No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
How could the station-based bike sharing system and the free-floating bike sharing system be coordinated?
Abstract
The station-based bike sharing system (SBBSS) and the free-floating bike sharing system (FFBSS) have been adopted on a large scale in China. However, the overlap between the services provided by these two systems often makes bike sharing inefficient. By comparing the factors that affect the usage of the two systems, this paper aims to propose appropriate strategies to promote their coordinated development. Using data collected in Nanjing, a predictive model is built to determine which system is more suitable at a given location. The influences of infrastructure, demand distribution, and land use attributes at the station level are examined via the support vector machine (SVM) approach. Our results show that the SBBSS tends to be favored in areas where there is a high concentration of travel demand, and close proximity to metro stations and commercial properties, whereas locations with a higher density of major roads and residential properties are associated with more frequent use of the FFBSS. With regard to the methods used, a comparison of several machine learning approaches shows that the SVM has the best predictive performance. Our findings could be used to help policy makers and transportation planners to optimize the deployment and redistribution of docked and dockless bikes.
... In general, bikeshare systems are categorised into two modes: station-based bikeshare systems (SBBS) and free-floating bikeshare systems (FFBS). They exhibit distinctive characteristics in terms of service use, first/last-mile flexibility, and accessibility (Ali et al., 2023;Cheng et al., 2020c;Gu et al., 2019a;Li et al., 2021;Ma et al., 2020;Wang et al., 2022). SBBS users need to rent bicycles and return them to designated stations. ...
... SBBS and FFBS show different service characteristics and cater to the travel demands of different population segments (Chen et al., 2020a;Cheng et al., 2020c;Fishman et al., 2015;Li, 2022;Younes et al., 2020). They have the potential to complement each other and improve the connectivity of urban metro systems Ma et al., 2020). ...
... The spatial distribution suggests that FFBS users travel more to lower-density neighbourhoods and SBBS users mainly travel to dense urban areas (Lazarus et al., 2020). Cheng et al. (2020c) found that proximity to metro stations is associated with more user demand for SBBS relative to the demand for FFBS. Through clustering metro stations in Nanjing, China, Chen et al. (2022) pointed out that the type of metro stations exerts different influences on the frequency of SBBS and FFBS feeder trips. ...
... One of the keys to the success of a DBS scheme is the location of the stations (Frade and Ribeiro, 2015;Lin and Yang, 2011). In general, DBS stations ought to be located in areas with high travel demand to ensure financial income (Cheng et al., 2020b;García-Palomares et al., 2012). A compact urban environment with higher population density, more commercial facilities, and more convenient metro services generally helps to generate travel demand for cycling (Cheng et al., , 2023Ji et al., 2017;Scott and Ciuro, 2019). ...
... Future studies should combine actual conditions such as land use and user intentions to identify more refined station locations. Second, the shock of dockless bike sharing on DBS has been attested to in previous studies (Chen et al., 2022b;Cheng et al., 2020b). Considering the competitive-cooperative relationship between dockless bike sharing and DBS in the site selection process is also an interesting topic that deserves broader examination. ...
In recent years, a growing number of cities worldwide have implemented docked bike sharing (DBS) systems. One of the most important features to the success of a DBS scheme is the deployment of the stations. However, prior studies on locating DBS stations have focused on travel demand while accessibility factors received limited attention. To tackle the above issue, this study proposes a three-stage framework to determine the appropriate locations for new DBS stations. Concretely, first, important factors influencing DBS usage are explored to yield a demand-based suitability map. Second, the ease of access to DBS services aggregated at demand points is assessed to generate a DBS accessibility map. Finally, combined with suitability and accessibility maps, a location-allocation model is leveraged to identify locations for building new stations to serve the most potential demand. A case study is conducted in Nanjing, China. The identification results show that ten new stations can further expand the DBS service area outward to some extent (from 80.71% to 83.87%) while meeting the high suitability and low accessibility conditions. These findings provide a useful tool for transportation planners and policymakers to take appropriate measures to achieve an equitable and profitable DBS system.
