2013 Session: 609

• Contrasting Artificial Intelligence Effectiveness: Application to Traffic Signal Optimization
  Abstract: Signal timing optimization in urban transportation networks is a NP-hard problem with no exact method to find an optimal solution. Therefore, researchers have used different methods and artificial intelligence algorithms to find near-optimal solutions. Choosing the right algorithm to solve the problem is extremely important since it directly influences the solution and consequently network performance. Of course, different algorithms have different convergence properties and due to the extremely large solution space of the problem, selecting a more efficient algorithm with lower runtime is vital. This study compares the performance of five meta-heuristic algorithms in optimizing traffic signals in terms of their runtimes and solution quality. These algorithms are: simple genetic algorithm (SGA), elitist genetic algorithm (EGA), micro-elitist genetic algorithm (MEGA), evolution strategy (ES) and, elitist evolution strategy (ES+).Findings indicated that when calibrated, each algorithm is capable of finding near-optimal solutions that prevent queue spillovers and gridlocks. In general, ES+ required the fewest number of Fitness Function Evaluations (FFE) to reach most levels of the upper-bound. ES required similar number of FFE to reach up to 90% of the upper-bound; however, for higher levels it was considerably slower than ES+. MEGA was very quick in early improvements in the fitness value; however, in most of the cases ES+ outperformed it reaching higher levels of the upper-bound. In symmetric demand patterns, EGA was much faster than ES+ in reaching to 97.5% of the theoretical upper-bound. Finally, SGA was in general among the least efficient algorithms for all demand patterns.
  Authors: Hajbabaie, Ali; Benekohal, Rahim F.
  Authors: Hajbabaie, Ali; Benekohal, Rahim F.
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-0264
• Use of Principal Component Analysis to Deal with Class Imbalance Problem for Traffic Incident Detection
  Abstract: High imbalance occurs in real-world where the traffic incident detection system is aimed to detect a rare but important case - incident case. Traffic incident detection can be treated as a task of learning classifiers from imbalanced or skewed datasets. Based on principal component analysis (PCA), a one-class classifier for incident detection is constructed from the major and minor principal components of normal instances. The experiments are conducted with a real traffic data collected from A12 highway in the Netherlands. The parameters setting, including the significance level, the percentage of the total variation explained and the upper bound of the eigenvalues for the minor components are discussed. The testing results demonstrate that this method achieves better performance comparing with partial least squares regression. It is shown to be a promising method for traffic incident detection.
  Authors: Changjiang, Zheng; Chen, Shuyan; Wang, Wei; Lu, Jian
  Authors: Changjiang, Zheng; Chen, Shuyan; Wang, Wei; Lu, Jian
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-0935
• Exploring the Properties of Mean-Variance Relations in Freeway Travel Times
  Abstract: Travel time estimation models have been widely studied in transportation field. However, the variation in the mean and standard deviation of travel times has been much less investigated. A temporary decrease in capacity (e.g. congestion caused by an active bottleneck) leads to a quite significant difference in the standard deviation of travel time for congestion onset and dissipation periods. This phenomenon results in hysteresis loops where the periods in congestion offset exhibit a higher or a lower travel time variance than the ones in congestion onset with the same mean travel time. The aim of this paper is to identify empirical reasons that cause the hysteresis phenomenon. Within this framework, using an analytical expression of travel time and closed form expression of mean and variance, hysteresis loops are reconstructed. This allows us to decompose the problem into its components. Factor analysis is implemented to identify which components cause the difference between onset and offset periods, and lead to a hysteresis pattern in mean-standard deviation curve.
  Authors: Yildirimoglu, Mehmet; Koymans, Anne; Geroliminis, Nikolas
  Authors: Yildirimoglu, Mehmet; Koymans, Anne; Geroliminis, Nikolas
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-1179
• Traffic Incident Detection Using Random Forest
  Abstract: This paper presents the applications of random forest in traffic incident detection. The detection performance is evaluated by the common criteria including detection rate, false alarm rate, mean time to detection, classification rate and the area under the curve of the receiver operating characteristic (ROC). Different from decision tree, random forest uses a combination of classification trees instead of a single tree to construct random forest model. This model can improve the average performances in traffic incident detection just by voting the decision tree classifiers. Two experiments are performed to investigate the potential application of random forest to traffic incident detection from the perspective of classification strength and correlation. Random forest trains many individual decision tree classifiers to construct the classifier ensemble, and then uses this classifier ensemble to detect the traffic incidents. Consequently, it needs to train many times. Compared with decision tree, the training time cost of decision tree is much lower, which is because of decision tree only need train one time. The detection performance of the random forest was compared to multi-layer feed forward neural networks (MLF) which yield superior incident detection performance in the previous studies. The experimental results indicate that random forest is competitive with MLF.
