Co-Evolutionary Location-Routing Model of Medical Isolation Areas for Major Public Health Emergencies Considering the Uncertainty of Future Traffic Environment

With the continuous development of the COVID-19 pandemic, the selection of locations for medical isolation areas has not always been optimal for the timely transportation of infected people, or those suspected of being infected. This has resulted in failure to control the rate of spread of infection cases in time. To address this problem, this paper proposes a co-evolutionary location-routing optimization (CELRO) model of medical isolation areas for use in major public health emergencies to develop a rapid location-routing scheme for epidemic isolation, including the selection of locations of medical isolation facilities per area and the optimal route per vehicle to each infected person. Specifically, this paper solves the following two sub-problems: (i) calculate the shortest transportation times and corresponding routes from any medical isolation area to any person infected or suspected of being infected, and (ii) calculate the location scheme for distribution of isolation areas. Different from previous studies, the vehicle operating characteristics and the interference of uncertainty of the traffic environment are considered in the proposed model. To find an appropriate scheme for location of medical isolation areas with the shortest travel times, a co-evolutionary clustering algorithm (CECA), which is a combination of some separated evolutionary programming operations, is proposed to solve the model. Various network sizes and uncertainty combinations are used to design some comparative tests, which aim to verify the effectiveness of the proposed model. In the experiment section, CELRO reduced travel time by at least 14% compared with other methods. This finding can provide an effective theoretical basis for optimizing the spatial layout of medical isolation areas or the location planning of new medical facilities. © National Academy of Sciences.

Strangers On This Road We Are On: A Literature Review of Pooling in On-Demand Mobility Services

Ridepooling service options introduced by transportation network companies (TNCs) and microtransit companies provide opportunities to increase shared-ride trips in vehicles, thereby improving congestion and environmental factors. This paper reviews the existing literature available on ridepooling and related services, specifically focusing on pooling options available from on-demand transportation companies. The paper summarizes the existing knowledge on the use of pooled-ride services, factors in travel mode service options for customers, available policy and planning strategies to incentivize sharing vehicles, and effects of the COVID-19 pandemic on shared-ride travel. Overall, research shows that ridepooling options are more likely to be considered by public transit users who have lower household incomes, while ridesourcing users of upperclass backgrounds are less likely to consider moving to a shared-ride service. Travel time and trip cost are the most important factors for travelers determining whether to use a ridesplitting or microtransit service rather than a ride-alone ridesourced trip. Existing policy and planning tools targeting pooled travel or TNCs can be expanded on and specified for on-demand ridepooling services, such as offering better incentives to use shared vehicles and increased access to curb areas or travel lanes, but the most effective strategies will include increasing the user costs for parking or riding alone. © National Academy of Sciences.

Reliability-Oriented Route Generation Algorithm for Multimodal Transport: A Perspective from Supply Chain Reliability Enhancement

Sudden infectious diseases and other malignant events cause excessive costs in the supply chain, particularly in the transportation sector. This issue, along with the uncertainty of the development of global epidemics and the frequency of extreme natural disaster events, continues to provoke discussion and reflection. However, transport systems involve interactions between different modes, which are further complicated by the reliable coupling of multiple modes. Therefore, for the vital subsystem of the supply chain-multimodal transport, in this paper, a heuristic algorithm considering node topology and transport characteristics in a multimodal transport network (MTN): the Reliability Oriented Routing Algorithm (RORA), is proposed based on the super-network and improved k-shell (IKS) algorithm. An empirical case based on the Yangtze River Delta region of China demonstrates that RORA enables a 16% reduction in the boundary value for route failure and a reduction of about 60.58% in the route cost increase compared to the typical cost-optimal algorithm, which means that RORA results in a more reliable routing solution. The analysis of network reliability also shows that the IKS values of the nodes are positively correlated with the reliability of the MTN, and nodes with different modes may have different transport reliabilities (highest for highways and lowest for inland waterways). These findings inform a reliability-based scheme and network design for multimodal transportation. Practical Applications: Recently, the COVID-19 epidemic and the frequency of natural disasters such as floods have prompted scholars to consider transport reliability. Therefore, efficient and reliable cargo transportation solutions are crucial for the sustainable development of multimodal transport in a country or region. In this paper, a new algorithm is designed to obtain a reliability-oriented optimal routing scheme for multimodal transport. Using actual data from the Yangtze River Delta region of China as an example for experimental analysis, we obtain that: (1) the proposed algorithm is superior in terms of efficiency, accuracy, and route reliability, which means that the new algorithm can quickly find more reliable routing solutions in the event of urban transport infrastructure failures;and (2) highway hubs have the greatest transport reliability. Conversely, inland waterway hubs are the least reliable. The influence of national highways and railways on the multimodal transport system is unbalanced. These findings provide decision support to transport policymakers on reliability. For example, transport investments should be focused on building large infrastructure and increasing transport capacity, strengthening the connectivity of inland waterway hubs to hubs with higher transport advantages, and leveraging the role of large hubs. © 2023 American Society of Civil Engineers.