... Numerous existing studies on FFBS data analysis have focused on revealing the mechanisms influencing O or D point usage patterns. These studies have investigated different aspects of this issue, including socio-demographics (Link et al. 2020;Orvin and Fatmi 2021), weather conditions (Peters and MacKenzie 2019), land use (Chen and Ye 2021;Cheng et al. 2020a), built environment (Guo and He 2020;Shen et al. 2018), and access to metro system (Cheng et al. , 2023Ma et al. 2019). On balance, FFBS usage is higher in areas with denser populations, comfortable weather conditions, higher land use mix, friendlier cycling environments, and better interchange facilities. ...
... FFBS is usually backed by venture capital funding. For profit-making purposes, most bikes are assigned to densely populated areas with high demand (Cheng et al. 2020a;Gu et al. 2019). Nanjing is no exception, and citizens in its peripheral districts Content courtesy of Springer Nature, terms of use apply. ...
Extracting flow clusters consisting of many similar origin–destination (OD) trips is essential to uncover the spatio-temporal interactions and mobility patterns in the free-floating bike sharing (FFBS) system. However, due to occlusion and display clutter issues, efforts to identify inhomogeneous flow clusters from large journey data have been hampered to some extent. In this study, we present a two-stage flow clustering method, which integrates the Leiden community detection algorithm and the shared nearest-neighbor-based flow (SNN_flow) clustering method to efficiently identify flow clusters with arbitrary shapes and uneven densities. The applicability and performance of the method in detecting flow clusters are investigated empirically using the FFBS system of Nanjing, China as a case study. Some interesting findings can be drawn from the spatio-temporal patterns. For instance, the share of flow clusters used to meet the “first-/last-mile” demand at metro stations is reasonably high, both during the morning (71.85%) and evening (65.79%) peaks. Compared with the “first-/last-mile” flow clusters between metro stations and adjacent workplaces, the solution of the “first-/last-mile” flow clusters between metro stations and adjacent residences is more dependent on the FFBS system. In addition, we explored the shape and density distribution of flow clusters from the perspective of origin and destination points. The endpoint distribution characteristics demonstrate that the shape distribution of metro station point clusters is generally flatter and the spatial points within them are more concentrated than other sorts of point clusters. Our findings could help to better understand human movement patterns and home-work commute, thereby providing more rational and targeted decisions for allocating FFBS infrastructure resources.
... Internal transport facilities comprise number of docking stations for SBBS and area of parking spaces for bicycles. The number of docking stations is considered because SBBS is expected to influence FFBS as a feeder mode to URT (Chen et al., 2021;Cheng et al., 2020b). In addition, we take into account another four control variables related to whether a URT station is a transfer station, whether it is located in urban areas, its distance to the central business area (CBD), and presence of a school 2 . ...
... It is an interesting finding that the existence of SBBS in station areas could be beneficial to the FFBS-URT integrated use. This aligns with the work of Cheng et al. (2020b) and Chen et al. (2020) that SBBS and FFBS complement each other to foster a bicyclefriendly environment that makes bicycling become a convenient feeder mode to URT stations. Fig. 5e shows that bicycle parking space is significantly associated with the integrated use for all quantiles except at the 95th quantile. ...
Bike-sharing offers a convenient feeder mode for connecting to public transport, which helps to address the last-mile problem. However, few studies have examined the nuanced relationship between the built environment and the integration of free-floating bike-sharing (FFBS) with urban rail transport (URT). Drawing on weekly records of 3.12 million trips of the FFBS system in Nanjing, China, we examined the nonlinear effects of the built environment on FFBS-URT integrated use. A quantile regression method is utilised to estimate the relationships for morning and evening peaks, respectively. The results demonstrate the existence of the nonlinearity of the relationships. The effects of the built environment show variations in the significance levels and magnitudes of coefficients, depending on the quantiles. For example, the length of minor roads in station areas is strongly related to the integrated use at low quantile stations, whereas this effect is not statistically significant at medium and high quantiles. We also find that bicycle infrastructure displays more salient nonlinear effects than land-use variables and external transport facilities. In addition, temporal differences in the relationships between the built environment and the integrated use are also unveiled. Our findings help to inform dedicated and effective built environment interventions which support the planning of seamless connections between bike-sharing and urban rail transport.
