Analysis Methods in Traffic Engineering
Course Description:
The aim of the course is to introduce students to advanced concepts of traffic flow models development within the framework of Intelligent traffic control systems. The course includes topics such as computer based and telematics traffic control systems, analysis standards for traffic junctions, urban corridors and networks, traffic simulation standards and their applications, queuing theory, traffic capacity in areas of traffic streams merging, traffic flow analysis, short-term traffic flow prediction, machine learning for traffic forecasting. Applications are developed in WEKA open source software and traffic simulation environment. The weekly program includes 4 teaching hours of theory and applications. During lecture time applications and exercises are solved and no clear distinction between theory and exercises exists. The course includes 4 mandatory exercises and 1 oral examination.
- Semester 9
- Teaching hours 4
- Website http://mycourses.ntua.gr/course_description/index.php?cidReq=CIVIL1002
- Instructors E. Vlahogianni (Coordinator)
Prerequisite Knowledge
Principles of traffic engineering taught in the following courses: Traffic Flow (Semester 7) and Urban Road Networks (Semester 8). Knowledge of the basic principles of statistical analysis is also a prerequisite.Course Units
| # | Title | Description | Hours |
|---|---|---|---|
| 1 | Intelligent Transportation Systems | Introduction. Traffic control systems. Processes and patterns. Microscopic and macroscopic traffic analysis. Traffic forecasting. | 2Χ4=8 |
| 2 | Advanced traffic flow patterns | Hydrodynamic models. Car-following models. Cellular automata. Traffic merging models in freeways. Applications. | 3Χ4=12 |
| 3 | Queuing theory | Basic principles. Queue and delay computations. Main characteristics of a queuing system. Types of queues. Single and multiple channel queuing systems. Queuing theory applications in traffic flow. | 2Χ4=8 |
| 4 | Traffic simulation | Basic principles. Simulation standards. Optimization of signalization. Traffic simulation in urban networks. Applications. | 3Χ4=12 |
| 5 | Machine learning | Machine learning principals. Introduction to open source machine learning software WEKA. Machine learning applications for traffic engineering (classification and forecasting). | 3Χ4=12 |
Learning Objectives
With the successful completion of the course, students will be able to:
- know the principal categories of analysis methods and simulation applied in traffic engineering,
- realize the influence of analytical methods on modern intelligent traffic control and management systems,
- understand the importance of open source software and programming in resolving traffic problems,
- develop codes to implement patterns for solving traffic flow problems, and
- assess traffic models based on their usefulness and reliability.
Teaching Methods
| Teaching methods | Lectures in class. Code development for applications implementation in class. Deliver of 4 individual exercises. |
|---|---|
| Teaching media | Presentations on board. Power Point slides. Computations with machine learning and simulation software. |
| Computer and software use | Students solve exercises in class with teachers' support. All exercises are solved in the PCs. |
| Problems - Applications | During lectures, exemplars of pattern development applications are presented. |
| Assignments (projects, reports) | Students perform and deliver individually 4 assignments solved in PC, which are corrected and returned to them during the oral examination. |
Student Assessment
- Assignments (projects, reports): 100%
Textbooks - Bibliography
Textbooks "Κυκλοφοριακή Τεχνική" Ι. Μ. Φραντζεσκάκη - Ι. Κ. Γκόλια - Μ. Χ. Πιτσιάβα-Λατινοπούλου, Εκδόσεις Παπασωτηρίου 2008. "Εφαρμογή Θεωρίας Ουρών στη Κυκλοφοριακή Τεχνική" Γκόλιας Ι. Κ. και Καρλαύτης Μ. Γ., 2004.
Proposed bibliography
Traffic Flow and Coordinated Signaling Chowdhury, D. , Santen, L. and Schadschneider A., (2000). ???? Daganzo C. F., (1997). "Fundamentals of transportation and traffic operations." Pergamon, ISBN 0-08-042785-5. Hall F. D., (1994), Traffic Stream Characteristics, Monograph on Traffic Flow Theory Institute of Transportation Engineers (ITE) (1993).Traffic Engineering Handbook. Editor Pline, J. L., Prentice Hall, Englewood Cliffs, N. J., 07632, ISBN 0139267913. May, A. D. (1990). Traffic Flow Fundamentals. Prentice-Hall Englewood Cli_s, NJ. Mc Shane, W. R., and Roess, P. (1990). Traffic Engineering. Prentice Hall, Englewood Cliffs, N. J., 07632, ISBN 0139261486. Papageorgiou M. (2003). Traffic Control. In Handbook of Transportation Science. Ed. R. W. Hall, Kluwer Academic Pub , ISBN: 1402072465. Salter R. J. Housell N. B. (1996). Highway Traffic Analysis and Design 3rd edition Palgrave McMillan, ISBN.
Statistical analysis Robert H. Shumway, David S. Stoffer (2000) Time series analysis and its applications : with R examples / New York ; Berlin : Springer. Simon P. Washington, Matthew G. Karlaftis, Fred L. Mannering (2003) Statistical and econometric methods for transportation data analysis. Boca Raton : Chapman & Hall/CRC Press.
Traffic forecasting Hyndman, R. J., & Athanasopoulos, G. (2014). Forecasting: principles and practice. OTexts. Vlahogianni, E I., Karlaftis, M. G., Golias, J.C. (2014). Short-term Traffic Forecasting: Where We Are and Where We're Going. Transportation Research Part C: Emerging Technologies, 43(1), 3-19. Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning (Vol. 1). Springer, Berlin: Springer series in statistics. Chambers, D., & Mandic, J. (2001). Recurrent neural networks for prediction: learning algorithms architecture and stability. John Wiley & Sons, Ltd., Chichester, 18, 32.
Machine learning Marsland, S. (2014). Machine learning: an algorithmic perspective. CRC press. Kruse, R., Borgelt, C., Klawonn, F., Moewes, C., Steinbrecher, M., & Held, P. (2013). Computational intelligence: a methodological introduction. Springer Science & Business Media. Engelbrecht, A. P. (2007). Computational intelligence: an introduction. John Wiley & Sons. TRB (2007). Artificial Intelligence in Transportation: Information for Application, Transportation Research Circular E-C113, Transportation Research Board, Washington DC. Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
Lecture Time - Place:
- Thursday, 08:45 – 12:30,
Rooms:- ΖΚτ. Αντ. Υλ., ΖΚτ. Αντ. Υλ. 101