Bus Network Design and Frequency Setting in the Post-COVID-19 Pandemic: The Case of London

A transit network design frequency setting model is proposed to cope with the postpandemic passenger demand. The multiobjective transit network design and frequency setting problem (TNDFSP) seeks to find optimal routes and their associated frequencies to operate public transport services in an urban area. The objective is to redesign the public transport network to minimize passenger costs without incurring massive changes to its former composition. The proposed TNDFSP model includes a route generation algorithm (RGA) that generates newlines in addition to the existing lines to serve the most demanding trips, and passenger assignment (PA) and frequency setting (FS) mixed-integer programming models that distribute the demand through the modified bus network and set the optimal number of buses for each line. Computational experiments were conducted on a test network and the network comprising the Royal Borough of Kensington and Chelsea in London. © 2023 American Society of Civil Engineers.

Combined Effect of Changes in Transit Service and Changes in Occupancy on Per-Passenger Energy Consumption

Many transit providers changed their schedules and route configurations during the COVID-19 pandemic, providing more frequent bus service on major routes and curtailing other routes, to reduce the risk of COVID-19 exposure. This research first assessed the changes in Metropolitan Atlanta Rapid Transit Authority (MARTA) service configurations by reviewing the prepandemic versus during-pandemic General Transit Feed Specification (GTFS) files. Energy use per route for a typical week was calculated for pre-pandemic, during-closure, and post-closure periods by integrating GTFS data with MOVES-Matrix transit energy and emission rates (MOVES signifying MOtor Vehicle Emission Simulator). MARTA automated passenger counter data were appended to the routes, and energy use per passenger-mile was compared across routes for the three periods. The results showed that the coupled effect of transit frequency shift and ridership decrease from 2019 to 2020 increased route-level energy use for over 87% of the routes and per-passenger-mile energy use for over 98% of the routes. In 2021, although MARTA service had largely returned to pre-pandemic conditions, ridership remained in an early stage of recovery. Total energy use decreased to about pre-pandemic levels, but per-passenger energy use remained higher for more than 91% of routes. The results confirm that while total energy use is more closely associated with trip schedules and routes, perpassenger energy use depends on both trip service and ridership. The results also indicate a need for data-based transit planning, to help avoid inefficiency associated with over-provision of service or inadequate social distancing protection caused by under-provision of service. © National Academy of Sciences: Transportation Research Board 2022.

Research on the Distribution and Transportation of Emergency Materials Under Public Health Emergencies

In order to reduce the shortages caused by public health events, emergency supplies must be reasonably allocated and transportation routes must be scientifically planed to maximize the rescue effect of emergency supplies. A two-stage model of emergency material distribution-transportation was modeled, and a genetic algorithm was designed to solve combining with the relevant data of COVID-19 in Xi'an. The results show that there is a negative correlation between the shortage effect and the fair distribution of objective function in the distribution model, as well as between the transportation cost and the delay cost of objective function in the transportation model. © 2022 SPIE.

Optimization of Transport Services Based on the K Shortest Path Algorithm

The link between the supply and demand sides of manufacturing has become increasingly frail as a result of the COVID-19 outbreak. In this paper, we analyze the key path nodes and propose a closed-loop path value-added strategy for logistics services to optimize the path cost on the supply and demand side under the influence of the COVID-19 epidemic. First, the k shortest path algorithm determines the optional paths in accordance with the structure of the road network made up of all path nodes. Second, closed-loop transportation routes for both forward and reverse transit are constructed using the optional paths. Finally, the transportation service strategy with the optimal choice of transportation cost and transportation time under a multi-stage epidemic is obtained. The method can provide a reference for logistics services. © 2022 IEEE.