... Initially, few articles focus on the feasibility and impacts of bike-sharing as a new public transportation mode in urban areas [11][12][13]. Recently, more papers begin to discuss the sustainable development of bike-sharing systems, especially the dockless bike-sharing systems [10,[14][15][16][17][18][19]. Because the study of dockless bike-sharing is still in progress, and some mature studies on the station-based bike-sharing can guide the development of the study on dockless bike-sharing, we review the literature on both station-based bike-sharing and dockless bike-sharing. ...
... Çelebi et al. considered station locations and bike allocation using a set-covering model and a queueing model for a station-based bike-sharing system, given a number of stations [23]. Cheng et al. [18] found that the station-based bikes are used more frequently near subway stations and commercial zones, whereas the dockless shared bikes are preferred in residential areas and near major roads, which provides useful suggestions for system operators to enhance the system efficiency by allocating and deploying these two types of shared bikes well. ...
The imbalanced distribution of shared bikes in the dockless bike-sharing system (a typical example of the resource-sharing system), which may lead to potential customer churn and lost profit, gradually becomes a vital problem for bike-sharing firms and their users. To resolve the problem, we first formulate the bike-sharing system as a Markovian queueing network with higher-demand nodes and lower-demand nodes, which can provide steady-state probabilities of having a certain number of bikes at one node. A model reduction method is then designed to reduce the complexity of the proposed model. Subsequently, we adopt an operator-based relocation strategy to optimize the reduced network. The objective of the optimization model is to maximize the total profit and act as a decision-making tool for operators to determine the optimal relocation frequency. The results reveal that it is possible for most of the shared bikes to gather at one low-demand node eventually in the long run under the influence of the various arrival rates at different nodes. However, the decrease of the number of bikes at the high-demand nodes is more sensitive to the unequal demands, especially when the size of the network and the number of bikes in the system are large. It may cause a significant loss for operators, to which they should pay attention. Meanwhile, different estimated values of parameters related with revenue and cost affect the optimization results differently.
... In this work, some studies describe station-based and dockless or free-floating systems [2,3]. The implications of implementing dockless systems are discussed in [4]. ...
This research aims to estimate the purposes for which bike-share users utilize shared bicycles from bike-sharing companies using selected predictors through multinomial logistic regression in Slovakia. The study seeks to provide a novel perspective on alternative transportation by addressing a gap in existing research, which has not previously focused on modeling the specific purposes of bicycle use. The final sample comprises 162 bike-share users out of more than 300 respondents. The results show that social status, bike-sharing company, and average distance are statistically significant input variables. Finally, we find that using shared bikes for recreation is more typical for employees with a traveled distance of up to 3 km from one of the two bike-sharing companies compared to the reference group (commuting to school). The paper contributes to better planning and management of bike-sharing systems.
... Luo [8] applied a continuous approximation analytical method to model the coupled optimization problem of a novel multimodal public transportation system based on a shared bicycle shuttle system. Cheng et al. [9] examined the efect of diferent factors on the station level through a support vector machine approach and concluded that the optimal choice of two shared bicycle service regimes, the station-based shared bicycle system (SBSBS) and the free-foating shared bicycle system (FFSBS), was optimal in the pairing of diferent scenarios. Tamakloe et al. [10] used truncated regression for a Simar-Wilson two-stage bootstrap data envelope analysis to explore the efciency of transit-oriented development (TOD) focusing on subway, bus, and shared bicycle systems at Seoul bus stations. ...