  Authors: Liu, Qingchao; Lu, Jian; Chen, Shuyan
  Authors: Liu, Qingchao; Lu, Jian; Chen, Shuyan
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-1610
• Agent-Based Modeling of Intergovernmental Decision Making: How Institutional Rules Generate Basins of Attraction in Funding Transportation Projects
  Abstract: A Pattern-Oriented, Agent Based Model (ABM) of an intergovernmental network is presented to demonstrate an application of complex systems and computational modeling in real world transportation policy implementation processes. This ABM simulates the dynamics of intergovernmental decision making that is deployed for transportation project prioritization processes. The ABM simulates baseline and alternate intergovernmental institutional rule structures and assesses their impacts on financial investment flows from federal to state, regional and local scale governments. The current version of the ABM is limited to simulating roadway projects in the state of Vermont that are primarily funded through US Surface Transportation Program and Interstate Maintenance Program. Multiple focus groups, individual interviews, and analysis of federal, state and regional scale transportation project and program data was used to calibrate this ABM. In particular, this ABM demonstrates how institutional rules set by federal, state and regional government agencies generate “basins of attraction” in funding roadway projects. The results from experimental simulations are presented to test system-wide effects of alternate institutional designs on the differential emergence of roadway project prioritization patterns and funding allocations across regions and local towns.
  Authors: Zia, Asim; Koliba, Christopher
  Authors: Zia, Asim; Koliba, Christopher
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-2153
• Modeling Yard Crane Operators as Reinforcement Learning Agents
  Abstract: Due to the importance of drayage operations, operators at marine container terminals are increasingly looking to reduce the time a truck spends at the terminal to complete a transaction. This study introduces an agent-based approach to model yard cranes for the analysis of truck turn time. The objective of the model is to solve the yard crane scheduling problem (i.e. determining the sequence of drayage trucks to serve to minimize their waiting time). It is accomplished by modeling the yard crane operators as agents that employ reinforcement learning; specially, q-learning. The proposed agent-based, q-learning model is developed using Netlogo. Experimental results show that the q-learning model is very effective in assisting the yard crane operator to select the next best move. Thus, the proposed q-learning model could potentially be integrated into existing yard management systems to automate the truck selection process and thereby improve yard operations.
  Authors: Fotuhi, Fateme; Huynh, Nathan N.; Vidal, Jose M.; Xie, Yuanchang
  Authors: Fotuhi, Fateme; Huynh, Nathan N.; Vidal, Jose M.; Xie, Yuanchang
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-2671
• Stochastic Network Design Problem with Fuzzy Goals
  Abstract: The transportation network design problem (NDP) is a high capital investment decision-making problem that inherently involves both subjective and objective uncertainties as well as multiple objectives. Goal programming is a practically useful approach with an explicit consideration of planners’ goal setting and priority structure among the multiple objectives. In this paper, we develop a hybrid goal programming (HGP) approach for modeling both subjective and objective uncertainties simultaneously in the NDP decision-making process. Specifically, planners’ subjective uncertainty on the linguistic setting of goals and priority structure is characterized as fuzzy variables with nonlinear achievement and satisfaction functions, while the objective travel demand uncertainty is characterized as random variables with predefined probability distributions. The HGP NDP is formulated as a chance constrained model in a bi-level programming framework and solved by a random simulation and fuzzy evaluation based genetic algorithm solution procedure. Numerical examples are also provided to demonstrate the features of the proposed HGP approach in solving the NDP under uncertain environments.