Research on Matching Mechanism and Route Planning of Intercity Carpool

Under the influence of COVID-19, intercity ride-sharing has become more and more popular due to its relatively little contact and low price and has gradually become one of the important ways of intercity transportation. The ride-sharing platform provides functions of information interaction among passengers and drivers, allocating the transportation tasks and recommending the optimal route planning. Existing ride-sharing platforms fail to take user's personalized needs into account when assigning tasks, and users have low satisfaction with the planned routes. This paper designs an allocation algorithm (Allocation Algorithm 4 Inter-city Carpool) for intercity carpool and proposes a pricing function related to the detour distance and user's satisfaction, so as to ensure the optimal benefits for ride-sharing platforms and drivers, as well as the optimal passenger satisfaction. The AA4IC algorithm is proved to be incentive compatible and budget balanced theoretically, and the effectiveness of allocation scheme generation and path planning is verified by experiments. When the algorithm is iterated 1000 times, the time is less than 200 s, and the task assignment under the optimal user satisfaction can be achieved. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

International Conference on Transportation and Development 2022

In 2017, the town of Innisfil, Ontario, launched Innisfil Transit in partnership with Uber, a transportation network company, to provide a subsidized on-demand public mobility service as an alternative to investing in a new fixed-route bus service. The performance of Innisfil Transit is documented in a 2021 Ryerson University report by Sweet, Mitra, and Benaroya, which shows greater cost effectiveness of the mobility provided over the proposed bus alternative. This paper expands on those findings by assessing Innisfil Transit with respect to sustainability, scalability, and resiliency. First, we quantify the energy and emissions of this program relative to traditional transit and driving alone across varying powertrains. We then characterize a conservative first-order estimate of the percentage of US communities that fall within a similar spatial-demographic tier as Innisfil. Replicability also hinges on service cost and performance in comparison to average values for low-density transit in the US. Lastly, most transit agencies experienced a significant drop in demand (as much as 90%) with slowly rebounding ridership since the onset of the COVID-19 pandemic. The resiliency of the Innisfil program to the pressures induced by the pandemic is examined in comparison to other transit operations. The lessons learned across these three dimensions complement prior work to better understand the efficiency and sustainability of on-demand public mobility service for low-density communities like Innisfil. © ASCE. All rights reserved.

Neural Architecture and Feature Search for Predicting the Ridership of Public Transportation Routes

Accurately predicting the ridership of public-transit routes provides substantial benefits to both transit agencies, who can dispatch additional vehicles proactively before the vehicles that serve a route become crowded, and to passengers, who can avoid crowded vehicles based on publicly available predictions. The spread of the coronavirus disease has further elevated the importance of ridership prediction as crowded vehicles now present not only an inconvenience but also a public-health risk. At the same time, accurately predicting ridership has become more challenging due to evolving ridership patterns, which may make all data except for the most recent records stale. One promising approach for improving prediction accuracy is to fine-tune the hyper-parameters of machine-learning models for each transit route based on the characteristics of the particular route, such as the number of records. However, manually designing a machine-learning model for each route is a labor-intensive process, which may require experts to spend a significant amount of their valuable time. To help experts with designing machine-learning models, we propose a neural-architecture and feature search approach, which optimizes the architecture and features of a deep neural network for predicting the ridership of a public-transit route. Our approach is based on a randomized local hyper-parameter search, which minimizes both prediction error as well as the complexity of the model. We evaluate our approach on real-world ridership data provided by the public transit agency of Chattanooga, TN, and we demonstrate that training neural networks whose architectures and features are optimized for each route provides significantly better performance than training neural networks whose architectures and features are generic. © 2022 IEEE.

Developing Cities for Citizens: Supporting Gender Equity for Successful and Sustainable Urban Mobility

Cities today face unprecedented challenges generated, among others, by climate change, demographic change, economic crisis and technological innovation. The Agenda 2030 sustainable goals aim to create more equitable and sustainable cities which account for all citizens’ needs and break down gender stereotypes. The mobility sector is still characterised by an uneven choice of travel modes due to multiple economic, social and cultural reasons. The COVID-19 crisis imposed harsh travel restrictions that had differentiated impacts on the mobility of various user groups, including the gender-defined ones. In this paper, the main social and economic trends, which affect gender demand, are identified along with their main characteristics. An overview of successful pre-pandemic European experiences in the gender planning field is discussed, with the aim of increasing the level of knowledge on the issue, adapting mobility services to meet the needs of all people, rethinking urban mobility and public space planning by incorporating more criteria of accessibility and sustainability, and improving the quality and safety of cycling, walking and public transport routes. For the recent pandemic circumstances, we indicate the facts that led women to experience a differentiated mobility landscape than men. Our research findings highlight the main factors that have led to gender inequality and discuss the gender gaps which emerged. Finally, we provide suggestions for the mitigation of this problem, laying the foundations for defining best practices useful for transport managers and authorities, which also increase both the quality of life and economic and employment opportunities. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