The primary objective of this paper is to minimize the overall travel costs for passengers while simultaneously maximizing the operational revenue for the transportation company. This is achieved through the optimization and adjustment of various factors, such as the intervals between regular bus and subway services, the duration of vehicle stops at each station, and the pricing structure for subway and shared bicycle usage. By enhancing the efficiency of passenger travel, we have successfully bolstered the company’s operational profits. In contrast to prior research, this paper comprehensively considers the dual uncertainties associated with both bus operations and shared bicycle operations within a cooperative system. By establishing a coordinated dual-level optimization model for regular bus, subway, and bike-sharing networks under dual uncertainty conditions, we employed convex combination techniques to unify the dual uncertain variables into a single objective, which was then incorporated into a chance-constrained bilevel programming model. Ultimately, we utilized KKT conditions to transform the model from a bilevel to a single level for resolution. This paper centers its research on the collaborative system comprising the Nanchang Metro Line 1, Bus Route 520, Bus Route 211, and the adjacent region hosting a cluster of shared bicycles. By leveraging Python programming, optimization models, empirical data on traffic flow and stoppage times, and OD data, we conducted an optimization analysis to solve the problem at hand. According to the optimization results, passenger waiting time, passenger transfer time, and passenger on board time are effectively reduced by 6.81%, 18.29%, and 23.92%. At a confidence level of 95%, the resulting time level results in a 12.44% reduction in total travel time. The average subway fare increased by 18.12%, the average shared bicycle fare decreased by 19.12%, and the total cost of travel expenses increased by 16.68%. The final total cost of travel was reduced by 4.06%, and the business operating income was increased by 13.10%. The comprehensive optimization results have effectively fulfilled the objectives of the bilevel optimization model, thereby confirming the rationality and practicality of the optimization approach. The research outcomes hold significant practical implications for facilitating the efficient and cooperative development of urban transportation networks, ultimately enhancing the convenience of residents’ travel experiences.
... These advanced bikes can enable geofenced returns without the need for installed stations, simplifying the establishment of temporary pop-up stations. Thereby, pop-up stations can conceptually unite the unique advantages of free-floating BSS in addition to the present station-based BSS [91]. • Dynamic pricing models: A pricing model that varies according to temporal and spatial factors such as time of days, location, and demand is implemented. ...
Bike-sharing systems (BSS) have emerged as an increasingly important form of transportation in smart cities, playing a pivotal role in the evolving landscape of urban mobility. As cities worldwide strive to promote sustainable and efficient transportation options, BSS offer a flexible, eco-friendly alternative that complements traditional public transport systems. These systems, however, are complex and influenced by a myriad of endogenous and exogenous factors. This complexity poses challenges in predicting BSS activity and optimizing its usage and effectiveness. This study delves into the dynamics of the BSS in Hamburg, Germany, focusing on system stability and activity prediction. We propose an interpretable attention-based Temporal Fusion Transformer (TFT) model and compare its performance with the state-of-the-art Long Short-Term Memory (LSTM) model. The proposed TFT model outperforms the LSTM model with a 36.8% improvement in RMSE and overcomes current black-box models via interpretability. Via detailed analysis, key factors influencing bike-sharing activity, especially in terms of temporal and spatial contexts, are identified, examined, and evaluated. Based on the results, we propose interventions and a deployed TFT model that can improve the effectiveness of BSS. This research contributes to the evolving field of sustainable urban mobility via data analysis for data-informed decision-making.
... Currently, shared micromobility services are mainly divided into two different types, station-based (docked) and dockless sharing systems [13]. Station-based systems have fixed docking stations, and users need to know in advance if there is an available dock near their destination, while dockless systems enable users to go directly and park in their respective destinations, leaving the micro-vehicles almost anywhere [2,14,15]. Both docked and dockless systems have been the subject of several studies. ...
