Package delivery via ridesharing provides appealing benefits of lower delivery cost and efficient vehicle usage.Most existing ridesharing systems operate the matching of ridesharing in a centralized manner,which may r...Package delivery via ridesharing provides appealing benefits of lower delivery cost and efficient vehicle usage.Most existing ridesharing systems operate the matching of ridesharing in a centralized manner,which may result in the single point of failure once the controller breaks down or is under attack.To tackle such problems,our goal in this paper is to develop a blockchain-based package delivery ridesharing system,where decentralization is adopted to remove intermediaries and direct transactions between the providers and the requestors are allowed.To complete the matching process under decentralized structure,an Event-Triggered Distributed Deep Reinforcement Learning(ETDDRL)algorithm is proposed to generate/update the real-time ridesharing orders for the new coming ridesharing requests from a local view.Simulation results reveal the vast potential of the ETDDRL matching algorithm under the blockchain framework for the promotion of the ridesharing profits.Finally,we develop an application for Android-based terminals to verify the ETDDRL matching algorithm.展开更多
The time cost of ridesharing rental represents a crucial factor influencing users'decisions to rent a car.Researchers have explored this aspect through text analysis and questionnaires.However,the current research...The time cost of ridesharing rental represents a crucial factor influencing users'decisions to rent a car.Researchers have explored this aspect through text analysis and questionnaires.However,the current research faces limitations in terms of data quantity and analysis methods,preventing the extraction of key information.Therefore,there is a need to further optimize the level of public opinion analysis.This study aimed to investigate user perspectives concerning travel time in ridesharing,both pre and post-pandemic,within the Twitter application.Our analysis focused on a dataset from users residing in the USA and India,with considerations for demographic variables such as age and gender.To accomplish our research objectives,we employed Latent Dirichlet Allocation for topic modeling and BERT for sentiment analysis.Our findings revealed significant influences of the pandemic and the user's country of origin on sentiment.Notably,there was a discernible increase in positive sentiment among users from both countries following the pandemic,particularly among older individuals.These findings bear relevance to the ridesharing industry,offering insights that can aid in establishing benchmarks for improving travel time.Such improvements are instrumental in enabling ridesharing companies to effectively compete with other public transportation alternatives.展开更多
Rideshare apps make getting around town easy and quick.With just a few taps on your phone,you can get a ride to your destination.How does the app work?It will show you a route and the cost.Then the app will find a dri...Rideshare apps make getting around town easy and quick.With just a few taps on your phone,you can get a ride to your destination.How does the app work?It will show you a route and the cost.Then the app will find a driver for you.展开更多
The city-wide ridesharing package delivery is becoming popular as it provides a convenience such as extra profits to the vehicle’s driver and high traffic efficiency to the city.The vehicle dispatching is a significa...The city-wide ridesharing package delivery is becoming popular as it provides a convenience such as extra profits to the vehicle’s driver and high traffic efficiency to the city.The vehicle dispatching is a significant issue to improve the ridesharing efficiency in package delivery.The classic one-hop ridesharing package delivery requires the highly similar paths between the package and the vehicle given by the limited detour time,which depresses the ridesharing efficiency.To tackle this problem,a city-wide vehicle dispatching strategy for the multi-hop ridesharing package delivery was proposed,where a package is permitted to be delivered sequentially by different vehicles,until arriving the destination.The study formulates the vehicle dispatching as a maximum multi-dimensional bipartite matching problem with the goal of maximizing the total saving distance given by the limited detour time and ridesharing capacity.A multi-hop ridesharing vehicle dispatching algorithm was proposed to solve this problem by selecting the farthest reachable locker and multi-dimensional matching.Simulation results based on real vehicle dataset of Beijing demonstrate the effectiveness and efficiency of the proposed vehicle dispatching strategy.展开更多
We deal with the problem of sharing vehicles by individuals with similar itineraries which is to find the minimum number of drivers, each of which has a vehicle capacity and a detour to realize all trips. Recently, Gu...We deal with the problem of sharing vehicles by individuals with similar itineraries which is to find the minimum number of drivers, each of which has a vehicle capacity and a detour to realize all trips. Recently, Gu et al. showed that the problem is NP-hard even for star graphs restricted with unique destination, and gave a polynomial-time algorithm to solve the problem for paths restricted with unique destination and zero detour. In this paper we will give a dynamic programming algorithm to solve the problem in polynomial time for trees restricted with unique destination and zero detour. In our best knowledge it is a first polynomial-time algorithm for trees.展开更多
Past studies have identified the general public’s level of satisfaction with the service attri-butes of conventional fixed-route transit and ridesharing services,but few have limited their focus to students.This stud...Past studies have identified the general public’s level of satisfaction with the service attri-butes of conventional fixed-route transit and ridesharing services,but few have limited their focus to students.This study employs latent class cluster analysis(LCCA)to identify clusters of university students,based on their satisfaction levels of the attributes of con-ventional fixed-route and ridesharing services,and uses a latent class behavioral model of a sample of university students in Arlington,Texas to explore the heterogeneity of their preferences toward ridesharing services.The results indicate that younger-and lower-income populations are more likely to be satisfied with on-demand ridesharing services than older-and higher-income populations,females are more likely to be satisfied with ridesharing services than males,and domestic students are more likely to be satisfied with ridesharing services than international students.The outcomes of the study will provide transportation planners with new insights about the significance of sociodemographic fac-tors on the satisfaction level of those who use conventional transit and on-demand ridesharing services and will help them incorporate strategies that will make their services more attractive to their potential ridership.展开更多
基金supported by National Natural Science Foundation of China(Grant No.62271073 and 61971066)Beijing Natural Science Foundation(L212003)the National Youth Top-notch Talent Support Program.