An Analysis of the Integration of DRT Services with Local Public Transport in Post-pandemic Period: Some of the Preliminary Insights in the Italian Context

Italy was one of the first country in Europe which was severely affected by COVID-19 pandemic. Several critical issues emerged during the different pandemic phases, especially in the health and mobility sector. Restrictions on public transport reduced the supply of transport, highlighting the need to rethink complementary transport systems. Since May 2020, in the post-lockdown phase, the provision of local public transport has been based on ordinary services, such as bus services, which are mainly intended to meet the needs of systematic travel between the places of residence and work on main development routes of the territory. These services have undergone reductions both in the on-board capacity and in some cases the complete elimination of transit routes. The rebalancing in favour of sustainable modes of transport and the reduction of the share of road mobility is pursued through the encouragement of ad-hoc measures aimed at balancing-off the supply-demand mechanism and improving the quality of services. The application of an on-demand responsive transit system has the ability to improve the transit needs in order to reach the places where personal or family services are provided or to enjoy the resources distributed within desired territory. In Italy since March 2020, new areas of weak demand for transport have been created, i.e. areas with a certain number of users that need to be transferred to and from places that have generally never had access to public transport or have had it restricted. The Demand Responsive Transport (DRT) system is, therefore, used in both urban and suburban areas, allowing even those who do not have their own means of transport (for example, disadvantaged social categories or users with a short stay in the area) or who are suitably equipped (people with reduced or no motor skills), to move around in areas easily. The present work focuses on an analysis of the current state of affairs, starting from the literature and regulations concerning the diffusion of the DRT systems in Italy, and offers some ideas for the optimisation of an integrated public transport service. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Forecasting the COVID-19 Space-time Dynamics in Brazil with Convolutional Graph Neural Networks and Transport Modals

One of the major challenges imposed by the SARS-CoV-2 pandemic is the lack of pattern in which the virus spreads, making it difficult to create effective policies to prevent and tackle the pandemic. Several approaches have been proposed to understand the virus behavior and anticipate its infection and death curves at country ans state levels, thus supporting containment measures. Those initiatives generalize well for general extents and decisions, but they do not predict so well the trajectory of the virus through specific regions, such as municipalities, considering their distinct interconnection profiles. Specially in countries with continental dimensions, like Brazil, too general decisions imply that containment measures are applied either too soon or too late. This study presents a novel scalable alternative to forecast the numbers of case and death by SARS-CoV-2, according to the influence that certain regions exert on others. By exploiting a single-model architecture of graph convolutional networks with recurrent networks, our approach maps the main access routes to municipalities in Brazil using the modals of transport, and processes this information via neural network algorithms to forecast at the municipal level ans for the whole country. We compared the performance in forecasting the pandemic daily numbers with three baseline models using Mean Absolute Error (MAE), Symmetric Mean Absolute Percentage Error (sMAPE) and Normalized Root Mean Square Error (NRMSE) metrics, with the forecasting horizon varying from 1 to 25 days. Results show that the proposed model overcomes the baselines when considering the MAE and NRMSE (p ˂0.01), being specially suitable for forecasts from 14 to 24 days ahead. Author

Beyond The Limits of Predictability in Human Mobility Prediction: Context-Transition Predictability

Urban human mobility prediction is forecasting how people move in cities. It is crucial for many smart city applications including route optimization, preparing for dramatic shifts in modes of transportation, or mitigating the epidemic spread of viruses such as COVID-19. Previous research propose the maximum predictability to derive the theoretical limits of accuracy that any predictive algorithm could achieve on predicting urban human mobility. However, existing maximum predictability only considers the sequential patterns of human movements and neglects the contextual information such as the time or the types of places that people visit, which plays an important role in predicting one's next location. In this paper, we propose new theoretical limits of predictability, namely Context-Transition Predictability, which not only captures the sequential patterns of human mobility, but also considers the contextual information of human behavior. We compare our Context-Transition Predictability with other kinds of predictability and find that it is larger than these existing ones. We also show that our proposed Context-Transition Predictability provides us a better guidance on which predictive algorithm to be used for forecasting the next location when considering the contextual information. Source code is at https://github.com/zcfinal/ContextTransitionPredictability. IEEE