International Journal of Scientific & Engineering Research, Volume 3, Issue 1, January-2012 1

ISSN 2229-5518

A Critical Review on the Development of Urban

Traffic Models & Control Systems

Rishi Asthana, Neelu Jyoti Ahuja, Manuj Darbari, Praveen Kumar Shukla

Abstract— Modeling and development of control systems to deal with the congestion at intersection in urban traffic is a critical research is- sue. Several approaches have been used to develop the modeling and controlling phenomenon in the said problem. These approaches in- clude, Petri net, Fuzzy Logic, Neural Network, Genetic Algorithms, Activity Theory, Multi Agent Systems and many more. This paper is a survey on the development of Urban Traffic Control Systems using techniques discussed above in the last decade.

Index Terms— Fuzzy Logic, Neural Network, Genetic Algorithms, Multi Agent Systems, Activity Theory, Petri Nets.

—————————— ——————————

he development of control systems to deal with the con- gestion at the intersection in urban traffic is a critical re- search issue. The prime requirements of the developed system are, the signal must not allow the ambiguous move- ment to the traffic and it must be clear that how/when the indication of signal shown to be changed. Two other aspects to be handled are to take decisions about signal indication se- quence in the control system to make the system well opti-

mized and development of control logic for signal generation.

This paper has been divided into 6 subsections. In section 2,

Petri net based modeling has been studied and revised.

Section 3 contains the review of multi-agent systems in urban

traffic control systems. Neural Network based approaches are

discussed in Section 4. Section 5 contains the fuzzy logic based

approaches in Traffic Control Systems. Several hybrid

approaches of fuzzy logic, neural network, petri nets are

discussed in section 6. Section 7 contains various other

approaches for the traffic control systems, like activity theory,

complex network theory, incident and real time traffic control

etc.

Petri Nets [1] are also known as a place/Transition Net or

P/T net. It is the mathematical modeling language for the de-

————————————————

*Praveen Kumar Shukla is pursuing Ph.D. in Compter Science from Gau- tam Buddh Technical University,Lucknow, India and he is also working as*

a facultymember in the department of Information Technology in North- ern India Engineering College,Lucknow,India.E- mail:praveenshuklak@rediffmail.com

scription of Discrete Event Systems (DES). PN theory is devel- oped in 1962 by Carie Asam Petri. These are highly applicable in graphical modeling, Mathematical modeling, simulation and real time control by the use of places and transitions.

Different variations of the Petri Nets are applied in the modeling and control of traffic systems.

A Colored Timed Petri net (CTPN) model has been used for validating a Urban Traffic Network in [2].

A model for real time control of urban traffic networks is proposed in [3]. A modular framework based on first order hybrid Petri nets model is developed. The vehicle flows by a first order fluid approximation, in this approach. The lane in- terruptions and the signal timing plan controlling the area are developed by the discrete event dynamics integrated with timed Petri nets.

A new hybrid Petri net model for modeling the traffic behavior at intersection is developed in [4]. The im- portant aspects of the flow dynamics in urban networks are interpreted very well.

A new approach of continuous Petri nets with variable speed (VCPN) is proposed in [5]. The analysis and control design in urban and interurban networks is done.

A network model via hybrid Petri nets [6] is used to dem-

onstrate and implement the solution of the problem of coordi-

nating several traffic lights. It aims the improvement in the

performance of some classes of special vehicles, like public

and emergency vehicles.

A model of TCPN (Timed Control Petri Nets) is used to

demonstrate and solve the problem of coordinating sever-

al traffic lights in [7]. The analysis of the control TCPN mod-

els is done by Occurrence Graphs (OG) techniques.

A Colored Petri Net Model of an urban traffic network for

the purpose of performance evaluation is demonstrated in [8].

The subnets for the network, the intersections, the external

traffic inputs and control are discussed.

A Urban Traffic Simulation has been done using petri net in

[9]. This approach is based on generating producer consumer

network and grid simulation of petri nets.