Sustainable urban mobility is an imperative concern in contemporary cities, and shared micromobility systems, such as docked bike-sharing, dockless bike-sharing, and dockless e-scooter-sharing, are recognized as essential contributors to sustainable behaviors in cities, both complementing and enhancing public transport options. Most of the literature on this subject predominantly focuses on individual assessments of these systems, overlooking the comparative analysis necessary for a comprehensive understanding. This study aims to bridge this gap by conducting a spatiotemporal analysis of two different shared micromobility modes of transportation, docked bike-sharing systems and dockless e-scooter-sharing systems operating in the municipality of Lisbon. The analysis is further segmented into arrivals and departures on weekdays and weekends. Additionally, this study explores the impact of sociodemographic factors, the population’s commuting modes, and points of interest (POIs) on the demand for both docked bike-sharing and dockless e-scooter-sharing. Multiscale Geographically Weighted Regression (MGWR) models are employed to estimate the influence of these factors on system usage in different parishes in Lisbon. Comparative analysis reveals that the temporal distribution of trips is similar for both docked bike-sharing and dockless e-scooter-sharing systems on weekdays and weekends. However, differences in spatial distribution between the two systems were observed. The MGWR results indicate that the number of individuals commuting by bike in each parish has a positive effect on docked bike-sharing, while it exerts a negative influence on dockless e-scooter-sharing. Also, the number of commercial points of interest (POIs) for weekday arrivals positively affects the usage of both systems. This study contributes to a deeper understanding of shared micromobility patterns in urban environments and can aid cities in developing effective strategies that not only promote and increase the utilization of these shared micromobility systems but also contribute to sustainable urban mobility.
... Network science, with its abstraction power, provides a quantitative framework for analyzing collective dynamics and interactions among network components in various disciplines, including transport systems. Specifically, graph theory has been instrumental in understanding transport networks, allowing for the study of topological structures, flow dynamics, and path relationships within these systems (Cheng et al., 2020a;Teixeira and Derudder, 2021;Chen et al., 2022a). Studies have used graph theory to analyze public transport networks by examining their topological stability (Derrible and Kennedy, 2011), robustness against perturbations (Builes-Jaramillo and Lotero, 2022), and community structure (Chen et al., 2022b). ...
Service bottlenecks are a key barrier to building a resilient public transport system. In this paper, we propose a new approach to automatically extract the role of a station in dynamical public transport flow networks based on the emerging role discovery method in network science. The term "role" in this study refers to the distinctive position or function that a station plays within the public transport flow network. Using smart card data from Nanjing public bikesharing agencies, we first construct dynamical public transport flow networks with notions of dynamical graph and edge. We then develop a dynamical algorithm to recursively compute the structural flow characteristics of nodes in passenger flow networks. Non-negative Matrix Factorization is conducted to extract the role memberships from the derived structural feature matrix and interpret each role in terms of measurements with practical values. The network hubs and potential service bottlenecks are then identified based on their operating characteristics and dynamics. Furthermore, the day-today and within-day role dynamics of public transport stations over time are unveiled. The results contribute to a better understanding of the interplay between stations in the network, and the identification of roles provides insight for public transport agencies to improve service resilience.
... Different from the feature importance results in section 4.2.3, the commercial had a significant positive effect on weekday bike-sharing use and was a global variable with little spatial variation. Dense commercial areas often have a high concentration of business activity and offices, so there are more commuters here on weekdays, which may lead to more bike-share use (Cheng et al., 2020). Previous studies have found a positive correlation between the density of cultural facilities and bicycle station use (Guo et al., 2022), our findings supported it only in 6.68% of the region on weekdays. ...
Bike-sharing offers a convenient and sustainable mode of transportation. Numerous studies have investigated the influence of temporal variations in the natural environment on cycling, as well as the impact of physical street characteristics like networks and infrastructures. However, few studies integrated and compared the effects of natural environment and street visual quality on cycling in the spatial dimension. As a case study, we focused on the impact of these two factors on Citi Bike system on weekdays and weekends in New York City, while accounting for sociodemographic and functional factors. This study employed machine learning and multiscale geographically weighted regression models at both station and neighborhood scales for a comprehensive analysis of their relationships. The results reveal that the natural environment factors, particularly visibility, are more important factors associated with bike-sharing use. Among the visual quality factors, motorized traffic has a negative impact on both weekday and weekend cycling. When considering geographical location, sky openness exhibits an unfavorable influence on weekday cycling in specific areas. By combining natural environment and visual quality factors, our study promotes optimal resource allocation and the development of bike-friendly cities.
