas of research that aim to enhance the efficiency of traffic signal operations through the integration of advanced technologies and data-driven approaches. First, the study compares traditional traffic delay measurement methods, specifically the Highway Capacity Manual (HCM) methodology, with a Machine Learning Vision System (MLVS). This comparison acknowledges the HCM's reliability in traffic analysis while highlighting the potential of MLVS in capturing nuanced traffic patterns and improving signal performance metrics. Second, the dissertation explores the use of Signal Performance Measures (SPM) data combined with machine learning models to estimate turning movement counts at intersections. Various models were tested, and XGBoost emerged as the most effective, demonstrating higher accuracy than the other models. This novel approach offers a practical solution for traffic engineers seeking to obtain turning movement count data at an intersection for analysis with limited data collection infrastructure. Third, the research introduces a mathematical framework for optimizing signal transitions across coordinated intersections. By adjusting collective offsets at multiple intersections, the framework reduced total time to coordination by over 60%, after it was validated through virtual traffic signal controller simulations. This optimization contributes to smoother traffic flow and reduced delays during signal transitions, addressing a key inefficiency in current traffic management practices. The study also highlights the adaptability of the proposed methodology, demonstrating its potential for application across various types of traffic signal controllers. Collectively, these findings offer innovative, practical solutions for advancing traffic signal management. This research provides a solid foundation for future developments in adaptive and data-driven traffic control systems.","abstract_has_math":false,"creators":["Cho, Nadan"],"institution":"University of Alabama Libraries","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Rahman, Mizanur","Liu, Jun","Lidbe, Abhay","Shen, Jinwei"],"advisors":["Hainen, Alex"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T18:44:20Z","subjects":["Traffic Delay","Traffic Signal Management"],"languages":["en_US","English"],"rights":["All rights reserved by the author unless otherwise indicated."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1114623"],"render_values":[{"text":"1114623","href":null,"code":true}]}]},"links":{"outbound_url":"https://ir.ua.edu/handle/123456789/15380","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Rahman, Mizanur","Liu, Jun","Lidbe, Abhay","Shen, Jinwei"]},{"key":"dc:contributor.advisor","label":"Advisor","values":["Hainen, Alex"]},{"key":"dc:creator","label":"Author","values":["Cho, Nadan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-02-11T13:21:50Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-02-11T13:21:50Z"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["University of Alabama Libraries"]},{"key":"dc:type","label":"Dc Type","values":["thesis","text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Traffic Delay","Traffic Signal Management"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["All rights reserved by the author unless otherwise indicated."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1114623"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://ir.ua.edu/handle/123456789/15380"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Electronic Thesis or Dissertation"]},{"key":"dc:description.abstract","label":"Abstract","values":["Traffic signal management plays a crucial role in optimizing traffic flow, reducing congestion, and improving travel time reliability at signalized intersections. This dissertation focuses on three key areas of research that aim to enhance the efficiency of traffic signal operations through the integration of advanced technologies and data-driven approaches. First, the study compares traditional traffic delay measurement methods, specifically the Highway Capacity Manual (HCM) methodology, with a Machine Learning Vision System (MLVS). This comparison acknowledges the HCM's reliability in traffic analysis while highlighting the potential of MLVS in capturing nuanced traffic patterns and improving signal performance metrics. Second, the dissertation explores the use of Signal Performance Measures (SPM) data combined with machine learning models to estimate turning movement counts at intersections. Various models were tested, and XGBoost emerged as the most effective, demonstrating higher accuracy than the other models. This novel approach offers a practical solution for traffic engineers seeking to obtain turning movement count data at an intersection for analysis with limited data collection infrastructure. Third, the research introduces a mathematical framework for optimizing signal transitions across coordinated intersections. By adjusting collective offsets at multiple intersections, the framework reduced total time to coordination by over 60%, after it was validated through virtual traffic signal controller simulations. This optimization contributes to smoother traffic flow and reduced delays during signal transitions, addressing a key inefficiency in current traffic management practices. The study also highlights the adaptability of the proposed methodology, demonstrating its potential for application across various types of traffic signal controllers. Collectively, these findings offer innovative, practical solutions for advancing traffic signal management. This research provides a solid foundation for future developments in adaptive and data-driven traffic control systems."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["electronic"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Advances in Traffic Signal Operations Management: Machine Learning Measurement and Transition Improvements Through High-Resolution Data"]}]}],"canonical_facts":{"dc:contributor":["Rahman, Mizanur","Liu, Jun","Lidbe, Abhay","Shen, Jinwei"],"dc:contributor.advisor":["Hainen, Alex"],"dc:creator":["Cho, Nadan"],"dc:date.accessioned":["2025-02-11T13:21:50Z"],"dc:date.available":["2025-02-11T13:21:50Z"],"dc:date.issued":["2024"],"dc:description":["Electronic Thesis or Dissertation"],"dc:description.abstract":["Traffic signal management plays a crucial role in optimizing traffic flow, reducing congestion, and improving travel time reliability at signalized intersections. This dissertation focuses on three key areas of research that aim to enhance the efficiency of traffic signal operations through the integration of advanced technologies and data-driven approaches. First, the study compares traditional traffic delay measurement methods, specifically the Highway Capacity Manual (HCM) methodology, with a Machine Learning Vision System (MLVS). This comparison acknowledges the HCM's reliability in traffic analysis while highlighting the potential of MLVS in capturing nuanced traffic patterns and improving signal performance metrics. Second, the dissertation explores the use of Signal Performance Measures (SPM) data combined with machine learning models to estimate turning movement counts at intersections. Various models were tested, and XGBoost emerged as the most effective, demonstrating higher accuracy than the other models. This novel approach offers a practical solution for traffic engineers seeking to obtain turning movement count data at an intersection for analysis with limited data collection infrastructure. Third, the research introduces a mathematical framework for optimizing signal transitions across coordinated intersections. By adjusting collective offsets at multiple intersections, the framework reduced total time to coordination by over 60%, after it was validated through virtual traffic signal controller simulations. This optimization contributes to smoother traffic flow and reduced delays during signal transitions, addressing a key inefficiency in current traffic management practices. The study also highlights the adaptability of the proposed methodology, demonstrating its potential for application across various types of traffic signal controllers. Collectively, these findings offer innovative, practical solutions for advancing traffic signal management. This research provides a solid foundation for future developments in adaptive and data-driven traffic control systems."],"dc:format.medium":["electronic"],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["1114623"],"dc:identifier.uri":["https://ir.ua.edu/handle/123456789/15380"],"dc:language":["English"],"dc:language.iso":["en_US"],"dc:publisher":["University of Alabama Libraries"],"dc:rights":["All rights reserved by the author unless otherwise indicated."],"dc:subject":["Traffic Delay","Traffic Signal Management"],"dc:title":["Advances in Traffic Signal Operations Management: Machine Learning Measurement and Transition Improvements Through High-Resolution Data"],"dc:type":["thesis","text"]},"updated_at":"2026-07-27T18:44:20Z"}