  Authors: Xu, Xiangdong; Chen, Anthony; Cheng, Lin
  Authors: Xu, Xiangdong; Chen, Anthony; Cheng, Lin
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-2770
• Activity Pattern Recognition by Using Support Vector Machines with Multiple Classes
  Abstract: The focus of this paper is to learn the daily activity engagement patterns of travelers by using a nontraditional model called Support Vector Machines (SVM) that is widely used in Artificial intelligence and Machine Learning. It is postulated that an individual’s choice of activities depends not only on socio-demographic characteristics but also on previous activities of individual at the same day. In the paper, Markov Chain models are used to study the sequential choice of activities. The dependency between activity type, activity sequence and socio-demographic data are captured by employing Conditional Random Fields. In order to learn model parameters, we use sequential multinomial logit model and multiclass Support Vector Machines (K-SVM) with two different dependency structures. In the first dependency structure, it is assumed that type of activity at time t depends on the last previous activity and sociodemographic data, whereas in the second structure we assume activity selection at time t depends on all previous activity types of the individual on the same day and her sociodemographic characteristics. The models are applied to data drawn from Orange County and San Diego County households and a comparison of the accuracy of estimation indicates the superiority of K-SVM with first dependency structure over the other models tested. Additionally, we show that by using different sets of explanatory variables or tuning parameters of the kernel function in K-SVM, its accuracy in estimating activity patterns increases.
  Authors: Allahviranloo, Mahdieh; Recker, Will
  Authors: Allahviranloo, Mahdieh; Recker, Will
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3046
• Coupling Space Syntax with Network Equilibrium Model to Simulate Complex Pedestrian Flow in Transit Stations
  Abstract: The pedestrian comfort and safety level in mass transit stations is now attracting more and more attention, especially in many Asian cities, due to the congested pedestrian flow pattern. This pattern in stations is affected by factors such as the indoor spatial setting of the station, the traffic demand between the entrance and the stairs and the escalators. As a result, multi-directional pedestrian flows interact with each other and finally formed a relatively complex distribution. To simulate this kind of pedestrian flow for planning or evaluation, the present paper addresses two key models in the problem: a hybrid routing model and a collision avoidance model. Space syntax and network flow assignment is combined as a hybrid model to automatically construct pedestrian network and then assign pedestrian to different routes. This procedure provides pedestrians route information, i.e., a sequence of intermediate destinations. Meanwhile, a behavioral model is introduced during the pedestrian movement process to avoid collisions with each other and the obstacles as well. As a case study, a station flow scenario is at last simulated and discussed.
  Authors: Ma, Jian; Liu, Shaobo; Wang, Weili; Lo, S. M.
  Authors: Ma, Jian; Liu, Shaobo; Wang, Weili; Lo, S. M.
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3322
• Computational Model for Stop-Start Wave Propagation Velocity Estimation Based on Unmanned Aerial Vehicle
  Abstract: The parameters involved in current traffic wave theoretical models such as the smooth relationship between velocity and density are difficult to obtain through traditional traffic detection devices, so it is difficult to apply these theoretical models to the actual verification and prediction for real situation. This paper investigates modeling of propagation velocity of stop-start wave at signalized intersections. Unmanned aerial vehicle (UAV) is introduced in this study as a new type of traffic information collection method to gather the real-time data of the necessary parameters which can hardly be obtained by traditional traffic detection devices. The influencing factors of the stop-start wave in actual situations such as traffic density in the queuing state and the proportion taken by large and medium-sized vehicles in the traffic are analyzed based on the traffic wave theory. Using them as the basic parameters, a computational model is developed to model the stop-start wave propagation velocity. A verification experiment is taken at the intersection of the Cao-an Highway and North Jia-song Road in Shanghai, China. Wave speeds calculated from the computational model of several cases are compared with the real wave speeds derived from actual observations using UAV. Data validation shows that this computational model fits well with the observation.