... q ir denotes the probability that a node i belongs to community r, and k i is the out-degree of node i. To obtain the final result of community detection, we need to iterate Equations (6)- (8). ...
In this paper, we investigate the sustainability of docked bike-sharing in Nanjing in terms of environmental benefits and financial operations by comparing the data of March 2017 and March 2023 in Nanjing. We modify a community detection method, give and prove dynamic boundary conditions for the objective function of the heuristic algorithm, and realize the estimation of the rebalancing coefficients for this mega-system, thus obtaining more accurate emission factors. We find that there are significant differences in the results obtained from environmental benefit assessments over time. Further, there are also significant differences at the national level. This may signify that the assessment data of one country’s system cannot give a direct reference for another country’s system. Second, we considered the economic basis required for the environmental benefits of docked bike-sharing systems. We have calculated the sustainability of the system’s financial operations by considering its revenues over the next nine years, including the cost of facility inputs, facility upgrades, dispatching costs, labor costs, maintenance costs, and the time value of money. The results show a 4.6-fold difference in emission factors between 2017 and 2023; comparing 2017 to 2023 (when demand loss has been severe), the investment in 2017 will be recouped 2 years later than in 2023. Switching distribution vehicles from fuel vehicles to electric trikes would severely deteriorate the operator’s key financial metrics while only reducing the emission factor value by 8.64 gCO2 eq/km, leading to an unsustainable system. This signals the potential for the financial unsustainability, or even bankruptcy, of operators if the requirements for sustained emissions reductions from the bike-sharing system are divorced from the form of the economy on which it is sustainably operated. Finally, we consider the geographical patterns between environmental benefits and financial operations. We find that financial sustainability varies across geographic locations. Under financial sustainability, we gave emission factors under the mix distribution vehicle scenario.
... Additionally, we used the statistical population density of the smallest administrative area where each sampling point is located as population density. Besides, road density, sidewalk density, and cycleway density were measured as the ratio of total road/sidewalk/cycleway length and the urban area, and the unit is km/km 2 , the same as the previous studies (Cervero et al., 2009;Cheng et al., 2020). Followed Cervero et al. (2009), considering the simplicity and accuracy of calculations, road density, sidewalk density, and cycleway density were aggregated and counted using a 1000-meter buffer. ...
... The dependent variables are the average hourly pick-up and drop-off usage per census tract pre and post pandemic. 2 According to previous studies that examined the associated factors of ridesourcing usage (Cheng et al., 2020a;Ghaffar et al., 2020;Jin et al., 2022b;Rayle et al., 2016), four categories of independent variables are considered in this research, including built environment factors (Cervero et al., 2009;Cervero & Kockelman, 1997;Cheng et al., 2020b;Jin et al., 2022c), socio-demographic factors, weather conditions, and temporal seasonality, which are shown in Table 1. All variables are aggregated at the census tract level. ...
Ridesourcing has undergone a magnificent development pre pandemic and has had a transformative impact on travel behavior and urban mobility. While an individual's travel behavior has been found to be inevitably influenced by the pandemic, how COVID-19 influences the utilization of ridesourcing has rarely been discussed in previous studies. Understanding how COVID-19 has reshaped people's ridesourcing usage may also be helpful for providing updated policy implications in the post-pandemic era. The objective of this research is to investigate the extent to which the impact of the built environment on the utilization of ridesourcing has changed post pandemic, as compared to pre-pandemic period. This study analyzes the spatiotemporal difference in ride-sourcing usage before and after the pandemic, and the differential impacts of built environment factors on ridesourcing usage using real-world trip data in Chicago. Generalized additive mixed models (GAMMs) are applied to analyze the nonlinear built environment effects on ridesourcing usage. Results show average ride-sourcing usage in the post-pandemic period failed to recover to pre-pandemic trip volumes by June 2022. There are significant differences in the effects of population density, intersection density, land use mix, population employment balance index, and bus accessibility on ridesourcing pickup usage between the post-pandemic and pre-pandemic periods. For example, population density had an overall positive effect pre pandemic. However, a significant negative effect was observed in areas with extremely high population density post pandemic. The positive effect of land use mix before the pandemic also turns into a negative effect after the pandemic. It seems that COVID-19 is having long-term effects on ridesourcing usage, at least in Chicago. Relevant policies and tailored land-use interventions should be updated regarding the differentiated built environment effects in the post-pandemic era.
