This thesis presents a comprehensive study on developing a machine learning model to predict mobility patterns. The primary focus of this project is to utilize GPS data and assess the effectiveness of machine learning models in forecasting whether users use a lift on their way or not considering route characteristics. Additionally, the research aims to identify the key factors influencing mobility behavior and explore the potential application of machine learning models in personalized mobility prediction and sustainable transportation planning. To achieve these objectives, a range of machine learning models will be evaluated for their accuracy and precision in forecasting mobility patterns. The research will investigate how different models perform in predicting mobility transportation. Moreover, an in-depth analysis will be conducted to identify the factors that significantly impact the accuracy of these models. By examining the accuracy and precision of various machine learning models, this research will provide valuable insights into their effectiveness in mobility forecasting. Furthermore, it will uncover the factors that play a crucial role in influencing the accuracy of these models. The findings of this study will contribute to the advancement of machine learning applications in transportation planning and assist in developing personalized mobility prediction systems for sustainable transportation.
This thesis presents a comprehensive study on developing a machine learning model to predict mobility patterns. The primary focus of this project is to utilize GPS data and assess the effectiveness of machine learning models in forecasting whether users use a lift on their way or not considering route characteristics. Additionally, the research aims to identify the key factors influencing mobility behavior and explore the potential application of machine learning models in personalized mobility prediction and sustainable transportation planning. To achieve these objectives, a range of machine learning models will be evaluated for their accuracy and precision in forecasting mobility patterns. The research will investigate how different models perform in predicting mobility transportation. Moreover, an in-depth analysis will be conducted to identify the factors that significantly impact the accuracy of these models. By examining the accuracy and precision of various machine learning models, this research will provide valuable insights into their effectiveness in mobility forecasting. Furthermore, it will uncover the factors that play a crucial role in influencing the accuracy of these models. The findings of this study will contribute to the advancement of machine learning applications in transportation planning and assist in developing personalized mobility prediction systems for sustainable transportation.
Analyzing bike tracks using artificial intelligence algorithms
KARIMI, NIMA
2022/2023
Abstract
This thesis presents a comprehensive study on developing a machine learning model to predict mobility patterns. The primary focus of this project is to utilize GPS data and assess the effectiveness of machine learning models in forecasting whether users use a lift on their way or not considering route characteristics. Additionally, the research aims to identify the key factors influencing mobility behavior and explore the potential application of machine learning models in personalized mobility prediction and sustainable transportation planning. To achieve these objectives, a range of machine learning models will be evaluated for their accuracy and precision in forecasting mobility patterns. The research will investigate how different models perform in predicting mobility transportation. Moreover, an in-depth analysis will be conducted to identify the factors that significantly impact the accuracy of these models. By examining the accuracy and precision of various machine learning models, this research will provide valuable insights into their effectiveness in mobility forecasting. Furthermore, it will uncover the factors that play a crucial role in influencing the accuracy of these models. The findings of this study will contribute to the advancement of machine learning applications in transportation planning and assist in developing personalized mobility prediction systems for sustainable transportation.File | Dimensione | Formato | |
---|---|---|---|
Karimi_Nima.pdf
accesso riservato
Dimensione
973.7 kB
Formato
Adobe PDF
|
973.7 kB | Adobe PDF |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/56505