Annual Average Daily Traffic Estimation in Liverpool
Budget: ₹1,500 – ₹12,500 INR
"Only accept if you have strong knowledge of GIS and can use Geopandas Library in Python"
This project aims to apply GIS technology, and geopandas in Python, and adapt the clustering and regression models presented by Sfyridis to develop a comprehensive and accurate traffic estimation model for the city of Liverpool. This study aims to provide valuable insights into traffic patterns specific to Liverpool by considering methods to classify data with missing variables and exploring models for individual vehicle types, such as LGVs and HGVs, to reveal patterns peculiar to specific traffic flows.
This work will focus primarily on:
• Utilize GIS technology and geopandas in Python to collect, manage, and analyze relevant spatial data related to the road network, traffic counts, and other influencing factors in Liverpool City.
• Adapt and customize the clustering methodology proposed by Sfyridis to classify traffic data into meaningful clusters, considering missing variables and finding the shortest distance from new points to the center of cluster centroids.
• Incorporate regression models to estimate the Average Annual Daily Traffic (AADT) for the road segments in Liverpool City, using the identified clusters and the variables with the smallest degree of overlap across clusters.
• Develop models specifically tailored to LGVs and HGVs, allowing for the identification of traffic patterns unique to these vehicle types and their respective flows within Liverpool City.
• Analyze and interpret the results obtained from the clustering and regression models, identifying the factors influencing cluster formation and traffic flow variations in Liverpool City.
• Evaluate the performance of the developed model through comparison with existing traffic estimation methods, considering accuracy, efficiency, and applicability to transportation planning and management decisions.
• Provide recommendations and insights based on the findings, highlighting the potential implications for transportation planning, infrastructure development, and environmental studies in Liverpool City.
This project aims to apply GIS technology, and geopandas in Python, and adapt the clustering and regression models presented by Sfyridis to develop a comprehensive and accurate traffic estimation model for the city of Liverpool. This study aims to provide valuable insights into traffic patterns specific to Liverpool by considering methods to classify data with missing variables and exploring models for individual vehicle types, such as LGVs and HGVs, to reveal patterns peculiar to specific traffic flows.
This work will focus primarily on:
• Utilize GIS technology and geopandas in Python to collect, manage, and analyze relevant spatial data related to the road network, traffic counts, and other influencing factors in Liverpool City.
• Adapt and customize the clustering methodology proposed by Sfyridis to classify traffic data into meaningful clusters, considering missing variables and finding the shortest distance from new points to the center of cluster centroids.
• Incorporate regression models to estimate the Average Annual Daily Traffic (AADT) for the road segments in Liverpool City, using the identified clusters and the variables with the smallest degree of overlap across clusters.
• Develop models specifically tailored to LGVs and HGVs, allowing for the identification of traffic patterns unique to these vehicle types and their respective flows within Liverpool City.
• Analyze and interpret the results obtained from the clustering and regression models, identifying the factors influencing cluster formation and traffic flow variations in Liverpool City.
• Evaluate the performance of the developed model through comparison with existing traffic estimation methods, considering accuracy, efficiency, and applicability to transportation planning and management decisions.
• Provide recommendations and insights based on the findings, highlighting the potential implications for transportation planning, infrastructure development, and environmental studies in Liverpool City.
Related categories:
Python
Machine Learning (ML)
Statistical Analysis
Data Science
Geographical Information System (GIS)