Application of wavelet technique to freeway incident detection

This paper presents an application of the wavelet technique to freeway incident detection because wavelet techniques have demonstrated superior performance in detecting changes in signals in electrical engineering. Unlike the existing wavelet incident detection algorithm, where the wavelet technique is utilized to denoise data before the data is input into an algorithm, this paper presents a different approach in the application of the wavelet technique to incident detection. In this approach, the features that are extracted from traffic measurements by using wavelet transformation are directly utilized in detecting changes in traffic flow. It is shown in the paper that the extracted features from traffic measurements in incident conditions are significantly different from those in normal conditions. This characteristic of the wavelet technique was used in developing the wavelet incident detection algorithm in this study. The algorithm was evaluated in comparison with the multi-layer feed-forward neural network, probabilistic neural network, radial basis function neural network, California and low-pass filtering algorithms. The test results indicate that the wavelet incident detection algorithm performs better than other algorithms, demonstrating its potential for practical application.     

A genetic algorithm-based method for improving quality of travel time prediction intervals

The transportation literature is rich in the application of neural networks for travel time prediction. The uncertainty prevailing in operation of transportation systems, however, highly degrades prediction performance of neural networks. Prediction intervals for neural network outcomes can properly represent the uncertainty associated with the predictions. This paper studies an application of the delta technique for the construction of prediction intervals for bus and freeway travel times. The quality of these intervals strongly depends on the neural network structure and a training hyperparameter. A genetic algorithm–based method is developed that automates the neural network model selection and adjustment of the hyperparameter. Model selection and parameter adjustment is carried out through minimization of a prediction interval-based cost function, which depends on the width and coverage probability of constructed prediction intervals. Experiments conducted using the bus and freeway travel time datasets demonstrate the suitability of the proposed method for improving the quality of constructed prediction intervals in terms of their length and coverage probability.     

Use of sequential learning for short-term traffic flow forecasting

Accurate short-term traffic flow forecasting has become a crucial step in the overall goal of better road network management. Previous research [H. Kirby, M. Dougherty, S. Watson, Should we use neural networks or statistical models for short term motorway traffic forecasting, International Journal of Forecasting 13 (1997) 43–50.] has demonstrated that a straightforward application of neural networks can be used to forecast traffic flows along a motorway link. The objective of this paper is to report on the application and performance of an alternative neural computing algorithm which involves ‘sequential or dynamic learning’ of the traffic flow process. Our initial work [H. Chen, S. Clark, M.S. Dougherty, S.M. Grant-Muller, Investigation of network performance prediction, Report on Dynamic Neural Network and Performance Indicator development, Institute for Transport Studies, University of Leeds Technical Note 418, 1998 (unpublished)] was based on simulated data (generated using a Hermite polynomial with random noise) that had a profile similar to that of traffic flows in real data. This indicated the potential suitability of dynamic neural networks with traffic flow data. Using the Kalman filter type network an initial application with M25 motorway flow data suggested that a percentage absolute error (PAE) of approximately 9.5% could be achieved for a network with five hidden units (compared with 11% for the static neural network model). Three different neural networks were trained with all the data (containing an unknown number of incidents) and secondly using data wholly obtained around incidents. Results showed that from the three different models, the ‘simple dynamic model’ with the first five units fixed (and subsequent hidden units distributed amongst these) had the best forecasting performance. Comparisons were also made of the networks’ performance on data obtained around incidents. More detailed analysis of how the performance of the three networks changed through a single day (including an incident) showed that the simple dynamic model again outperformed the other two networks in all time periods. The use of ‘piecewise’ models (i.e. where a different model is selected according to traffic flow conditions) for data obtained around incidents highlighted good performance again by the simple dynamic network. This outperformed the standard Kalman filter neural network for a medium-sized network and is our overall recommendation for any future application.     