  Authors: Cheng, Ke; Chang, Yuntao; Peng, Zhong-Ren
  Authors: Cheng, Ke; Chang, Yuntao; Peng, Zhong-Ren
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3472
• Framework to Evaluate Rescheduling due to Unexpected Events in an Activity-Based Model
  Abstract: The concept of rescheduling is essential to activity-based modeling in order to calculate effects of both unexpected incidents and adaptation of individuals to traffic demand management measures. When collaboration between individuals is involved or timetable based public transportation modes are chosen, rescheduling becomes complex. This paper describes a new framework to investigate algorithms for rescheduling on a large scale. The framework explicitely models the information flow between traffic information services and travelers. It combines macroscopic traffic assignment with microscopic simulation of agents adapting their schedules. Perception filtering is introduced to allow for traveler specific interpretation of perceived macroscopic data and information going unnoticed; it feeds person specific short term predictions required for schedule adaptation. Individuals are assumed to maximize schedule utility. Initial agendas are created by the FEATHERS activity-based schedule generator for mutually independent individuals using an undisturbed loaded transportation network. The new framework allows both agent behavior and external phenomena to influence the transportation network state; individuals interpret the state changes via perception filtering and start adapting their schedules, again affecting the network via updated traffic demand. The first rescheduler investigated uses marginal utility that monotonically decreases with activity duration and a monotonically converging relaxation algorithm to efficiently determine the new activity timing. The current framework implementation can support re-timing, re-location and activity re-sequencing; re-routing however is the subject of future research.
  Authors: Knapen, Luk; Usman, Muhammad; Yasar, Ansar-Ul-Haque; Bellemans, Tom; Janssens, Davy; Wets, Geert
  Authors: Knapen, Luk; Usman, Muhammad; Yasar, Ansar-Ul-Haque; Bellemans, Tom; Janssens, Davy; Wets, Geert
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3682
• Dynamic Forecast of Incident Clearance Time Using Adaptive Artificial Neural Networks
  Abstract: This paper presents an adaptive model to forecast the clearance time of real-time traffic incidents. This information is vitally important for the incident management process, to adequate the operational response to the incident zone, and to predict network conditions induced by the incident. It is essential to design proactive measures in terms of traffic control and traveller information to mitigate impending congestion and safety impacts. This is a challenging problem in real-time environments because the incident characteristics reported by incident responders or others, which are needed to model and forecast in a timely way, are limited, often inaccurate and vague. Therefore, an adaptive model was developed to capture the incident characterization dynamics to improve the predictive performance. This solution includes four adaptive Artificial Neural Network-based models, which are activated with incoming data, from the incident notification until the point of the incident road clearance. The first model (M1) uses basic incident characteristics usually available with the incident notification, such as the type, location, time, road geometry and blockages. Then M2 uses response times and arrival demand and outputs from M1. Next, M3 uses the number and type of vehicles involved as well as the outputs from M2. At last, M4 uses incident severity together with M3 outputs.This model was calibrated and tested using incident records from Portuguese highways, and the performance shows that M4 was able to estimate 72% of incidents with less than 10 minutes error and about 92% with less than 20 minutes error. This model tends to overestimate in about 75% the prediction values for major accidents, minor incidents and road works and about 85% of incidents with duration up to 80 minutes are under estimated, which are opportunities for further improvements.
  Authors: Lopes, Jorge
  Authors: Lopes, Jorge
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3885
• Real-Time Traffic Network State Estimation and Prediction with Decision Support Capabilities: Application to Integrated Corridor Management
  Abstract: This paper presents a real-time traffic network state estimation and prediction system with built-in decision support capabilities for traffic network management. The system seeks to provide traffic network managers with the capabilities to estimate the current network conditions, predict congestion dynamics, and generate efficient traffic management schemes for recurrent and non-recurrent congestion situations. The system adopts a closed-loop rolling horizon framework in which network state estimation and prediction modules are integrated. The system is applied in the context of Integrated Corridor Management (ICM), which is envisioned to provide a system-based approach for managing congested urban corridors. A genetic algorithm methodology is developed to generate efficient traffic management schemes that integrate preapproved control actions by all managing agencies. The system is applied to a section of a commuter corridor in Dallas, Texas. The results show the ability of the system to improve the overall network performance during hypothetical incident scenarios.
