In this study, we develop a mathematical framework to predict cycle-based queued vehicles at each individual lane using a deep learning method – the long short-term memory (LSTM) network. The key challenges are to de...
详细信息
In this study, we develop a mathematical framework to predict cycle-based queued vehicles at each individual lane using a deep learning method – the long short-term memory (LSTM) network. The key challenges are to decide the existence of residual queued vehicles at the end of each cycle, and to predict the lane-based downstream arrivals to calculate vertical queue lengths at individual lanes using an integrated deep learning method. The primary contribution of the proposed method is to enhance the predictive accuracy of lane-based queue lengths in the future cycles using the historical queuing patterns. A major advantage of implementing an integrated deep learning process compared to the previously Kalman-filter-based queue estimation approach (Lee et al., 2015) is that there is no need to calibrate the co-variance matrix and tune the gain values (parameters) of the estimator. In the simulation results, the proposed method perform better in only straight movements and a shared lane with left turning movements.
modeling and simulation of hurricane evacuation is an important task in emergency planning and management. One typically ignored factor that affects the development of a reliable evacuation model is the uncertainty ca...
详细信息
ISBN:
(纸本)9781538670255
modeling and simulation of hurricane evacuation is an important task in emergency planning and management. One typically ignored factor that affects the development of a reliable evacuation model is the uncertainty caused by the incident-induced capacity loss. Lately, the impact of incidents on evacuation has drawn increasingly attention among researchers and practitioners, but few of them thoroughly investigated it using the real data in the modeling and simulation context. This study aims to investigate the impact of various types of incidents on modeling and simulation of hurricane evacuation. Particularly, the incidents that occurred under actual hurricane conditions are examined and their impact on the capacity loss is modeled. The developed incident frequency and duration models are incorporated into the network assignment model to study traffic conditions under hurricane Sandy in New York. Results show that the consideration of incident-induced capacity loss can greatly change the outcome of the evacuation model. Our findings suggest the need to include a well calibrated and validated traffic incident generation module for modeling and simulating hurricane evacuation.
This paper presents an investigation into the convergence of the fine-grained parallel algorithm for computing an incomplete LU factorization for non-symmetric and indefinite matrices. The fine-grained parallel incomp...
详细信息
ISBN:
(纸本)9781510860162
This paper presents an investigation into the convergence of the fine-grained parallel algorithm for computing an incomplete LU factorization for non-symmetric and indefinite matrices. The fine-grained parallel incomplete LU factorization is a nonlinear fixed point iteration and convergence has not been extensively studied for problems that are not symmetric positive definite. This work investigates the convergence of the algorithm for these more difficult problems and additionally investigates how the occurrence of a computing fault may impact the convergence of the algorithm for the problems being studied. The results obtained suggest that this class of problems presents challenges for the fine-grained parallel incomplete LU factorization (less than 30% of configurations converge naturally), and that while the occurrence of a fault can cause significant negative effects, the simple algorithmic change advocated here can completely ameliorate the effects of a fault.
Stress can impose negative impact on the health and well-being of a person. People who do not have tools to manage their stress are more likely to acquire cardiovascular disease (CVD) -The leading cause of death in th...
详细信息
Understanding pedestrian behavior under emergency conditions is critical for emergency preparedness. However, the high cost associated with field experiments limited the opportunities for exploring large-scale pedestr...
详细信息
In discrete event simulation development, a large conceptual leap often is made when going from the system model to the simulation implementation. The event model, describing how events are scheduled and executed, is ...
详细信息
This paper summarizes work underway on neurosurgery simulation and navigation, emphasizing anatomical modeling techniques and clinical requirements for simulation. We describe innovations that center on patient-specif...
详细信息
We have developed a realistic nucleon-nucleon (NN) interaction, dubbed Daejeon16. We start from a SRG (similarity renormalization group) evolved chiral N3LO interaction. We then apply PETs (phase-equivalent transforma...
详细信息
Reducing the risk of secondary crashes is a key goal for effective traffic incident management. However, only few countermeasures have been established in practices to achieve the goal. This is mainly due to the stoch...
详细信息
This paper presents a new educational roadmap for teaching discrete event system (DES) simulation software design. This roadmap represents the hierarchical structure and inter-relationships characterizing the worldvie...
详细信息
暂无评论