Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Peak-aware traffic prediction with deep learning models and a driver simulation method with probabilistic hybrid automaton
Download
Fatih___METU_Thesis_Traffic (6).pdf
Date
2022-8
Author
Acun, Fatih
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
283
views
101
downloads
Cite This
Accurately predicting traffic is crucial due to its impact on urban life in many aspects. Several statistical methods, machine learning, and deep learning approaches are applied to different traffic datasets. In general, traffic follows a stable behavior except for the morning and evening peaks which span a small period in time. To consider a prediction model to be accurate, it must demonstrate successful results during peak hours. In this thesis, a novel distance to mean weighting technique is presented that can be applied to any deep learning model by introducing a minor change in the loss function. The method also makes it possible to evaluate the performance of the models during peak hours in traffic. Traffic prediction is frequently used in estimating travel times and energy consumption (battery or fuel). In this thesis, in order to estimate both travel time and consumption, a driver simulation model based on Probabilistic Hybrid Automata is developed. The simulator generates speed-time data with respect to the given traffic and driver characteristics. The result is then used to estimate the consumption using an electric vehicle simulator.
Subject Keywords
Traffic prediction
,
Deep learning
,
Driver modeling
,
Probabilistic hybrid automata
URI
https://hdl.handle.net/11511/98589
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Pedestrian self-reports of factors influencing the use of pedestrian bridges
Rasanen, Mikko; Lajunen, Timo; Alticafarbay, Farahnaz; Aydin, Cumhur (2007-09-01)
The study was designed to find out factors that influence use/non-use of pedestrian bridges. The use rate of five pedestrian bridges was observed in the central business district (CBD) of Ankara. After the observations, a survey was conducted among pedestrians using those bridges and crossing contrary to safe practice under them at street level (n = 408). In the present data, the use rate of pedestrian bridges varied from 6 to 63%. The frequent use of the bridge when crossing the road concerned, and seeing ...
Realistic Simulation of IEEE 802.11p Channel in Mobile Vehicle to Vehicle Communication
Islam, Tarikul; Hu, Yongchang; Onur, Ertan; Boltjes, Bert; De Jongh, J. F. C. M. (2013-04-18)
Intelligent Transportation Systems (ITS) is becoming an important paradigm, because of its ability to enhance safety and to mitigate congestion on road traffic scenarios. Realizing the fact that data collection scheme from in-situ test beds for large number of vehicles is always expensive and time consuming, before being employed in large scale, such safety critical system should be tested narrowing down the gap between real circumstances and analytical models in a simulation platform. It is evident that un...
Spatio-temporal accident analysis for accident prevention in relation to behavioral factors in driving: The case of South Anatolian Motorway
Kaygisiz, Omur; Duzgun, Sebnem; Yildiz, Ahmet; ŞENBİL, Metin (2015-08-01)
Analyzing the pattern of traffic accidents on road segments can highlight the hazardous locations where the accidents occur frequently and help to determine problematic parts of the roads. The objective of this paper is to utilize accident hotspots to analyze the effect adifferent measures on the behavioral factors in driving. Every change in the road and its environment affects the choices of the driver and therefore the safety of the road itself. A spatio-temporal analysis of hotspots therefore can highli...
Developing multi-objective linear programming approaches for traffic signal optimization
Coşkun, Mustafa Murat; Toroslu, İsmail Hakkı; Şener, Cevat; Department of Computer Engineering (2021-7)
In many countries and metropolitan cities, traffic congestion, mainly caused by population growth and the increase in urbanization, has reached a significant level and has become a major problem for residents and decision-makers. Today, although infrastructural strategies such as the construction of underpasses and road widening to alleviate traffic congestion are applied in urban networks, the strategies can also be quite costly and environmentally damaging. Therefore, decision makers allocate large bu...
Driver profiles based on values and traffic safety climate and their relationships with driver behaviors
Kaçan, Bilgesu; Fındık, Gizem; Üzümcüoğlu, Yeşim; Azık Özkan, Derya; Solmazer, Gaye; Ersan, Özlem; Özkan, Türker; Lajunen, Timo; Öz, Bahar; Pashkevich, Anton; Pashkevich, Maria; Danelli-Mylona, Vassiliki; Georgogianni, Dimitra; Berisha Krasniqi, Ema; Krasniqi, Muhamed; Makris, Evangelos; Shubenkova, Ksenia; Xheladini, Gentianë (Elsevier BV, 2019-7)
Drivers have an important place in the traffic system when the human factor is taken into consideration. Drivers from different cultures are exposed to different values, norms, and traffic systems, and these differences may form various driver behaviors. Thus, traffic climate and individual values can impact driver behaviors. In this study, the relationships between Schwartz's individual values and traffic climate dimensions were examined. Clusters were then created from the traffic climate dimensions and i...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
F. Acun, “Peak-aware traffic prediction with deep learning models and a driver simulation method with probabilistic hybrid automaton,” M.S. - Master of Science, Middle East Technical University, 2022.