  Authors: Hashemi, Hossein; Abdelghany, Khaled F.; Hassan, Ahmed; Lezar, Maverick
  Authors: Hashemi, Hossein; Abdelghany, Khaled F.; Hassan, Ahmed; Lezar, Maverick
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4029
• Large-Scale Agent-Based Transport Simulation in Shanghai, China
  Abstract: The activity-based model system is being coined as the next-generation demand forecasting model. The agent-based transport simulation toolkit MATSim is a fully integrated system that models decisions from the long-term to the short-term, and these decisions in Matsim are activity-based models. By applying MATSim to the large scenario of Shanghai, a large scale multi agent-based transport simulation in Shanghai is presented in this paper. The algorithms of integrating new data in Shanghai with Matsim inputs such as synthetic population, facilities and network are separately designed according to data characteristics. Then, the activity-based modelling is introduced to generate population plans, and activity preplanning are employed to learn the better travel plans, while scoring for a plan is modelled by using utility-based approach. Finally, a full MATSim-based simulation platform for Shanghai scenario is built in detail. The scenario contains 200 thousand synthetic persons and they are simulated on a network with 50 thousand links. The relaxed state of simulation system is reached after 100 iterations of the replanning procedures, and the mode choice, route choice and activity time allocation modules are used to optimized the activity plans of agents. The feasibility of transport simulation in Shanghai by MATSim is validated against the mode split and the observed counts. Extensive simulation results on the designed Shanghai simulation scenarios indicates that most of the observed counts are matched quite well with the traffic simulation volumes, and the potential of MATSim for large-scale dynamic transport simulation has been demonstrated.
  Authors: Zhang, Lun; Yang, Wenchen; Wang, Jiamei; Rao, Qian
  Authors: Zhang, Lun; Yang, Wenchen; Wang, Jiamei; Rao, Qian
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4405
• Forecasting of Short-Term Urban Rail Transit Passenger Flow with Support Vector Machine Hybrid Online Model
  Abstract: Prediction for short-term urban passenger rail flow is essential for effective urban rail transit operation and management. It is important for a forecasting model to capture the periodicity and nonlinearity of short-term passenger flow and to embed these characteristics into the model to enhance forecasting performance. In this research, a support vector machine global online model (SVMGOL) is first proposed by embedding the periodic characteristics via SARIMA model to capture the inherent periodicity of passenger flow. A support vector machine local online model (SVMLOL) is then proposed by embedding the nonlinear characteristics via successive passenger flow value inputs to capture the local nonlinear characteristics of the passenger flow. To take advantage of the two online models, this research then constructs a support vector machine hybrid online model (SVMHOL) based on the idea of data fusion. The model building process and its application in the prediction of short-term passenger flow at Zhujianglu Station of Nanjing Metro is discussed. Testing results show that for the one-step forecasting, the SVMHOL model outperforms the individual SARIMA or SVM model in terms of mean absolute error, mean absolute percent error and root mean square error.
  Authors: Zhang, Ning; Zhang, Yunlong; Wang, Xuemei
  Authors: Zhang, Ning; Zhang, Yunlong; Wang, Xuemei
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4393
• Framework for Automatic Identification and Extraction of Travel Lane Information from Georectified Aerial Images Using Support Vector Machine
  Abstract: Travel lane data such as number of lanes and lane width are basic input to many transportation studies. Traditionally, these data are either collected in the field or are manually extracted from aerial images. These methods of data acquisition are both resource intensive and slow, especially when large study areas are involved. The availability of high-resolution geo-rectified aerial images provides an inexpensive alternative to acquiring these data via automatic extraction methods. This paper presents a framework for automatically identifying and extracting travel lane data from geo-rectified aerial images using a classification technique known as Support Vector Machine (SVM). Five-folder cross-validation was applied to a test location in Miami-Dade County in Florida, where 490 instances were extracted from real-world data. The binary classification test shows that SVM with the polynomial kernel and the Radial Basis Function (RBF) kernel both gave ideal accuracy. In a sample test with a lane profile model consisting of 13 features, both the polynomial kernel with exponent higher than three and the RBF kernel with ? larger than 1 provided a precision rate of higher than 90%. The accuracy statistics indicate that it is feasible to identify complete travel lane profiles from geo-rectified aerial images with the proposed framework.
