Αναμενόμενος χρόνος άφιξης και πρόβλεψη τοποθεσίας σε ένα αστικό σενάριο κινητικότητας
Expected time of arrival and location prediction in an urban mobility scenario
View/
Keywords
Machine learning ; Algorithms ; Neural network ; DataAbstract
Machine Learning is a rapidly developing field in computer science that can offer solutions to
complex and demanding problems. This thesis aims to develop and compare systems for
predicting passenger disembarkation stops using public transportation data from the city of
Riga, utilizing machine learning models. Additionally, it thoroughly examines algorithms such as
Decision Tree, Random Forest, Bagging, Gradient Boosting, Kernel Ridge Regression, Neural
Networks, XGBoost, and LightGBM, analyzing their theoretical foundations, implementation
methods, and performance metrics. These algorithms are then applied to the collected
transportation data, and the accuracy of their predictions is evaluated and justified. This
research highlights the importance of selecting the appropriate model based on the
characteristics of the data and the problem's requirements, providing practical insights into the
application of machine learning techniques for predicting public transportation disembarkation
stops.
Postgraduate Studies Programme
Κυβερνοασφάλεια και Επιστήμη ΔεδομένωνDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα ΠληροφορικήςNumber of pages
43Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα