Ruey Long Cheu

Neural Networks for Real-Time Traffic Signal Control

Real-time traffic signal control is an integral part of the urban traffic control system, and providing effective real-time traffic signal control for a large complex traffic network is an extremely challenging distributed control problem. This paper adopts the multiagent system approach to develop distributed unsupervised traffic responsive signal control models, where each agent in the system is a local traffic signal controller for one intersection in the traffic network. The first multiagent system is developed using hybrid computational intelligent techniques. Each agent employs a multistage online learning process to update and adapt its knowledge base and decision-making mechanism. The second multiagent system is developed by integrating the simultaneous perturbation stochastic approximation theorem in fuzzy neural networks (NN). The problem of real-time traffic signal control is especially challenging if the agents are used for an infinite horizon problem, where online learning has to take place continuously once the agent-based traffic signal controllers are implemented into the traffic network. A comprehensive simulation model of a section of the Central Business District of Singapore has been developed using PARAMICS microscopic simulation program. Simulation results show that the hybrid multiagent system provides significant improvement in traffic conditions when evaluated against an existing traffic signal control algorithm as well as the SPSA-NN-based multiagent system as the complexity of the simulation scenario increases. Using the hybrid NN-based multiagent system, the mean delay of each vehicle was reduced by 78% and the mean stoppage time, by 85% compared to the existing traffic signal control algorithm. The promising results demonstrate the efficacy of the hybrid NN-based multiagent system in solving large-scale traffic signal control problems in a distributed manner

Cooperative, hybrid agent architecture for real-time traffic signal control

This paper presents a new hybrid, synergistic approach in applying computational intelligence concepts to implement a cooperative, hierarchical, multiagent system for real-time traffic signal control of a complex traffic network. The large-scale traffic signal control problem is divided into various subproblems, and each subproblem is handled by an intelligent agent with a fuzzy neural decision-making module. The decisions made by lower-level agents are mediated by their respective higher-level agents. Through adopting a cooperative distributed problem solving approach, coordinated control by the agents is achieved. In order for the multiagent architecture to adapt itself continuously to the dynamically changing problem domain, a multistage online learning process for each agent is implemented involving reinforcement learning, learning rate and weight adjustment as well as dynamic update of fuzzy relations using an evolutionary algorithm. The test bed used for this research is a section of the Central Business District of Singapore. The performance of the proposed multiagent architecture is evaluated against the set of signal plans used by the current real-time adaptive traffic control system. The multiagent architecture produces significant improvements in the conditions of the traffic network, reducing the total mean delay by 40% and total vehicle stoppage time by 50%.

Automated detection of lane-blocking freeway incidents using artificial neural networks

Abstract A major source of urban freeway delay in the U.S. is non-recurring congestion caused by incidents. The automated detection of incidents is an important function of a freeway traffic management center. A number of incident detection algorithms, using inductive loop data as input, have been developed over the past several decades, and a few of them are being deployed at urban freeway systems in major cities. These algorithms have shown varying degrees of success in their detection performance. In this paper, we present a new incident detection technique based on artificial neural networks (ANNs). Three types of neural network models, namely the multi-layer feedforward (MLF), the self-organizing feature map (SOFM) and adaptive resonance theory 2 (ART2), were developed to classify traffic surveillance data obtained from loop detectors, with the objective of using the classified output to detect lane-blocking freeway incidents. The models were developed with simulation data from a study site and tested with both simulation and field data at the same site. The MLF was found to have the highest potential, among the three ANNs, to achieve a better incident detection performance. The MLF was also tested with limited field data collected from three other freeway locations to explore its transferability. Our results and analyzes with data from the study site as well as the three test sites have shown that the MLF consistently detected most of the lane-blocking incidents and typically gave a false alarm rate lower than the California, McMaster and Minnesota algorithms currently in use.

PROBE VEHICLE POPULATION AND SAMPLE SIZE FOR ARTERIAL SPEED ESTIMATION

Equipping probe vehicles with global posi- tioning system (GPS)receivers is a cost-effective way of collecting real-time location and speed information. A large-scale, nationwide travel speed information acquisi- tion and dissemination system has already been in opera- tion in Singapore, using a large fleet of taxis equipped with differential GPS (DGPS)receivers. This paper discusses the use of simulation approach to study the reliability of estimated average arterial link speed from probe vehicles. This study is based on the road network at the Clementi town area in Singapore. Simulation runs were made with a variety of traffic volumes, and with different percentages of probes in the total traffic volume. The reliability of link speed estimate is analyzed with respect to (1)overall probe vehicle percentages; and (2)number of probe vehicles sam- pled in a link. Results indicate that for an absolute error in estimated average link speed to be less than 5 km/hr at least 95% of the time, the network needs to have 4% to 5% of active probe vehicles, or at least ten probe vehicles must passed through a link within the sampling period.

INCIDENT DETECTION USING SUPPORT VECTOR MACHINES

Abstract This paper presents the applications of a recently developed pattern classifier called support vector machine (SVM) in incident detection. Support vector machine is constructed from a unique learning algorithm that extracts training vectors that lie closest to the class boundary, and makes use of them to construct a decision boundary that optimally separates the different classes of data. Two SVMs, each with a different non-linear kernel function, were trained and tested with simulated incident data from an arterial network. Test results have shown that SVM offers a lower misclassification rate, higher correct detection rate, lower false alarm rate and slightly faster detection time than the multi-layer feed forward neural network (MLF) and probabilistic neural network models in arterial incident detection. Three different SVMs have also been developed and tested with real I-880 Freeway data in California. The freeway SVMs have exhibited incident detection performance as good as the MLF, one of the most promising incident detection model developed to date.