RENAISSANCE – A unified macroscopic model-based approach to real-time freeway network traffic surveillance

The paper presents a unified macroscopic model-based approach to real-time freeway network traffic surveillance as well as a software tool RENAISSANCE that has been recently developed to implement this approach for field applications. RENAISSANCE is designed on the basis of stochastic macroscopic freeway network traffic flow modeling, extended Kalman filtering, and a number of traffic surveillance algorithms. Fed with a limited amount of real-time traffic measurements, RENAISSANCE enables a number of freeway network traffic surveillance tasks, including traffic state estimation and short-term traffic state prediction, travel time estimation and prediction, queue tail/head/length estimation and prediction, and incident alarm. The traffic state estimation and prediction lay the operating foundation of RENAISSANCE since RENAISSANCE bases the other traffic surveillance tasks on its traffic state estimation or prediction results. The paper first introduces the utilized stochastic macroscopic freeway network traffic flow model and a real-time traffic measurement model, upon which the complete dynamic system model of RENAISSANCE is established with special attention to the handling of some important model parameters. The algorithms for the various traffic surveillance tasks addressed are described along with the functional architecture of the tool. A simulation test was conducted via application of RENAISSANCE to a hypothetical freeway network example with a sparse detector configuration, and the testing results are presented in some detail. Final conclusions and future work are outlined.     

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

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.     

Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network

Development of a universal freeway incident detection algorithm is a task that remains unfulfilled despite the promising approaches that have been recently explored. Incident detection researchers are realizing that an operationally successful detection framework needs to fulfill a full set of recognized needs. In this paper we attempt to define one possible set of universality requirements. Among the set of requirements, a freeway incident detection algorithm needs to be operationally accurate and transferable. Guided by the envisioned requirements, we introduce a new algorithm with potential for enhanced performance. The algorithm is a modified form of the Bayesian-based Probabilistic Neural Network (PNN) that utilizes the concept of statistical distance. The paper is divided into three main sections. The first section is a detailed definition of the attributes and capabilities that a potentially universal freeway incident detection framework should possess. The second section discusses the training and testing of the PNN. In the third section, we evaluate the PNN relative to the universality template previously defined. In addition to a large set of simulated incidents, we utilize a fairly large real incident databases from the I-880 freeway in California and the I-35W in Minnesota to comparatively evaluate the performance and transferability of different algorithms, including the PNN. Experimental results indicate that the new PNN-based algorithm is competitive with the Multi Layer Feed Forward (MLF) architecture, which was found in previous studies to yield superior incident detection performance, while being significantly faster to train. In addition, results also point to the possibility of utilizing the real-time learning capability of this new architecture to produce a transferable incident detection algorithm without the need for explicit off-line retraining in the new site. In this respect, and unlike existing algorithms, the PNN has been found to markedly improve in performance with time in service as it retrains itself on captured incident data, verified by the Traffic Management Center (TMC) operator. Moreover, the overall PNN-based framework promises potential enhancements towards the envisioned universality requirements.     

Understanding the variability of speed distributions under mixed traffic conditions caused by holiday traffic

Understanding the variability of speed patterns and congestion characteristics of interstate freeway systems caused by holiday traffic is beneficial because appropriate countermeasures for safety improvement and congestion mitigation can be prepared and drivers can avoid traffic congestion and change their holiday travel schedules. This study evaluated the traffic congestion patterns during the Thanksgiving holiday period in 2006 using a Gaussian mixture speed distribution estimated by the Expectation–Maximization (EM) algorithm. This mathematical approach showed the potential of improving freeway operational performance evaluation schemes for holiday periods (even non-holiday periods). This study suggested that a Gaussian mixture model using the EM algorithm could be used to properly characterize the severity and the variability of congestion on certain interstate roadway systems. However, this study also pointed out that the fundamental limitations of the mixture model and the statistical significance test about the mixture components should be well understood and need to be further investigated. In addition, because this study investigated the changing patterns of speed distributions with only one interstate freeway system, I-95 northbound, other freeway systems with both directions need to be evaluated so that a more broad and confident analysis on holiday traffic can be achieved.     