IJSER © 2012

International Journal of Scientific & Engineering Research, Volume 3, Issue 1, January-2012 2

ISSN 2229-5518

A multi-agent system (MAS) [10] is a system consists of multiple interacting intelligent agents. Multi-agent systems can be used to solve problems that are possible to be difficult or impossible for an individual agent or a monolithic sys-

al and algorithmic searching, finding and processing techniqu es.

A multi agent system approach to develop distributed un- supervised traffic responsive signal control models, has been developed in [11]. Each agent in the system is a lo- cal traffic signal controller for one intersection in the traffic network. The first multi agent system is identified using hybrid soft computing techniques. Each agent employs a multistage online learning process to update and adapt its knowledge base and decision-making procedure. The second multi agent system is produced by integrating the simultane- ous perturbation stochastic approximation theorem in fuzzy extended neural networks (NN).

An approach to model the traffic of an important crossroad in Mashhad city using intelligent elements in a multi-agent environment and a large amount of real data, has been devel- oped in [12]. The overall traffic behavior at the intersection was first modeled by the Bayesian networks structures. Also, the probabilistic causal networks are used to model the effec- tive factors.

Among the several ITS applications is the notion of Dynam-

ic Traffic Routing (DTR), which involves generating “optimal”

routing recommendations to drivers with the aim of maximiz-

ing network utilizing. In [13], it has been presented that the

feasibility of using a self-learning intelligent agent to solve the

DTR problem to achieve traffic user equilibrium in a transpor-

tation network. The agent then learns by itself by interacting

with the simulation model. Once the agent reaches a satisfac-

tory level of performance, it can then be deployed to the real-

world, where it would continue to learn how to refine its con-

trol policies over time.

The integration of cooperative, distributed multi-agent sys-

tem to improve urban traffic control system is proposed in

[14]. Real-time control over the urban traffic network is done

through an agent-based distributed hierarchy traffic control

system. This system cooperates with dynamic route guidance

system. Cooperative system framework and agent structure

are discussed in this work.

A new framework of hybrid control system for UTC is pre-

sented in [15], in which any optimal control strategy can be

adopted. By the interface D-S and interface C-S namely coop-

eration model, the hybrid system of UTC is divided into three

layers including digital control loop, discrete event module,

and Group Decision-making Support System (GDSS). By inte-

grating GDSS consisted of central agent and intersection

agents, real time control and coordinate control with the cha-

racteristics of self-decision, cooperation, and intelligence are

implemented.

An approach of modeling the urban traffic flow system is

discovered for combining the global and local model informa-

tion for the whole city net in [16]. It is assumed that traffic di-

graph consists of several nodes and those nodes are linked with routes lines. The proposed system uses the random walk theory. Vehicle flow density and driver strategy independence are also the important factors in this approach.

An agent-based approach to model the individual driver

behavior under the influence of real-time traffic information is

proposed in [17]. The driver behaviour models developed in

this work are based on a behavioural survey of drivers. This

survey was conducted on a congested commuting corridor in

Brisbane, Australia. Based on the results obtained from the

behavioural survey, the agent behaviour parameters which

define driver characteristics, knowledge and preferences were

identified and their values determined.

An artificial neuron is a computational model inspired in the natural neurons. Natural neurons receive signals through synapses located on the dendrites or membrane of the neuron. When the signals received are strong enough (surpass a cer- tain threshold), the neuron is activated and emits a signal though the axon. This signal might be sent to another synapse, and might activate other neurons. The network developed on this theory in called Artificial Neural Network (ANN) [18]. The ANNs are highly applicable in the design of models for traffic control systems.

An intelligent model consists of two levels of neur- al network [19] for the traffic control system. The first level is a traffic flow neural network model to predict the traffic flow changes in road tunnel, the result of predicting will be used as an input of the second level neural network which is used to describe an intelligent model of urban road ventilation system, through the different states of predicted traffic flow, to estab- lish an intelligent model of urban road tunnel ventilation sys- tem based on multi-level neural network.

A neural network model is proposed for forecasting crossroads traffic flow using back propagation (BP) neural network in [20]. The work gives a new reliable and effective way of forecasting short term traffic flow of crossroads

in urban road network.

