National Technical University of Athens (NTUA)
Human-in-the-loop predictive analytics for incident detection in smart transportation systems
Abstract
dc:descriptionThe current PhD dissertation explores the need for advanced real-time traffic incident detection systems in urban environments, where the complexity and volume of data often overwhelm traditional methods. The research focuses on integrating advanced data analytics including Machine Learning and Deep Learning, in addition to Automated Machine Learning (AutoML), Human-in-the-Loop (HITL) approaches, and Explainability techniques to develop a robust and scalable framework for incident detection. Moreover, an end-to-end information system is presented, which has been tested and validated in real-world scenarios in two major European cities, where the results demonstrated its effectiveness and superiority compared to traditional methods.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Gkioka, Georgia
- Γκιόκα, Γεωργία
Subjects
dc:subject × 16- Ανίχνευση περιστατικών κακοποίησης στο σχολείο
- Τεχνητή νοημοσύνη
- Ανθρώπινη παρέμβαση
- Επεξηγησιμότητα
- Προβλεπτική Αναλυτική
- Traffic incident detection
- Artificial intelligence
- Human-in-the-loop
- Explainability
- Predictive analytics
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Επιστήμες Μηχανικού και Τεχνολογία
- Υπολογιστές, Υλικό (hardware) και Αρχιτεκτονική
- Electrical Engineering, Electronic Engineering, Information Engineering
- Engineering and Technology
- Computer science, Hardware and Architecture
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/58620