Discrete dynamic models for freeway incident detection systems

This paper considers the problem of freeway incident detection within the general framework of computer‐based freeway surveillance and control. A new approach to the detection of freeway traffic incidents is presented based on a discrete‐time stochastic model of the form ARIMA (0, 1, 3) that describes the dynamics of traffic occupancy observations. This approach utilizes real‐time estimates of the variability in traffic occupancies as detection thresholds, thus eliminating the need for threshold calibration and lessening the problem of false‐alarms. Because the moving average parameters of the ARIMA (0, 1, 3) model change over time, these parameters can be updated occasionally. The performance of the developed detection algorithm has been evaluated in terms of detection rate, false‐alarm rate, and average time‐lag to detection, using a total of 1692 minutes of occupancy observations recorded during 50 representative traffic incidents.     

Optimization of mainline traffic via an adaptive co-ordinated ramp-metering control model with dynamic OD estimation

Frequently implemented at freeway accesses to streamline traffic, ramp-metering control strategy is often implemented during rush hours in heavily congested areas. This paper presents a novel ramp-metering control model capable of optimizing mainline traffic by providing metering rates for accesses within the control segments. Based on Payne's continuum traffic stream model, a linear dynamic model with a quadratic objective function is constructed for integrated-responsive ramp-metering control. Incorporating on-line origin–destination (OD) estimation of co-ordinated interchanges into the proposed model increases efficiency of the control. In addition, an iterative algorithm is proposed to obtain the optimal solution. Simulation results demonstrate the robustness of the proposed model and its ability to streamline freeway traffic while avoiding traffic congestion.     

Freeway ramp control using fuzzy set theory for inexact reasoning

This paper presents a fuzzy controller for freeway ramp metering, which uses rules of the form: IF “freeway condition” THEN “control action.” The controller has been designed to consider varied levels of congestion, a downstream control area, changing occupancy levels, upstream flows, and a distributed detector array in its rule base. Through fuzzy implication, the inference of each rule is used to the degree to which the condition is true. Using a dynamic simulation model of conditions0fj at the San Francisco-Oakland Bay Bridge, the action of the fuzzy controller is compared to the existing “crisp” control scheme, and an idealized controller. Tests under a variety of scenarios with different incident locations and capacity reductions show that the fuzzy controller is able to extract 40 to 100% of the possible savings in passenger-hours. In general, the fuzzy algorithm displays smooth and rapid response to incidents, and significantly reduces the minute-miles of congestion.     

Real-time freeway traffic state estimation based on extended Kalman filter: Adaptive capabilities and real data testing

This paper reports on real data testing of a real-time freeway traffic state estimator, with a particular focus on its adaptive capabilities. The pursued general approach to the real-time adaptive estimation of complete traffic state in freeway stretches or networks is based on stochastic macroscopic traffic flow modeling and extended Kalman filtering. One major innovative feature of the traffic state estimator is the online joint estimation of important model parameters (free speed, critical density, and capacity) and traffic flow variables (flows, mean speeds, and densities), which leads to three significant advantages of the estimator: (1) avoidance of prior model calibration; (2) automatic adaptation to changing external conditions (e.g. weather and lighting conditions, traffic composition, control measures); (3) enabling of incident alarms. These three advantages are demonstrated via suitable real data testing. The achieved testing results are satisfactory and promising for subsequent applications.     

A probabilistic optimization model for allocating freeway sensors

This paper proposes a sensor location model to identify a sensor configuration that minimizes overall freeway performance monitoring errors while considering the consequences of probabilistic sensor failures. To date, existing sensor location models for freeway monitoring inherently assume that either deployed sensors never fail or the consequences of sensor failure are trivial matters. However, history has revealed that neither assumption is realistic, suggesting that ignoring failures in sensor allocation models may actually produce a significantly suboptimal configuration in the real world. Our work addresses this dilemma by developing a probabilistic optimization model that will minimize the error expectation by examining all possible failure scenarios, each with an occurrence probability. To ensure the scenario completeness and uniqueness, a sensor failure scenario is represented by using a binary string with 1 indicating an operational sensor at a given site and 0 for sensor failure or no sensor deployed. When applied to a case study network, it is shown that an optimal configuration that considers sensor failure is significantly different from an optimal configuration that ignores sensor failure, revealing that sensor failures pose non-trivial consequences on performance monitoring accuracy.     