  Authors: Tang, Li; Gan, Albert; Alluri, Priyanka
  Authors: Tang, Li; Gan, Albert; Alluri, Priyanka
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4786
• Real-Time Sight Distance and Road Surface Calculations via the Wavefront Topology Algorithm
  Abstract: The Wavefront Topology System (WTS) is a novel 3D tessellation algorithm. The WTS algorithm is extended to applications in navigation and highway design models. The WTS road surface navigation algorithm determines sight distance, center lines, and road geometry; information on surface slope is inferred from the process. The algorithm processes road surface data from video images. Road geometry is calculated through an iterative procedure which involves comparing WTS coordinate nodes to the lane boundaries. The lane delimiters are segmented with the assistance of an edge detection filter. The geometric structure of the road surface is extracted with a region filling process. Once the surface domain is filled with WTS coordinate nodes, then additional road properties are calculated. The maximum distance and angle of the sight line vector is computed for each road surface corresponding to an image frame. A virtual field of view (FOV) facilitates determination of road profiles and local slopes. The intersection of the WTS nodes with the field of view x-y plane provides an interpretation of slope maxima and minima. The center line elements are determined from the WTS boundary nodes. Each WTS node is a data structure that contains Cartesian coordinates and links to its adjacent points.
  Authors: Thomas, Clayton; Jha, Manoj K.
  Authors: Thomas, Clayton; Jha, Manoj K.
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-5278
• Car-Following Trajectory Modeling with Machine Learning: Showcase for Merits of Artificial Intelligence
  Abstract: This paper attempts to showcase the benefits and merits of using artificial intelligence techniques in transportation applications. The example we use in this paper is modeling of a car-following trajectory data and comparing the machine learning approach to regression analysis. For the machine learning approach, we use Neuro-Fuzzy Actor-Critic Reinforcement Learning (NFACRL). We train the NFACRL network using vehicle trajectory data extracted from the Naturalistic Car Driving Study (NCDS) databases provided by the Virginia Tech Transportation Institute (VTTI). Our results show that both the machine learning and regression analysis could predict the upcoming acceleration value with a very high R2 value (more than 0.98). However, only the machine learning approach could reproduce the vehicle trajectory, while the regression analysis would ultimately lead to an erroneous model.
  Authors: Abbas, Montasir M.; Chong, Linsen
  Authors: Abbas, Montasir M.; Chong, Linsen
  Year: 2013
  Document Type: Paper
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4712
• Activity Pattern Recognition by Using Support Vector Machines with Multiple Classes
  Authors: Allahviranloo, Mahdieh
  Authors: Allahviranloo, Mahdieh
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3046
• Coupling Space Syntax with Network Equilibrium Model to Simulate Complex Pedestrian Flow in Transit Stations
  Authors: Ma, Jian
  Authors: Ma, Jian
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3322
• Computational Model for Stop-Start Wave Propagation Velocity Estimation Based on Unmanned Aerial Vehicle
  Authors: Cheng, Ke
  Authors: Cheng, Ke
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3472
• Framework for Automatic Identification and Extraction of Travel Lane Information from Georectified Aerial Images Using Support Vector Machine
  Authors: Alluri, Priyanka
  Authors: Alluri, Priyanka
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4786
• Large-Scale Agent-Based Transport Simulation in Shanghai, China
  Authors: Yang, Wenchen
  Keywords: poster presentation; poster design; poster template
  Authors: Yang, Wenchen
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4405
• Stochastic Network Design Problem with Fuzzy Goals
  Authors: Chen, Anthony
  Authors: Chen, Anthony
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-2770
• Real-Time Traffic Network State Estimation and Prediction with Decision Support Capabilities: Application to Integrated Corridor Management
  Authors: Hashemi, Hossein
  Authors: Hashemi, Hossein
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4029
• Modeling Yard Crane Operators as Reinforcement Learning Agents
  Authors: Fotuhi, Fateme
  Authors: Fotuhi, Fateme
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-2671
• Framework to Evaluate Rescheduling due to Unexpected Events in an Activity-Based Model
  Authors: Knapen, Luk
  Authors: Knapen, Luk
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3682
• Framework to Evaluate Rescheduling due to Unexpected Events in an Activity-Based Model
  Authors: Bellemans, Tom
  Authors: Bellemans, Tom
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-3682
• Framework for Automatic Identification and Extraction of Travel Lane Information from Georectified Aerial Images Using Support Vector Machine
  Authors: Tang, Li
  Authors: Tang, Li
  Year: 2013
  Document Type: Presentation; Poster
  Subject: Administration and Management; Data and Information Technology
  Session: 609
  Paper Number: 13-4786