Taxi Dispatch System Based on Current Demands and Real-Time Traffic Conditions

The existing taxi dispatch system that taxi operators in Singapore use to handle current bookings was studied. This dispatch system adopts the Global Positioning System and is based on the nearest-coordinate method: the taxi assigned for each booking is the one with the shortest, direct, straight-line distance to the customer location. However, the taxi assigned under this system often is not capable of reaching the customer in the shortest time possible. An alternative dispatch system is proposed, whereby the dispatch of taxis is determined by real-time traffic conditions. In the proposed system, the taxi assigned the booking job is the one with the shortest time path, reaching the customer in the shortest time. This dispatch ensures that customers are served within the shortest period of time and increases customer satisfaction. The effectiveness of both the existing and the proposed dispatch systems is investigated through computer simulations. The results from a simulation model of the Singapore central business district network are presented and analyzed. Data from the simulations show that the proposed dispatch system is capable of being more efficient in dispatching taxis more quickly and leads to more than 50% reductions in passenger pickup times and average travel distances. A more efficient dispatch system would result in higher standards of customer service and a more organized taxi fleet to meet customer demands better.

GIS and genetic algorithms for HAZMAT route planning with security considerations

Singapore is the third largest oil-refining centre in the world, with a large petrochemical hub located at Jurong Island. In view of the increasing concern for transportation security, there is an urgent need to improve the way trucks carrying hazardous materials (HAZMATs) are being routed on urban and suburban road networks. Routing of such vehicles should not only ensure the safety of travelers in the network but also consider the risk of the HAZMAT being used as weapon of mass destruction. This paper explores a novel approach to evaluating the risk of HAZMAT transportation by integrating Geographic Information Systems (GISs) and Genetic Algorithms (GAs). A set of evaluation criteria that are used to route the HAZMAT vehicles was identified and assessed. The criteria considered are related to safety, costs and, more importantly, security. A GIS was employed to quantify the factors on each link in the network that contribute to the evaluation criteria for a possible route, while a GA was applied to efficiently determine the weights of the different factors in the hierarchical form, allowing for the computation of the relative total costs of the alternate routes. Therefore, each route can be quantified by a generalized cost function from which the suitability of the routes for HAZMAT transportation can be compared. The proposed route evaluation method was demonstrated on a typical portion of the road network in Singapore.

Evaluation of adaptive neural network models for freeway incident detection

Automated incident detection is an essential component of a modern freeway traffic monitoring system. A number of neural network (NN)-based incident detection models have been tested independently over the past decade. This paper evaluates the adaptability of three promising NN models for this problem: a multilayer feed-forward NN (MLFNN), a basic probabilistic NN (BPNN) and a constructive probabilistic NN (CPNN). These three models have been developed on an original freeway site in Singapore and then adapted to a new freeway site in California. In addition to their incident detection performance, their ability to adapt to new freeway sites, and network sizes have also been compared. A novel updating scheme has been used for adjustment of smoothing parameter of the BPNN. Results of this study show that the MLFNN model has the best incident detection performance at the development site while CPNN model has the best performance after model adaptation at the new site. In addition, the adaptation method for CPNN model is less laborious. The efficient network pruning procedure for the CPNN network resulted in a smaller network size, making it easier to implement it for real-time application. The results suggest that CPNN model has good potential for application in an operational automatic incident detection system for freeways.

Relocation Simulation Model for Multiple-Station Shared-Use Vehicle Systems

A shared-use vehicle system has a small number of vehicles reserved exclusively for use by a relatively larger group of members. Challenged by accessible and economical public transportation systems, multiple-station shared-use vehicle companies are driven to gain a competitive edge by using an operator-based relocation system to ensure privacy, simplicity, and convenience to their users. To help operators identify measures to maximize resources and enhance service levels, a simulation model is developed, with an emphasis on operator-based relocation techniques. A qualitative analysis conducted on operator-based relocation systems provides insights on the key issues involved and their influences over each other. On the basis of this analysis, a time-stepping simulation model is developed, and three performance indicators are proposed to evaluate the effectiveness of the different relocation techniques. The model has been validated by using commercially operational data from a local shared-use vehicle company. With the existing operational data as the base scenario, two proposed relocation techniques, namely, shortest time and inventory balancing techniques, and various operating parameters are studied. The simulation results have shown that if the inventory balancing relocation technique is used, the system can afford a 10% reduction in car park lots and 25% reduction in staff strength, generating cost savings of approximately 12.8% without lowering the level of service for users.

Classification of freeway traffic patterns for incident detection using constructive probabilistic neural networks

This paper proposes a new technique for freeway incident detection using a constructive probabilistic neural network (CPNN). The CPNN incorporates a clustering technique with an automated training process. The work reported in this paper was conducted on Ayer Rajah Expressway (AYE) in Singapore for incident detection model development, and subsequently on I-880 freeway in California, for model adaptation. The model developed achieved incident detection performance of 92% detection rate and 0.81% false alarm rate on AYE, and 91.30% detection rate and 0.27% false alarm rate on I-880 freeway using the proposed adaptation method. In addition to its superior performance, the network pruning method employed facilitated model size reduction by a factor of 11 compared to a conventional probabilistic neural network. A more impressive size reduction by a factor of 50 was achieved after the model was adapted for the new site. The results from this paper suggest that CPNN is a better adaptive classifier for incident detection problem with a changing site traffic environment.