{"id":{"repo_id":"northampton","oai_identifier":"oai:pure.atira.dk:studenttheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30"},"canonical_url":"https://search.dev.ndltd.org/etd/northampton/oai:pure.atira.dk:studenttheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30","repository":{"repo_id":"northampton","name":"University of Northampton","base_url":"https://pure.northampton.ac.uk/ws/oai"},"display":{"title":"Predicting Traffic Speed and Recommending Optimal Routes using GPS Data: A Smart Navigation System for Commuters","abstract":"Traffic congestion continues to be a major challenge for commuters, as current prediction and route recommendation systems often fall short due to limitations in the data they rely on. Many of these systems depend on simulated traffic data that lack real-world complexities or traditional sensors that provide only limited geographic coverage.<br/>This thesis introduces a novel framework designed to tackle these shortcomings by using real-world GPS data to predict traffic speed one hour ahead and recommend optimal routes for commuters. The framework introduces a proposed solution for map matching, which enhances the accuracy of input data by removing noise, eliminating redundant (repetitive or unnecessary data) points, and ensuring precise alignment with the digital road map. This processed data is then used for traffic speed prediction, utilising a Fine Tree machine learning model.<br/>The system is trained using the T-Drive dataset, and data preprocessing is implemented in MATLAB, achieving a map-matching accuracy of 99.92\\%. For traffic speed prediction, the Fine Tree model delivers a low Mean Squared Error (MSE) of 0.02 and an execution time of 2 milliseconds, balancing high accuracy with real-time performance.<br/>Additionally, the system accounts for additional factors impacting traffic flow, such as weather conditions, accidents, and temporary road closures. These elements are managed through a PostgreSQL database, enabling flexible and comprehensive route recommendations tailored to real-world conditions.<br/>The key contributions of this thesis include the development of an advanced map-matching algorithm, an effective machine learning-based traffic speed prediction model, and an integrated framework offering dynamic, data-driven solutions to road traffic challenges. By addressing the intricacies of urban traffic, this research provides commuters with intelligent navigation tools, fostering more efficient travel and reduced congestion.<br/>","abstract_html":"Traffic congestion continues to be a major challenge for commuters, as current prediction and route recommendation systems often fall short due to limitations in the data they rely on. Many of these systems depend on simulated traffic data that lack real-world complexities or traditional sensors that provide only limited geographic coverage.&lt;br/&gt;This thesis introduces a novel framework designed to tackle these shortcomings by using real-world GPS data to predict traffic speed one hour ahead and recommend optimal routes for commuters. The framework introduces a proposed solution for map matching, which enhances the accuracy of input data by removing noise, eliminating redundant (repetitive or unnecessary data) points, and ensuring precise alignment with the digital road map. This processed data is then used for traffic speed prediction, utilising a Fine Tree machine learning model.&lt;br/&gt;The system is trained using the T-Drive dataset, and data preprocessing is implemented in MATLAB, achieving a map-matching accuracy of 99.92\\%. For traffic speed prediction, the Fine Tree model delivers a low Mean Squared Error (MSE) of 0.02 and an execution time of 2 milliseconds, balancing high accuracy with real-time performance.&lt;br/&gt;Additionally, the system accounts for additional factors impacting traffic flow, such as weather conditions, accidents, and temporary road closures. These elements are managed through a PostgreSQL database, enabling flexible and comprehensive route recommendations tailored to real-world conditions.&lt;br/&gt;The key contributions of this thesis include the development of an advanced map-matching algorithm, an effective machine learning-based traffic speed prediction model, and an integrated framework offering dynamic, data-driven solutions to road traffic challenges. By addressing the intricacies of urban traffic, this research provides commuters with intelligent navigation tools, fostering more efficient travel and reduced congestion.&lt;br/&gt;","abstract_has_math":false,"creators":["Alkhazraji, Hussein"],"institution":"University of Northampton","degree_name":"Doctoral Thesis","degree_level":"Student thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Opoku Agyeman, Michael","Kanakis, Triantafyllos","Bhaya, Wesam"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-2-13","date_published":"2025-2-13","updated_at":"2026-07-24T03:26:59Z","subjects":["GPS Data","Road Traffic Prediction","Map Matching","Route Recommendation"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:pure.atira.dk:studenttheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30"],"render_values":[{"text":"oai:pure.atira.dk:studenttheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30","href":null,"code":true}]}]},"links":{"outbound_url":"https://pure.northampton.ac.uk/en/studentTheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Opoku Agyeman, Michael","Kanakis, Triantafyllos","Bhaya, Wesam"]},{"key":"dc:creator","label":"Author","values":["Alkhazraji, Hussein"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-2-13"]},{"key":"dc:date.issued","label":"Date","values":["2025-2-13"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Graduate School","Centre for Advanced and Smart Technologies","Computing","Faculty of Arts, Science & Technology"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Northampton"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://pure.northampton.ac.uk/en/studentTheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Student thesis"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Doctoral Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["GPS Data","Road Traffic Prediction","Map Matching","Route Recommendation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:pure.atira.dk:studenttheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30","https://pure.northampton.ac.uk/en/studentTheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://pure.northampton.ac.uk/files/81791945/Alkhazraji_Hussein_2025_Predicting_Traffic_Speed_and_Recommending_Optimal_Routes_using_GPS.