Trip demand prediction is an integral part of intelligent transportation systems. It is concerned with estimating future trip demand based on past observations. An accurate forecasting model can help with the efficient reallocation of vehicle resources to better meet travel demands, which can benefit many transportation services. The prediction process is a challenging task due to the complex and dynamic spatio-temporal correlations of trip data. Recent advances in deep learning-based methods have inspired researchers to apply them to traffic forecasting tasks. Some of these methods use Convolution Neural Networks to model the spatio-temporal dependencies in trip data by representing trip data as 2D grids. Other methods utilize the natural graph I would like to thank my thesis supervisor, Professor Doron Nussbaum, for his advice, constructive feedback, and guidance through the preparation of this thesis. I'm grateful to my wife and kids for their unwavering support and encouragement during my graduate studies at Carleton University. And I owe my parents a debt of gratitude for their patience and financial support over the years.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.