Telecommuting is a Transportation Demand Management strategy to partially or completely replace the daily commute with telecommunication technologies. Research has revealed that telecommuting can be effectively done f...Telecommuting is a Transportation Demand Management strategy to partially or completely replace the daily commute with telecommunication technologies. Research has revealed that telecommuting can be effectively done from special places provided for this purpose called telecenters. In telecenter-based telecommuting, trip lengths are shortened due to change in the location of work places. Thus suitable locations of telecenters play an important role in increasing the beneficial impacts of telecommuting in the transportation systems. In this research, a mathematical optimization model for finding optimal location and capacity of telecenters is proposed. This model is a bi-objective linear program, and a Fuzzy Goal Programming method with a preemptive structure is used to solve it. Telecommuting demand is classified into three groups of telecommuters and a priority structure that assigns the higher priority class to the closer telecenters is also incorporated into the model. The proposed model is implemented in a case study of finding optimal location of telecenters for government employees in Tehran (capital of Iran) metropolitan area. The base model is solved and its sensitivity to different parameters has been analyzed based on which, an optimal model is selected. The solution of this model is an optimal pattern for distribution of telecommuting capacities and yields the most system-wide benefits from implementation of telecommuting.展开更多
Traffic incidents are a major cause of non-recurrent congestion and delays,making accu-rate incident duration(ID)prediction essential for effective traffic management.While machine learning(ML)and deep learning(DL)mod...Traffic incidents are a major cause of non-recurrent congestion and delays,making accu-rate incident duration(ID)prediction essential for effective traffic management.While machine learning(ML)and deep learning(DL)models have been developed to predict ID and its sub-periods(verification,response,and clearance times),their reliability has not been systematically assessed.This study introduces a novel framework to evaluate the reli-ability of these predictions using 4000 traffic incident records.Non-parametric kernel den-sity estimation(KDE)effectively captured variations in the data,outperforming traditional parametric methods.Monte Carlo simulation(MCS)was then used to assess prediction reliability.Among the models tested,bagged ensemble trees provided the best balance between accuracy and complexity,showing strong reliability for predicting total ID and sub-periods.Adding 5–25%buffer adjustments further improved reliability by accounting for prediction uncertainties.This framework offers a robust tool for assessing prediction reliability,is adaptable to various ML and DL models,and represents a significant step for-ward in traffic incident management.展开更多
文摘Telecommuting is a Transportation Demand Management strategy to partially or completely replace the daily commute with telecommunication technologies. Research has revealed that telecommuting can be effectively done from special places provided for this purpose called telecenters. In telecenter-based telecommuting, trip lengths are shortened due to change in the location of work places. Thus suitable locations of telecenters play an important role in increasing the beneficial impacts of telecommuting in the transportation systems. In this research, a mathematical optimization model for finding optimal location and capacity of telecenters is proposed. This model is a bi-objective linear program, and a Fuzzy Goal Programming method with a preemptive structure is used to solve it. Telecommuting demand is classified into three groups of telecommuters and a priority structure that assigns the higher priority class to the closer telecenters is also incorporated into the model. The proposed model is implemented in a case study of finding optimal location of telecenters for government employees in Tehran (capital of Iran) metropolitan area. The base model is solved and its sensitivity to different parameters has been analyzed based on which, an optimal model is selected. The solution of this model is an optimal pattern for distribution of telecommuting capacities and yields the most system-wide benefits from implementation of telecommuting.
文摘Traffic incidents are a major cause of non-recurrent congestion and delays,making accu-rate incident duration(ID)prediction essential for effective traffic management.While machine learning(ML)and deep learning(DL)models have been developed to predict ID and its sub-periods(verification,response,and clearance times),their reliability has not been systematically assessed.This study introduces a novel framework to evaluate the reli-ability of these predictions using 4000 traffic incident records.Non-parametric kernel den-sity estimation(KDE)effectively captured variations in the data,outperforming traditional parametric methods.Monte Carlo simulation(MCS)was then used to assess prediction reliability.Among the models tested,bagged ensemble trees provided the best balance between accuracy and complexity,showing strong reliability for predicting total ID and sub-periods.Adding 5–25%buffer adjustments further improved reliability by accounting for prediction uncertainties.This framework offers a robust tool for assessing prediction reliability,is adaptable to various ML and DL models,and represents a significant step for-ward in traffic incident management.