A commonly used macroscopic dynamic deterministic traffic flow model for traffic control is analyzed in [21]. The neural network model for the urban expressway traffic flow is established and the urban expressway multi-variable neural control strategy with both the on-ramp control and the road speeds control is implemented.

MTL (Multi Task Learning) based neural networks are used for traffic flow forecasting in [22]. For neural network MTL, a back propagation (BP) network is discovered by incorporating traffic flows at several contiguous time instants into an output layer. Nodes in the output layer can be seen as outputs of different but closely related STL tasks.

A back propagation artificial neural network model, which utilizes the characteristics of urban signalized intersec- tions for occurrence prediction of intersection - re- lated traffic crashes, along with its application for crash reduc-

IJSER © 2012

International Journal of Scientific & Engineering Research, Volume 3, Issue 1, January-2012 3

ISSN 2229-5518

tion, are proposed in [23]. With the ANN model, a proposed decision-making scheme for intersection rehabilitation was suggested.

A commonly used macroscopic dynamic deterministic traf- fic flow model is analyzed in [24]. The 1.5-layer feed-forward network modeling for the urban expressway traffic flow is implemented.

A novel intelligent identification method is proposed in [25] to reduce the computation cost and to improve the identifica- tion rate. The proposed method combines principal compo- nent analysis (PCA) method with higher-order Boltzmann machine (BM). PCA is applied to reduce the dimension of in- put feature space. It can not only reduce the computation cost but also filter noise of the source data. BM is a kind of stochas- tic network that is used to get the global optimum solution. Higher-order BM without hidden units can save lots of com- putation cost without decreasing modeling power. The trained higher-order BM is used to identify traffic state.

Short-term forecasting of traffic parameters such as flow and occupancy is an essential element of modern Intelligent Transportation Systems research and practice. An advanced, genetic algorithm based, multilayered structural optimization strategy that can help both in the proper representation of traffic flow data with temporal and spatial characteristics is presented in [26]. After that, it evaluates the performance of the developed network by applying it to both univariate and multivariate traffic flow data from an urban signalized arteri- al.

Fuzzy logic [27] is a form of many-valued logic; it deals with reasoning that is approximate rather than fixed and ex- act. In contrast with traditional logic theory, where binary sets have two-valued logic: true or false, fuzzy logic variables may have a truth value that ranges in degree between 0 and 1. Fuzzy Logic Theory is highly applicable in the design strate- gies for modeling traffic control systems.

The coordination of Urban Traffic Flow Guidance System (UTFGS) and Urban Traffic Control System (UTCS) can give decision support to navigation and signal timing at the same time. It realizes basic information sharing and to get the op- timal results from the point of system integration. A com- bined model of traffic assignment and signal control is pre- sented in [28], with the object to minimize congestion degree both at links and intersections. To avoid the complexity and difficulties in solving the optimal model, a fuzzy control algo- rithm is put forward, the input collected traffic data is de- scribed. Then the fuzzy control rules are listed in table to get the optimal link volumes.

The automated urban traffic control systems [29] are based on deterministic algorithms. They have a multi-level architec- ture. To achieve global optimality, hierarchical control algo- rithms are generally employed. An alternative approach is to use a fully distributed architecture in which there is effectively only one (low) level of control. These systems are aimed at increasing the response time of the controller and, again, these often incorporate computational intelligence techniques.

A new route choice model taking account of the impreci- sion and the uncertainties lying in the dynamic choice process is proposed in [30]. This model makes possible a more accu- rate description of the process than those (deterministic or stochastic) used in the literature. It is assumed that drivers choose a path all the more than it is foreseen to have a lesser cost. The predicted cost for each path is modeled by a fuzzy subset which can represent imprecision on network know- ledge (e.g. length of links) as well as uncertainty on traffic conditions (e.g. congested or uncongested network, incident).

Sometimes, the approaches like, neural network fuzzy log- ic, petri net are hybridized to develop the model for urban traffic control systems.

A hybrid model for single point short term traffic flow fore- casting in an urban traffic network is proposed in [31]. The hybrid model consists of two main modules: a fuzzy input fuzzy output filter (FIFO-filter) and a multi-layer feed-forward artificial neural network architecture optimized using evolu- tion strategies (MLFN-ES). The FIFO-filter does the data clus- tering operation and results in a rough forecasted prediction value based on the input data to the MLFN-ES associated with each cluster for modeling the input–output relation to provide accurate short term forecast value.