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Traffic congestion continues to be a major challenge for commuters, as current prediction and route recommendation systems often fall short due to limitations in the data they rely on. Many of these systems depend on simulated traffic data that lack real-world complexities or traditional sensors that provide only limited geographic coverage.<br/>This thesis introduces a novel framework designed to tackle these shortcomings by using real-world GPS data to predict traffic speed one hour ahead and recommend optimal routes for commuters. The framework introduces a proposed solution for map matching, which enhances the accuracy of input data by removing noise, eliminating redundant (repetitive or unnecessary data) points, and ensuring precise alignment with the digital road map. This processed data is then used for traffic speed prediction, utilising a Fine Tree machine learning model.<br/>The system is trained using the T-Drive dataset, and data preprocessing is implemented in MATLAB, achieving a map-matching accuracy of 99.92\\%. For traffic speed prediction, the Fine Tree model delivers a low Mean Squared Error (MSE) of 0.02 and an execution time of 2 milliseconds, balancing high accuracy with real-time performance.<br/>Additionally, the system accounts for additional factors impacting traffic flow, such as weather conditions, accidents, and temporary road closures. These elements are managed through a PostgreSQL database, enabling flexible and comprehensive route recommendations tailored to real-world conditions.<br/>The key contributions of this thesis include the development of an advanced map-matching algorithm, an effective machine learning-based traffic speed prediction model, and an integrated framework offering dynamic, data-driven solutions to road traffic challenges. By addressing the intricacies of urban traffic, this research provides commuters with intelligent navigation tools, fostering more efficient travel and reduced congestion.<br/>"]},{"key":"dc:title","label":"Title","values":["Predicting Traffic Speed and Recommending Optimal Routes using GPS Data: A Smart Navigation System for Commuters"]}]}],"canonical_facts":{"dc:contributor.advisor":["Opoku Agyeman, Michael","Kanakis, Triantafyllos","Bhaya, Wesam"],"dc:creator":["Alkhazraji, Hussein"],"dc:date":["2025-2-13"],"dc:date.issued":["2025-2-13"],"dc:description.abstract":["Traffic congestion continues to be a major challenge for commuters, as current prediction and route recommendation systems often fall short due to limitations in the data they rely on. Many of these systems depend on simulated traffic data that lack real-world complexities or traditional sensors that provide only limited geographic coverage.<br/>This thesis introduces a novel framework designed to tackle these shortcomings by using real-world GPS data to predict traffic speed one hour ahead and recommend optimal routes for commuters. The framework introduces a proposed solution for map matching, which enhances the accuracy of input data by removing noise, eliminating redundant (repetitive or unnecessary data) points, and ensuring precise alignment with the digital road map. This processed data is then used for traffic speed prediction, utilising a Fine Tree machine learning model.<br/>The system is trained using the T-Drive dataset, and data preprocessing is implemented in MATLAB, achieving a map-matching accuracy of 99.92\\%. For traffic speed prediction, the Fine Tree model delivers a low Mean Squared Error (MSE) of 0.02 and an execution time of 2 milliseconds, balancing high accuracy with real-time performance.<br/>Additionally, the system accounts for additional factors impacting traffic flow, such as weather conditions, accidents, and temporary road closures. These elements are managed through a PostgreSQL database, enabling flexible and comprehensive route recommendations tailored to real-world conditions.<br/>The key contributions of this thesis include the development of an advanced map-matching algorithm, an effective machine learning-based traffic speed prediction model, and an integrated framework offering dynamic, data-driven solutions to road traffic challenges. By addressing the intricacies of urban traffic, this research provides commuters with intelligent navigation tools, fostering more efficient travel and reduced congestion.<br/>"],"dc:identifier":["oai:pure.atira.dk:studenttheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30","https://pure.northampton.ac.uk/en/studentTheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30"],"dc:identifier.uri":["https://pure.northampton.ac.uk/files/81791945/Alkhazraji_Hussein_2025_Predicting_Traffic_Speed_and_Recommending_Optimal_Routes_using_GPS.pdf"],"dc:language":["eng"],"dc:publisher.department":["Graduate School","Centre for Advanced and Smart Technologies","Computing","Faculty of Arts, Science & Technology"],"dc:publisher.institution":["University of Northampton"],"dc:relation.isreferencedby":["https://pure.northampton.ac.uk/en/studentTheses/4bff58e7-2ee6-45b9-9f11-739bd5e55c30"],"dc:subject":["GPS Data","Road Traffic Prediction","Map Matching","Route Recommendation"],"dc:title":["Predicting Traffic Speed and Recommending Optimal Routes using GPS Data: A Smart Navigation System for Commuters"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["Student thesis"],"dc:type.qualificationname":["Doctoral Thesis"]},"updated_at":"2026-07-24T03:26:59Z"}