Download Free Travel Time Estimation And Short Term Prediction In Urban Arterial Networks Using Conditional Independence Graphs And State Space Neural Networks Book in PDF and EPUB Free Download. You can read online Travel Time Estimation And Short Term Prediction In Urban Arterial Networks Using Conditional Independence Graphs And State Space Neural Networks and write the review.

Proceedings Annie Conference, November 2006, St. Louis, Missouri. The newest volume in this series presents refereed papers in the following categories and their applications in the engineering domain: Neural Networks; Complex Networks; Evolutionary Programming; Data Mining; Fuzzy Logic; Adaptive Control; Pattern Recognition; Smart Engineering System Design. These papers are intended to provide a forum for researchers in the field to exchange ideas on smart engineering system design.
As urban centers become larger and more densely developed, their roadway networks tend to experience more severe congestion for longer periods of the day and increasingly unreliable travel times. Proactive traffic management (PTM) strategies such as proactive traffic signal control systems and advanced traveler information systems provide the potential to cost effectively improve road network operations. However, these proactive management strategies require an ability to accurately predict near-future traffic conditions. Traffic conditions can be described using a variety of measures of performance and travel time is one of the most valued by both travelers and transportation system managers. Consequently, there exists a large body of literature dedicated to methods for performing travel time prediction. The majority of the existing body of research on travel time prediction has focused on freeway travel time prediction using fixed point sensor data. Predicting travel times on signalized arterials is more challenging than on freeways mainly as a result of the higher variation of travel times in these environments. For both freeways and arterial environments, making predictions in real-time is more challenging than performing off-line predictions, mainly because of data availability issues that arise for real-time applications. Recently, Bluetooth detectors have been utilized for collecting both spatial (i.e. travel time) and fixed point (e.g. number of detections) data. Bluetooth detectors have surpassed most of the conventional travel time measuring techniques in three main capacities: (i) direct measurement of travel time, (ii) continuous collection of travel times provides large samples, and (iii) anonymous detection. Beside these advantages, there are also caveats when using these detectors: (i) the Bluetooth obtained data include different sources of outliers and measurement errors that should be filtered out before the data are used in any travel time analysis and (ii) there is an inherent time lag in acquiring Bluetooth travel times (due to the matching of the detections at the upstream and downstream sensors) that should be carefully handled in real-time applications. In this thesis, (1) the magnitude of Bluetooth travel time measurement error has been examined through a simulation framework; (2) a real-time proactive outlier detection algorithm, which is suitable for filtering out data anomalies in Bluetooth obtained travel times, has been proposed; (3) the performance of the existing real-time outlier detection algorithms has been evaluated using both field data and simulation data; and (4) two different data-driven methodologies, that are appropriate for real-time applications, have been developed to predict near future travel times on arterials using data obtained from Bluetooth detectors. The results of this research demonstrate that (1) although the mean Bluetooth travel time measurement error is sufficiently close to zero across all the examined traffic conditions, for some situations the 95% confidence interval of the mentioned error approaches 35% of the true mean travel time; (2) the proposed proactive filtering algorithm appropriately detects the Bluetooth travel time outliers in real time and outperforms the existing data-driven filtering techniques; (3) the performance of different outlier detection algorithms can be objectively quantified under different conditions using the developed simulation framework; (4) the proposed prediction approaches significantly improved the accuracy of travel time predictions for 5-minutre prediction horizon. The daily mean absolute relative errors are improved by 18% to 24% for the proposed k-NN model and 8% to 14% for the proposed Markov model; (5) prevailing arterial traffic state and its transition through the course of the day can be adequately modeled using data obtained from Bluetooth technology.