A hybrid adaptive model, based on a combination of co- lored Petri nets, fuzzy logic and learning automata has been studied in [32].

An original method using high level petri nets for the speci- fication and design of interactive systems is presented in [33]. An agent oriented architecture based on the classic compo- nents of an interactive application (application, dialogue con- trol, and interface with the application) is demonstrated.

An approach of intelligent urban traffic control is devel- oped in [34], using the neuro-genetic petri net approach. In this approach genetic algorithm is used to provide dynamic change of weight for faster learning and converging of neuro- petri nets.

Effective control strategies are required to disperse incident based traffic jams in urban networks. In [35], such a control strategy has been developed and their effectiveness in dispers- ing incident-based traffic jams in two-way rectangular grid networks is presented. The spatial topology of traffic jam is proposed for propagation, the concept of vehicle movement ban is implemented, which is frequently adopted in real urban networks as a temporary traffic management measure.

A vehicle routing problem in dynam- ic urban traffic network with real-time traffic information is presented in [36]. Both re-current and non- recurrent congestion are handled in the problem. A method to

IJSER © 2012

International Journal of Scientific & Engineering Research, Volume 3, Issue 1, January-2012 4

ISSN 2229-5518

solve the problem by combining the initial routes arrangement with the real-time route adjustment has been implemented. The genetic algorithm is also integrated in this work.

The prediction of traffic situations is a vital issue in mod- ern Intelligent Transport Systems (ITS). A situational algo- rithm of real time traffic is proposed in [37].

Urban transportation system consists of surface-way networks, freeway networks, and ramps with a mixed traffic flow of vehicles, bicycles, and pedestrians. In [38], a survey has been carried out for control and management of recurrent and non-recurrent congestion in traffic network using computational intelligence techniques.

The three factors are important for tuning the network traf- fic system: (i) the topology of underlying infrastructure; (ii) the distribution of traffic resources; (iii) the routing strategy. The optimization of network capacity based on com- plex network theory is done in [39]. The optimization method of network traffic in several situations corresponding to the real cases has been studied, also.

Route network model, construction of route network database and optimization route algorithm has been studied in [40]. Theurban route network model, which includes direction, crossing delay and restraint of urban traffic is introduced. The resolution to optimization route of turning delay and restraint is presented based on im- proved Dijkstra algorithm and programs the algorithm.

Some advanced model-based control methods for intelli- gent traffic networks are discussed in [41]. Specifically, we consider model predictive control (MPC) of integrated free- way and urban traffic networks. The basic principles of MPC are presented for traffic control including prediction models, control objectives, and constraints. The proposed MPC control approach is modular, allowing the easy substitution of predic- tion models and the addition of extra control measures or the extension of the network.

The mathematical model was formulated in [42] to describe the effectiveness of traffic jams information under the assump- tion of simple network and linear cost function. The impact of traffic congestion information on congestion propagation was discovered by using two models namely stochastic and deterministic user equilibrium assignment.

In [43], the problem of efficiently collecting and disseminat- ing traffic information in an urban setting is discovered. The traffic data acquisition problem and explore solutions in the mobile sensor network domain while considering realistic application requirements is formulated.

In the last decade, economic approaches based on computa- tional markets have been proposed as a paradigm for the de-

sign and control of complex socio-technical systems, such as urban road traffic systems. The control problem of an urban road traffic system can be modeled as a distributed resource-allocation problem to apply market-based techniques as solution methods. A competitive computational market is designed in [44], where driver agents trade the use of the ca- pacity inside the intersections with intersection manager agents.

Traffic congestion in urban road and freeway networks leads to a strong degradation of the network infrastructure and accordingly reduced throughput, which can be countered via suitable control measures and strategies. A comprehensive overview of proposed and implemented control strategies is provided for three areas: urban road networks, freeway net- works, and route guidance has been discussed in [45].

