Thesis topic proposal
Tamás Tettamanti
Multi-level modeling for urban road traffic network and deep learning in traffic estimation


Institute: Budapest University of Technology and Economics
transportation and vehicle engineering
Kálmán Kandó Doctoral School of Transportation and Vehicle Engineering

Thesis supervisor: Tamás Tettamanti
Location of studies (in Hungarian): Department of Control for Transportation and Vehicle Systems
Abbreviation of location of studies: KJIT

Description of the research topic:

a) Background:
The road traffic modeling and control has great tradition in science. At the same time, due to the spreading development of information technology the topic became again very important. Big data information is also relevant concerning the transportation processes. Accordingly, the proper use of data mining and artificial intelligence opens new ways for traffic modeling and estimation.

b) Goal of research:
The goal of research is to create advanced modeling by applying multi-level approach for urban road traffic network. Accordingly, the analysis of advanced measurement and estimation methods (e.g. Kalman Filter, data fusion, deep learning) is needed during the research, which van be potentially used for multi-level modeling.
Moreover, the research will consist of the applicability of artificial intelligence in road traffic with special focus on intelligent transport systems and automated/autonomous vehicle technologies.

c) Main tasks of research:
• State-of-the-art research.
• Traffic modeling theory.
• Urban road traffic modeling and simulation.
• Research about advanced traffic measurement and estimation
• Development of advanced modeling applying multi-level approach for urban road traffic network.
• Application of artificial intelligence (e.g. deep learning) for traffic estimation and control
• Testing and validation of the developed models an algorithms.

d) HW/SW tools provided for research:
• road traffic controllers,
• PC,

e) Minimum expected scientific results:
• 2 articles in refereed international journal with SCI index,
• 3 articles in international conference proceedings.

f) Related bibliography:
• T. Tettamanti T., M.T. Horváth, I. Varga: Road traffic measurement and related data fusion methodology for traffic estimation, Transport and Telecommunication 15:(4) pp. 269-279, 2014, https://search.proquest.com/openview/36a113b9d9cbb2beaa1e7f2ae252c5e2/1?pq-origsite=gscholar&cbl=2026667
• Tamás Tettamanti, Márton Tamás Horváth, István Varga: Nonlinear traffic modeling for urban road network and related robust state estimation, Proceedings of the 9th European Nonlinear Dynamics Conference, ENOC 2017, Paper ID 247, ISBN 978-963-12-9168-1, June 25-30, 2017, Budapest, Hungary, http://congressline.hu/enoc2017/abstracts/247.pdf
• T. Tettamanti, A. Csikós, K. B. Kis, Zs. J. Viharos, I. Varga: Pattern recognition based speed forecasting methodology for urban traffic network, Transport, 2017, http://dx.doi.org/10.3846/16484142.2017.1352027

Required language skills: English: proficient user
Further requirements: 
• Proper knowledge of control theory
• Advanced skills of informatics: Microsoft Office, basic programming (e.g. Java/C/C++/C#/Python), Matlab

Number of students who can be accepted: 1

Deadline for application: 2018-06-27

All rights reserved © 2007, Hungarian Doctoral Council. Doctoral Council registration number at commissioner for data protection: 02003/0001. Program version: 2.2358 ( 2017. X. 31. )