A model for estimating travel time on short arterial links of congested urban networks, using currently available technology, is introduced in this thesis. The objective is to estimate travel time, with an acceptable level of accuracy for real-life traffic problems, such as congestion management and emergency evacuation. To achieve this research objective, various travel time estimation methods, including highway trajectories, multiple linear regression (MLR), artificial neural networks (ANN) and K-nearest neighbor (K-NN) were applied and tested on the same dataset. The results demonstrate that ANN and K-NN methods outperform linear methods by a significant margin, also, show particularly good rformance in detecting congested intervals. To ensure the quality of the analysis results, set of procedures and algorithms based on traffic flow theory and test field information, were introduced to validate and clean the data used to build, train and test the different models.
Centralization of work, population and economic growth alongside continued urbanization are the main causes of congestion. As cities strive to update or expand aging infrastructure, the application of big data, new models and analytics to better understand and help to combat traffic congestion is crucial to the health and development of our smart cities of XXI century. Traffic support tools specifically designed to detect, forecast and alert these conditions are highly requested nowadays.This dissertation is dedicated to study techniques that may help to estimate and forecast conditions about a traffic network. First, we consider the problem Dynamic Travel Time (DTT) short-term forecast based on data driven methods. We propose two fusion techniques to compute short-term forecasts from clustered time series. The first technique considers the error covariance matrix and uses its information to fuse individual forecasts based on best linear unbiased estimation principles. The second technique exploits similarity measurements between the signal to be predicted and clusters detected in historical data and it performs afusion as a weighted average of individual forecasts. Tests over real data were implemented in the study case of the Grenoble South Ring, it comprises a highway of 10.5Km monitored through the Grenoble Traffic Lab (GTL) a real time application was implemented and open to the public.Based on the previous study we consider then the problem of simultaneous density/flow reconstruction in urban networks based on heterogeneous sources of information. The traffic network is modeled within the framework of macroscopic traffic models, where we adopt Lighthill-Whitham-Richards (LWR) conservation equation and a piecewise linear fundamental diagram. The estimation problem considers two key principles. First, the error minimization between the measured and reconstructed flows and densities, and second the equilibrium state of the network which establishes flow propagation within the network. Both principles are integrated together with the traffic model constraints established by the supply/demand paradigm. Finally the problem is casted as a constrained quadratic optimization with equality constraints in order to shrink the feasible region of estimated variables. Some simulation scenarios based on synthetic data for a manhattan grid network are provided in order to validate the performance of the proposed algorithm.
The artificial neural network (ANN) approach has been recognized as a capable technique to model the highly complex and nonlinear problem of travel time prediction. In addition to the nonlinearity, a traffic system is also temporally and spatially dynamic. Addressing the temporal-spatial relationships of a traffic system in the context of neural networks, however, has not received much attention. Furthermore, many of the past studies have not fully explored the inclusion of incident information into the ANN model development, despite that incident might be a major source of prediction degradations. Additionally, directly deriving corridor travel times in a one-step manner raises some intractable problems, such as pairing input-target data, which have not yet been adequately discussed. In this study, the corridor travel time prediction problem has been divided into two stages with the first stage on prediction of the segment travel time and the second stage on corridor travel time aggregation methodologies of the predicted segmental results. To address the dynamic nature of traffic system that are often under the influence of incidents, time delay neural network (TDNN), state-space neural network (SSNN), and an extended state-space neural network (ExtSSNN) that incorporates incident inputs are evaluated for travel time prediction along with a traditional back propagation neural network (BP) and compared with baseline methods based on historical data. In the first stage, the empirical results show that the SSNN and ExtSSNN, which are both trained with Bayesian regulated Levenberg Marquardt algorithm, outperform other models. It is also concluded that the incident information is redundant to the travel time prediction problem with speed and volume data as inputs. In the second stage, the evaluations on the applications of the SSNN model to predict snapshot travel times and experienced travel times are made. The outcomes of these evaluations are satisfactory and the method is found to be practically significant in that it (1) explicitly reconstructs the temporalspatial traffic dynamics in the model, (2) is extendable to arbitrary O-D pairs without complete retraining of the model, and (3) can be used to predict both traveler experiences and system overall conditions.