The automation of highways as part of the intelligent ve- hicle highway system (IVHS) program is seen as a way to alle- viate congestion on urban highways. The concept of lane as- signment in the context of automated highway systems (AHS) is discussed in [46]. Lane assignments represent the schedul- ing of the path taken by the vehicle once it enters an auto- mated multilane corridor. The classification of lane assign- ment strategies is developed into non-partitioned (totally un- constrained, general, and constant lane) and partitioned (des- tination monotone, origin monotone, and monotone) strate- gies. An optimization problem is also formulated with the performance criterion being a combination of travel time and manoeuvre costs.

A congestion propagation model of urban network traffic is

proposed in [47] based on the cell transmission model (CTM).

The proposed model includes a link model, which describes

flow propagation on links, and a node model, which

represents link-to-link flow propagation. A new method of

estimating average journey velocity (AJV) of both link and

network is developed to identify network congestion bottle-

necks. A numerical example is studied in Sioux Falls urban

traffic network.

Intelligent transportation systems (ITS) is effective on solv-

ing the problem of traffic jam in cities. Prediction of cros-

sroads’ traffic volume is the key technology in ITS. In [48], BP

neural network is universally used in prediction of crossroads’

traffic volume.

In reality, the individual's day-to-day route choice behavior

is a long-time evolution process, and travelers choose their

traveling routes according to the combination of historical

experience and real-time traffic information. Considering two

classes of users, one equipped with advanced traveler infor-

mation systems (ATIS) and the other without, the travel effi-

ciency under two different information feedback strategies,

namely, travel time feedback strategy and mean velocity feed-

back strategy, has been investigated in [49].

A discrete-time, link-based dynamic user-optimal route

choice problem using the variational inequality approach is

formulated in [50]. The proposed model complies with the

dynamic user-optimal equilibrium condition in which for each

origin-destination pair, the actual travel time experienced by

travelers departing during the same interval is equal and mi-

nimal.

IJSER © 2012

International Journal of Scientific & Engineering Research, Volume 3, Issue 1, January-2012 5

ISSN 2229-5518

Activity Theory is more of a descriptive meta-theory or framework than a predictive theory. It considers entire work/activity system that includes teams, organizations, etc., beyond just one actor or user and accounts for environment, history of the person, culture, role of the artifact, motivations, complexity of real life action, etc.

A conceptual activity-based and time-dependent traffic as- signment model is proposed in [51]. The temporal utility pro- files of activities are employed to formulate the temporal activ- ity choice behavior of individuals as a multinomial logic mod- el. Route choice behavior is then described as the ideal dynam- ic user equilibrium condition.

A model for urban traffic control has been proposed in [52],

which integrates the model driven engineering and activity

theory. It is also extended with fuzzy logic to deal with issues

of uncertainty.

The development of models and control systems for Urban Traffic is an important research issue. Several problems and research issues have been identified in this field. To deal with these issues, several approaches and models have been pro- posed and implemented using Fuzzy Logic, Neural Network, Petri Net, etc. These approaches have been reviewed in this paper.

In future, the authors are interested in the development of urban traffic control systems using satellite based and global positioning systems.

[1] R. Zurawski, M. Zhou, “Petri nets and industrial applications: A tu- torial”, *IEEE Transactions on Industrial Electronics*, Vol. 41, No. 6, 567-

583, Dec. 1994.

[2] Dotoli, M.; Fanti, M.P.; Iacobellis, G.; Validation of an Urban Traffic Network Model using Colored Timed Petri Nets, , 2005 IEEE Interna- tional Conference on Systems, Man and Cybernetics, Vol. 2, 1347 –

1352, 10 January 2006

[3] Dotoli, M.; Fanti, M.P.; Iacobellis, G.; An urban traffic network model by first order hybrid Petri nets, IEEE International Conference on Systems, Man and Cybernetics, 2008. SMC 2008. 1929 – 1934, 07 April

2009

[4] que , C.R.; Sutarto, H.Y.; Boel, R.; Silva, M.; Hybrid Petri net model of a traffic intersection in an urban network, 2010 IEEE Inter- national Conference on Control Applications (CCA), 658 – 664, 8-10

Sept. 2010

[5] Tolba, C.; Lefebvre, D.; Thomas, P.; El Moudni, A.; Continuous Petri nets models for the analysis of traffic urban networks, Systems, Man, and Cybernetics, 2001 IEEE International Conference on Systems, Man, and Cybernetics, Vol.2, 2001, 1323-1328.