Stochastic cell transmission model (SCTM): A stochastic dynamic traffic model for traffic state surveillance and assignment

The paper proposes a first-order macroscopic stochastic dynamic traffic model, namely the stochastic cell transmission model (SCTM), to model traffic flow density on freeway segments with stochastic demand and supply. The SCTM consists of five operational modes corresponding to different congestion levels of the freeway segment. Each mode is formulated as a discrete time bilinear stochastic system. A set of probabilistic conditions is proposed to characterize the probability of occurrence of each mode. The overall effect of the five modes is estimated by the joint traffic density which is derived from the theory of finite mixture distribution. The SCTM captures not only the mean and standard deviation (SD) of density of the traffic flow, but also the propagation of SD over time and space. The SCTM is tested with a hypothetical freeway corridor simulation and an empirical study. The simulation results are compared against the means and SDs of traffic densities obtained from the Monte Carlo Simulation (MCS) of the modified cell transmission model (MCTM). An approximately two-miles freeway segment of Interstate 210 West (I-210W) in Los Ageles, Southern California, is chosen for the empirical study. Traffic data is obtained from the Performance Measurement System (PeMS). The stochastic parameters of the SCTM are calibrated against the flow-density empirical data of I-210W. Both the SCTM and the MCS of the MCTM are tested. A discussion of the computational efficiency and the accuracy issues of the two methods is provided based on the empirical results. Both the numerical simulation results and the empirical results confirm that the SCTM is capable of accurately estimating the means and SDs of the freeway densities as compared to the MCS.     

基于RBF神经网络的发动机怠速抖动故障诊断

针对难以获取发动机怠速抖动的精确数学模型,文章提出一种基于RBF神经网络的模型逼近算法。该算法利用RBF神经网络良好的模型逼近能力,对造成发动机怠速抖动的几种典型故障原因进行了诊断。实验结果表明该算法具有良好的逼近效率和诊断效果。     

An application of the CUSUM algorithm to freeway incident detection based on two contiguous detectors

The CUSUM (cumulative sum of log‐likelihood ratio) algorithm is a detection algorithm that shows potential for the improvement of incident detection algorithms because it is designed to minimize the mean detect delay for a given false alarm constraint and it can also detect changes with different patterns. In this study, the CUSUM algorithm was applied to freeway incident detection by integrating traffic measurements from two contiguous loop detectors and the non‐stationarity of traffic flows. The developed algorithm was tested based on incident data from the PATH program, with consideration given to the impact of different geometric conditions on algorithm performance. It was also compared with two existing algorithms, in order to address the influence of traffic patterns. The evaluation results show that the CUSUM incident detection algorithm can perform equally well in comparison with the selected algorithms.     

Modeling the effects of traveler information on freeway origin–destination demand prediction

The primary focus of this research is to develop an approach to capture the effect of travel time information on travelers’ route switching behavior in real-time, based on on-line traffic surveillance data. It also presents a freeway Origin–Destination demand prediction algorithm using an adaptive Kalman Filtering technique, where the effect of travel time information on users’ route diversion behavior has been explicitly modeled using a dynamic, aggregate, route diversion model. The inherent dynamic nature of the traffic flow characteristics is captured using a Kalman Filter modeling framework. Changes in drivers’ perceptions, as well as other randomness in the route diversion behavior, have been modeled using an adaptive, aggregate, dynamic linear model where the model parameters are updated on-line using a Bayesian updating approach. The impact of route diversion on freeway Origin–Destination demands has been integrated in the estimation framework. The proposed methodology is evaluated using data obtained from a microscopic traffic simulator, INTEGRATION. Experimental results on a freeway corridor in northwest Indiana establish that significant improvement in Origin–Destination demand prediction can be achieved by explicitly accounting for route diversion behavior.     

