Adaptive traffic parameter prediction: Effect of number of states and transferability of models

Traffic parameters can show shifts due to factors such as weather, accidents, and driving characteristics. This study develops a model for predicting traffic speeds under these abrupt changes within regime switching framework. The proposed approach utilizes Hidden Markov, Expectation Maximization, Recursive Least Squares Filtering, and ARIMA methods for an adaptive forecasting method. The method is compared with naive and mean updating linear and nonlinear time series models. The model is fitted and tested extensively using 1993 I-880 loop data from California and January 2014 INRIX data from Virginia. Analysis for number of states, impact of number of states on forecasting, prediction scope, and transferability of the model to different locations are investigated. A 5-state model is found to be providing best results. Developed model is tested for 1-step to 45-step forecasts. The accuracy of predictions are improved until 15-step over nonadaptive and mean adaptive models. Except 1-step predictions, the model is found to be transferable to different locations. Even if the developed model is not retrained on different datasets, it is able to provide better or close results with nonadaptive and adaptive models that are retrained on the corresponding dataset.     

Real time detection of driver attention: Emerging solutions based on robust iconic classifiers and dictionary of poses

Real time monitoring of driver attention by computer vision techniques is a key issue in the development of advanced driver assistance systems. While past work mostly focused on structured feature-based approaches, characterized by high computational requirements, emerging technologies based on iconic classifiers recently proved to be good candidates for the implementation of accurate and real-time solutions, characterized by simplicity and automatic fast training stages.In this work the combined use of binary classifiers and iconic data reduction, based on Sanger neural networks, is proposed, detailing critical aspects related to the application of this approach to the specific problem of driving assistance. In particular it is investigated the possibility of a simplified learning stage, based on a small dictionary of poses, that makes the system almost independent from the actual user.On-board experiments demonstrate the effectiveness of the approach, even in case of noise and adverse light conditions. Moreover the system proved unexpected robustness to various categories of users, including people with beard and eyeglasses. Temporal integration of classification results, together with a partial distinction among visual distraction and fatigue effects, make the proposed technology an excellent candidate for the exploration of adaptive and user-centered applications in the automotive field.     

Deciding whether and how to improve statewide travel demand models based on transportation planning application needs

Many states in the USA have developed statewide travel demand models for transportation planning at the state level and along intercity corridors. Travel demand models at mega-region and provincial levels are also widely used in Europe and Asia. With modern transportation planning applications requiring enhanced model capabilities, many states are considering improving their four-step statewide demand models. This paper synthesizes representative statewide models developed with traditional four-step, advanced four-step, and integrated micro-simulation methods. The focus of this synthesis study is as much on model applications and data requirements as on modeling methods. An incremental model improvement approach toward advanced statewide models is recommended. Review findings also suggest model improvement activities should be justified by planning application needs. For statewide model improvement plans to be successful and financially sustainable, the return on model improvement investment needs to be demonstrated by timely applications that rely on improved model capabilities.     

Estimating heterogeneity of car travelers on mode shifting behavior based on discrete choice models

In order to understand the mode shift behavior of car travelers and relieve traffic congestion, a Stated Preference survey has been conducted in the city of Ji'nan in China to analyze bus choice behavior and the heterogeneity of car travelers. Several discrete choice models, including multinomial logit, mixed logit and latent class model (LCM) are developed based on these survey data. A comparative analysis indicates that the LCM has the highest precision and is more suitable to analyze the heterogeneity of car travelers. The LCM divides car travelers into three classes. Different classes have different sets of influencing factors in the model. Policy recommendations are also proposed for those classes to promote bus shift from car travelers based on the model results. Finally, sensitivity analysis on parking fees and fuel cost is carried out on the LCMs under different bus service levels. Car travelers have different sensitivities to the influencing factors. The conclusions indicate that the LCM can reflect the heterogeneity and preferences of car travelers and can be used to understand how to shift the behavior of car travelers and make more effective traffic policy.     

A validation measure for computational scheduler activity-based transportation models based on sequence alignment methods

In recent decades, activity-based transportation models have gained growing attention, due to their strong foundation in behavioral theory and ability to model the response of individuals to travel demand management policies. Hence, researchers have become increasingly interested in analyzing and predicting individuals’ decisions about activity participation. This paper investigates the reliability and uncertainty of computational process activity-based models. The design of the scheduling process model is experimented with by introducing an alternative decision sequence. The results provide additional information to better understand the process model’s reliability and behavior. Furthermore, the findings show that the current sequence of decision steps in the process model in ALBATROSS achieves satisfactory work activity schedules. Finally, the study concludes that using a decision tree model achieves a better performance than using diverse data mining approaches.