[6] Di Febbraro, A.; Giglio, D.; Sacco, N.; Urban traffic control structure based on hybrid Petri nets, IEEE Transactions on Intelligent Trans- portation Systems, 5(4), 224-237, Dec. 2004.

[7] Yi-Sheng Huang; Ta-Hsiang Chung; Jenn-Huei Lin; A Timed Co- loured Petri Net Supervisor for Urban Traffic Networks, IMACS Multiconference on Computational Engineering in Systems Applica- tions, 4-6 Oct. 2006, 2151 – 2156.

[8] Frank DiCesare, Paul T. Kulp, Michael Gile and George List ,The

application of Petri nets to the modeling, analysis and control of in- telligent urban traffic networks, Lecture Notes in Computer Science,

1994, Volume 815, Application and Theory of Petri Nets 1994, Pages

2-15.

[9] M. Darbari, V K Singh, R. Asthana, S Prakash, N- dimensional self organizing petri net for urban traffic modeling, International Journal of Computer Science Issues, 4(2), July 2010.

[10] Michael Wooldridge, An Introduction to MultiAgent Systems, John

Wiley & Sons Ltd, 2002, paperback, 366 pages,

[11] Srinivasan, D.; Min Chee Choy; Cheu, R.L.; Neural Networks for Real-Time Traffic Signal Control, IEEE Transactions on Intelligent Transportation Systems, Volume : 7 , Issue:3 Sept. 2006 261 – 272.

[12] Maarefdoust, R.; Rahati, S.; Traffic Modeling with Multi Agent Baye- sian and Causal Networks and Performance Prediction for Changed Setting System, 2010 Second International Conference on Machine Learning and Computing (ICMLC), 9-11 Feb. 2010, 17 – 21.

[13] Add Sadek and Nagi Basha, Self-Learning Intelligent Agents for

Dynamic Traffic Routing on Transportation Networks,

2010, Unifying Themes in Complex Systems, Part III:, Pages 503-510. [14] Xin Chen; Zhao-Sheng Yang; Hai-Yang Wang; A Multi-Agent Urban

Traffic Control System Cooperated with Dynamic Route Guidance,

2006 International Conference on Machine Learning and Cybernetics,

330 – 335, 13-16 Aug. 2006.

[15] Dong Guo; Zhiheng Li; Jingyan Song; Yi Zhang; A study on the framework of urban traffic control system, Proceedings. 2003 IEEE Intelligent Transportation Systems, 2003, Vol. 1, pp. 842-846.

[16] Yu Cheng, Tao Zhang and Jianfei Wang ,Multi-agent System Model for Urban Traffic Simulation and Optimizing Based on Random Walk, Lecture Notes in Electrical Engineering, 1, Volume

67, Advances in Neural Network Research and Applications, Part 7,

Pages 703-711.

[17] Hussein Dia An agent-based approach to modelling driver route choice behaviour under the influence of real-time information, Transportation Research Part C: Emerging Technologies, Volume 10, Issues 5-6, October-December 2002, Pages 331-349.

[18] Daniel Graupe, Principles of artificial neural networks, Advanced

Series on Circuits and Systems, Vol. 6, World Scientific, 2007.

[19] Chengqian Ma; Desheng Jiang; Xi Yue; Intelligent Model of Urban Road Tunnel Ventilation System Based on Multi-Level Neural Net- work, Pacific-Asia Conference on Circuits, Communications and Sys- tems, 2009. PACCS '09. 16-17 May 2009 636 - 639

[20] Guo Xiaojian; Zhu Quan; A traffic flow forecasting model based on

BP neural network, 2009 2nd International Conference on Power

Electronics and Intelligent Transportation System (PEITS), Vol.3, 311

– 314, 19-20 Dec. 2009 .