Towards universal freeway incident detection algorithms

This paper reports the intensive test of the new transport systems centre (TSC) algorithm applied to incident detection on freeways. The TSC algorithm is designed to fulfil the universality expectations of automated incident detection. The algorithm consists of two modules: data processing module and incident detection module. The data processing module is designed to handle specific features of different sites. The Bayesian network based incident detection module is used to store and manage general expert traffic knowledge, and to perform coherent reasoning to detect incidents. The TSC algorithm is tested using 100 field incident data sets obtained from Tullamarine Freeway and South Eastern Freeway in Melbourne, Australia. The performance of the algorithm demonstrates its competitiveness with the best performing neural network algorithm which was developed and tested using the same incident data sets in an early research. Most importantly, both the detection rate and false alarm rate of the TSC algorithm are not sensitive to the incident decision threshold, which greatly improves the stability of incident detection. In addition, a very consistent algorithm performance is achieved when the TSC algorithm is transferred from Southern Expressway of Adelaide to both Tullamarine Freeway and South Eastern Freeway of Melbourne. No substantial algorithm retraining is required. A significant step towards algorithm universality is possible from this research.     

Stochasticity of freeway operational capacity and chance-constrained ramp metering

The notion of capacity is essential to the planning, design, and operations of freeway systems. However, in the practice freeway capacity is commonly referred as a theoretical/design value without consideration of operational characteristics of freeways. This is evident from the Highway Capacity Manual (HCM) 2000 in that no influence from downstream traffic is considered in the definition of freeway capacity. In contrast to this definition, in this paper, we consider the impact of downstream traffic and define freeway operational capacity as the maximum hourly rate at which vehicles can be expected to traverse a point or a uniform section of a roadway under prevailing traffic flow conditions. Therefore freeway operational capacity is not a single value with theoretical notion. Rather, it changes under different traffic flow conditions. Specifically, this concept addresses the capacity loss during congested traffic conditions. We further study the stochasticity of freeway operational capacity by examining loop detector data at three specifically selected detector stations in the Twin Cities’ area. It is found that values of freeway operational capacity under different traffic flow conditions generally fit normal distributions. In recognition of the stochastic nature of freeway capacity, we propose a new chance-constrained ramp metering strategy, in which, constant capacity value is replaced by a probabilistic one that changes dynamically depending on real-time traffic conditions and acceptable probability of risk determined by traffic engineers. We then improve the Minnesota ZONE metering algorithm by applying the stochastic chance constraints and test the improved algorithm through microscopic traffic simulation. The evaluation results demonstrate varying degrees of system improvement depending on the acceptable level of risk defined.     

Dynamic traffic assignment of cooperative adaptive cruise control

Advances in connected and automated vehicle technologies have resulted in new vehicle applications, such as cooperative adaptive cruise control (CACC). Microsimulation models have shown significant increases in capacity and stability due to CACC, but most previous work has relied on microsimulation. To study the effects of CACC on larger networks and with user equilibrium route choice, we incorporate CACC into the link transmission model (LTM) for dynamic network loading. First, we derive the flow-density relationship from the MIXIC car-following model of CACC (at 100% CACC market penetration). The flow-density relationship has an unusual shape; part of the congested regime has an infinite congested wave speed. However, we verify that the flow predictions match observations from MIXIC modeled in VISSIM. Then, we use the flow-density relationship from MIXIC in LTM. Although the independence of separate links restricts the maximum congested wave speed, for common freeway link lengths the congested wave speed is sufficiently high to fit the observed flows from MIXIC. Results on a freeway and regional networks (with CACC-exclusive lanes) indicate that CACC could reduce freeway congestion, but naïve deployment of CACC-exclusive lanes could cause an increase in total system travel time.