文摘Package delivery via ridesharing provides appealing benefits of lower delivery cost and efficient vehicle usage.Most existing ridesharing systems operate the matching of ridesharing in a centralized manner,which may result in the single point of failure once the controller breaks down or is under attack.To tackle such problems,our goal in this paper is to develop a blockchain-based package delivery ridesharing system,where decentralization is adopted to remove intermediaries and direct transactions between the providers and the requestors are allowed.To complete the matching process under decentralized structure,an Event-Triggered Distributed Deep Reinforcement Learning(ETDDRL)algorithm is proposed to generate/update the real-time ridesharing orders for the new coming ridesharing requests from a local view.Simulation results reveal the vast potential of the ETDDRL matching algorithm under the blockchain framework for the promotion of the ridesharing profits.Finally,we develop an application for Android-based terminals to verify the ETDDRL matching algorithm.
基金supported by the Chinese National Natural Science Foundation(52172348)the Postdoctoral Research Foundation of China.
文摘The time cost of ridesharing rental represents a crucial factor influencing users'decisions to rent a car.Researchers have explored this aspect through text analysis and questionnaires.However,the current research faces limitations in terms of data quantity and analysis methods,preventing the extraction of key information.Therefore,there is a need to further optimize the level of public opinion analysis.This study aimed to investigate user perspectives concerning travel time in ridesharing,both pre and post-pandemic,within the Twitter application.Our analysis focused on a dataset from users residing in the USA and India,with considerations for demographic variables such as age and gender.To accomplish our research objectives,we employed Latent Dirichlet Allocation for topic modeling and BERT for sentiment analysis.Our findings revealed significant influences of the pandemic and the user's country of origin on sentiment.Notably,there was a discernible increase in positive sentiment among users from both countries following the pandemic,particularly among older individuals.These findings bear relevance to the ridesharing industry,offering insights that can aid in establishing benchmarks for improving travel time.Such improvements are instrumental in enabling ridesharing companies to effectively compete with other public transportation alternatives.
文摘Rideshare apps make getting around town easy and quick.With just a few taps on your phone,you can get a ride to your destination.How does the app work?It will show you a route and the cost.Then the app will find a driver for you.
基金the National Natural Science Foundation of China(61701037)the National Undergraduate Innovation and Entrepreneurship Taining Program。
文摘The city-wide ridesharing package delivery is becoming popular as it provides a convenience such as extra profits to the vehicle’s driver and high traffic efficiency to the city.The vehicle dispatching is a significant issue to improve the ridesharing efficiency in package delivery.The classic one-hop ridesharing package delivery requires the highly similar paths between the package and the vehicle given by the limited detour time,which depresses the ridesharing efficiency.To tackle this problem,a city-wide vehicle dispatching strategy for the multi-hop ridesharing package delivery was proposed,where a package is permitted to be delivered sequentially by different vehicles,until arriving the destination.The study formulates the vehicle dispatching as a maximum multi-dimensional bipartite matching problem with the goal of maximizing the total saving distance given by the limited detour time and ridesharing capacity.A multi-hop ridesharing vehicle dispatching algorithm was proposed to solve this problem by selecting the farthest reachable locker and multi-dimensional matching.Simulation results based on real vehicle dataset of Beijing demonstrate the effectiveness and efficiency of the proposed vehicle dispatching strategy.
文摘We deal with the problem of sharing vehicles by individuals with similar itineraries which is to find the minimum number of drivers, each of which has a vehicle capacity and a detour to realize all trips. Recently, Gu et al. showed that the problem is NP-hard even for star graphs restricted with unique destination, and gave a polynomial-time algorithm to solve the problem for paths restricted with unique destination and zero detour. In this paper we will give a dynamic programming algorithm to solve the problem in polynomial time for trees restricted with unique destination and zero detour. In our best knowledge it is a first polynomial-time algorithm for trees.
文摘Past studies have identified the general public’s level of satisfaction with the service attri-butes of conventional fixed-route transit and ridesharing services,but few have limited their focus to students.This study employs latent class cluster analysis(LCCA)to identify clusters of university students,based on their satisfaction levels of the attributes of con-ventional fixed-route and ridesharing services,and uses a latent class behavioral model of a sample of university students in Arlington,Texas to explore the heterogeneity of their preferences toward ridesharing services.The results indicate that younger-and lower-income populations are more likely to be satisfied with on-demand ridesharing services than older-and higher-income populations,females are more likely to be satisfied with ridesharing services than males,and domestic students are more likely to be satisfied with ridesharing services than international students.The outcomes of the study will provide transportation planners with new insights about the significance of sociodemographic fac-tors on the satisfaction level of those who use conventional transit and on-demand ridesharing services and will help them incorporate strategies that will make their services more attractive to their potential ridership.