[21] Shen Guojiang; Dai Huaping; Liu Xiang; Wang Zhi; Sun Youx- ian; Urban expressway traffic flow modeling and control using artifi- cial neural networks, Proceedings. 2003 Intelligent Transportation Systems, 2003., Vol. 1, 836-841.

[22] Feng Jin; Shiliang Sun; Neural network multitask learning for traffic flow forecasting, IEEE International Joint Conference on : Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computa- tional Intelligence). 1897 - 1901 1-8 June 2008.

IJSER © 2012

International Journal of Scientific & Engineering Research, Volume 3, Issue 1, January-2012 6

ISSN 2229-5518

[23] Pei Liu; A Neural Network Approach on Analyzing and Reducing Signalized Intersection Crashes, Third International Conference on Natural Computation, 2007. ICNC 2007, Vol. 1, 723-729, 24-27 Aug.

2007.

[24] Guo-Jiang Shen, Traffic Flow Modeling of Urban Expressway Using

Artificial Neural Networks, Lecture Notes in Computer Science,

2006, Volume 3973, Advances in Neural Networks- ISNN 2006, Pages

15-22.

[25] Zhanquan Sun and Yinglong Wang, Traffic congestion identification by combining PCA with higher-order Boltzmann machine, Neural Computing & Applications, 2009, Volume 18, Number 5, Pages 417-

422.

[26] Eleni I. Vlahogianni, Matthew G. Karlaftis , John C. Golias, Opti- mized and meta-optimized neural networks for short-term traf- fic flow prediction: A genetic approach, Transportation Research Part C: Emerging Technologies, Volume 13, Issue 3, June 2005, Pages211-

234.

[27] T. J. Ross, Fuzzy Logic with Engineering Applications, Wiley, 2010. [28] Hong Dai; Zhao-Sheng Yang; Xiao-Jun Jiang; Application of Fuzzy

Control in Combined Algorithm Between Traffic Guidance and Sig- nal Timing, 2006 International Conference on Machine Learning and Cybernetics, 13-16 Aug. 2006, 417 – 421.

[29] Y. J. Cao, N. Ireson, L. Bull and R. Miles, Design of a Traffic Junction

Controller Using Classifier System and Fuzzy Logic, Lecture Notes in Computer Science, 1999, Volume 1625, Computational Intelligence, Pages 342-353.

[30] Vincent Henn , Fuzzy route choice model for traffic assignment, Fuzzy Sets and Systems, Volume 116, Issue 1, 16 November 2000, Pages 77-101.

[31] Dipti Srinivasan, Chee Wai Chan, P.G. Balaji, Computational intelli- gence-based congestion prediction for a dynamic urban street net- work, NeurocomputingVolume 72, Issues 10-12, June 2009, Pages

2710-2716

[32] S. Barzegar, M. Davoudpour, M.R. Meybodi, A. Sadeghian, M. Tirandazian, Formalized learning automata with adaptive fuzzy coloured Petri net; an application specific to managing traffic signals, Scientia Iranica, Volume 18, Issue 3, June 2011, Pages 554-565

[33] Houcine Ezzedine, Abdelwaheb Trabelsi, Christophe Kolski, Model- ing of an interactive system with an agent-based architecture using Petri Nets, application of the method to the supervision of a transport system, Mathematics and Computers in Simulation Volume 70, Is- sues 5-6, 24 February 2006, Pages 358-376

[34] M. Darbari, R. Asthana, H. Ahmed, N J Ahuja, Enhancing the capa- bilities of N-dimensional self organizing petri net using neuro- genetic approach, International Journal of Computer Science Issues,

8(3), May 2011.

[35] Long, J.; Gao, Z.; Orenstein, P.; Ren, H.; Control Strategies for Dis- persing Incident-Based Traffic Jams in Two-Way Grid Networks, IEEE Transactions on Intelligent Transportation Systems, 99, Oct.

2011, 1-13.

[36] i Yanfeng; Gao Ziyou; Li Jun; Vehicle routing problem in dynamic urban traffic network, 2011 8th International Conference on Service Systems and Service Management (ICSSSM), 25-27 June 2011, 1 – 6.

[37] Dietrich Leihsa, Andrzej Adamski, Situational Analysis in Real-Time

Traffic Systems, Procedia - Social and Behavioral Sciences, Volume

20, 2011, Pages 506-513

[38] Zhao, D.; Dai, Y.; Zhang, Z.; Computational Intelligence in Urban

Traffic Signal Control: A Survey, IEEE Transactions on Systems, Man,

and Cybernetics, Part C: Applications and Reviews, Issue: 99 , 1 – 10,

08 August 2011.

[39] Mao-Bin Hu; Rui Jiang; Ruili Wang; Wen-Bo Du; Qing-Song Wu; Optimization of network traffic, IEEE International Conference on Control and Automation, 2009. ICCA 2009., 9-11 Dec. 2009, 2278 –

2281.

[40] Fan Yue-zhen; Lu Dun-min; Wang Qing-chun; Jiang Fa-chao; An improved Dijkstra algorithm used on vehicle optimization route planning, 2010 2nd International Conference on Computer Engineer- ing and Technology (ICCET), Vol. 3, 16-18 April 2010 , 693-696.

[41] B. De Schutter, H. Hellendoorn, A. Hegyi, M. van den Berg and S. K.

Zegeye, Model-based Control of Intelligent Traffic Networks, Intelli- gent Systems, Control and Automation: Science and Engineering, 1, Volume 42, Intelligent Infrastructures, Part 3, Pages 277-310.

[42] Ye Xaofei; Chen Jun; Analysis on traffic congestion propagation in- fluenced by traffic congestion information, 2011 International Confe- rence on Electric Technology and Civil Engineering (ICETCE), 3883 -

3886 , 22-24 April 2011.

[43] Skordylis, A.; Trigoni, N.; Efficient Data Propagation in Traffic- Monitoring Vehicular Networks, IEEE Transactions on Intelligent Transportation Systems, Sept. 2011, 12 , Issue:3, 680 – 694.

[44] Vasirani, M.; Ossowski, S.; A Computational Market for Distributed Control of Urban Road Traffic Systems, IEEE Transactions on Intelli- gent Transportation Systems, June 2011, 12 , Issue:2 , 313 - 321

[45] Papageorgiou, M.; Diakaki, C.; Dinopoulou, V.; Kotsialos, A.; Yibing Wang; Review of road traffic control strategies, Proceedings of the IEEE, Dec 2003, 91 , Issue:12 , 2043 - 2067

[46] Ramaswamy, D.; Medanic, J.V.; Perkins, W.R.; Benekohal, R.F.; Lane assignment on automated highway systems, IEEE Transactions on Vehicular Technology, : 46 , Issue:3 755 - 769 06 August 2002

[47] JianCheng Long, ZiYou Gao, HuaLing Ren and AiPing Lian, Urban traffic congestion propagation and bottleneck identification, Science in China Series F: Information Sciences, 2008, Volume 51, Number 7, Pages 948-964

[48] Yuming Mao, Shiying Shi, Hai Yang and Yuanyuan Zhang, Research

on Method of Double-Layers BP Neural Network in Prediction of

Crossroads’ Traffic Volume, Lecture Notes in Computer Science,

2009, Volume 5553, Advances in Neural Networks – ISNN 2009, Pag- es 909-914.

[49] Lijun TIANa, Haijun HUANG, Tianliang LIU,Day-To-Day Route Choice Decision Simulation Based on Dynamic Feedback Informa- tionJournal of Transportation Systems Engineering and Information Technology, Volume 10, Issue 4, August 2010, Pages 79-85

[50] Huey-Kuo Chen , Che-Fu Hsueh, A model and an algorithm for the dynamic user-optimal route choice problem, Transportation Research Part B: Methodological, Volume 32, Issue 3, 1 April 1998, Pages 219-

234

[51] William H.K. Lam, Yafeng Yin, An activity-based time-dependent traffic assignment model Transportation Research Part B: Methodo- logical, Volume 35, Issue 6, July 2001, Pages 549-574.

[52] M. Darbari, R. Asthana, V K Singh, Integrating Fuzzy Mde-AT Framework for urban traffic simulation, International Journal of Software Engineering, 1(1), 2010.

IJSER © 2012