... With the rapid development of urbanization and technology, exploring the dynamics of transit networks has become challenging due to their increasing size and complexity, along with our greater access to large-scale automatically-collected data sources such as smart card (SC) data. Network science provides us with an abstraction for quantitatively analyzing the collective dynamics accounting for the interactions among components in networks across a broad set of disciplines, including transport, biology, information, and social sciences (Coviello, 2006;Snijders et al., 2010;Cheng et al., 2020;Teixeira and Derudder, 2021;Chen et al., 2022a). Over the past few decades, there have been numerous network studies on transit systems (Melkote and Daskin, 2001;Derrible and Kennedy, 2011;Zhang et al., 2019;Builes-Jaramillo and Lotero, 2022;Chen et al., 2022b). ...
... In general, higher road densities are associated with more walkable and bikeable communities, which can make FFBS more convenient and appealing. But at the same time, more roads also mean more vehicles and intersections, which raises concerns about safety and delay (Cheng et al., 2020;Zhang et al., 2017). As for commuting mode choice, land use types, such as residential and commercial patterns, could attract more adoption of bike-sharing (Guo and He, 2020). ...
The free-floating bike-sharing system (FFBS) is an effective method of alleviating urban traffic congestion and greenhouse gas (GHG) emissions. The present study used street view images and the normalized difference vegetation index (NDVI) to explore the influence of urban greenness on FFBS usage in Beijing, China. In a full sample Poisson model, FFBS usage at a given location would increase 1.003-fold for each unit increase in the greenery view index (GVI) at that location. However, NDVI was negatively associated with FFBS usage. The spatial distribution of urban functional areas was identified. It indicated that they moderated the relationship between urban greenness indices and FFBS usage. Several policy implications were proposed for promoting the level of urban greenness and encouraging the adoption of green travel modes such as FFBS.
... In the previous literature, it is assumed that the predictors and travel behaviours follow a pre-defined or parametric relationship. More recent studies began to explore the nonlinear relationships between built environment variables and travel behaviours [34][35][36][37]. Most statistical models predetermine a model structure that requires the input data to satisfy as- sumptions, such as random utility maximization theory [38], while many machine learning methods rely on computers to probe the data for its structure. ...
The rail transit system was developed in Chinese large cities to achieve more efficient and sustainable transport development. However, the extent to which the newly built rail transit system can facilitate people’s multimodality still lacks evidence, and limited research examines the interrelationship between trip stages within a single trip. This study aims to explore the interrelations between trip stage characteristics, socio-demographic attributes, and the built environment. It examines how rail transit is integrated as part of multimodal trips after it is introduced. The data are extracted from the Chongqing Urban Resident Travel Survey from 2014, three years after the new rail transit network was established. It applies an XGBoost model to examine the non-linear effect. As a result, the separate trip stage characteristics have more of an impact than the general trip characteristics. The non-linear effects revealed by the machine learning model show changing effects and thresholds of impact by trip stage characteristics on people’s main mode choice of rail transit. An optimal radius of facility distribution along the transit lines is suggested accordingly. Synergistic effects between variables are identified, including by groups of people and land use characteristics.
... Cycling behaviour is influenced by various factors [3] including socio-demographic characteristics, the social environment, weather conditions, and the built environment [4][5][6][7][8]. ...
The incorporation of cycling as a mode of transport has been shown to have a positive impact on reducing traffic congestion, improving mental health outcomes, and contributing to the development of sustainable cities. The proliferation of bike-sharing systems, characterised by their wide availability and high usage rates, has made cycling in urban areas more accessible and convenient for individuals. While the existence of a relationship between cycling behaviour and the built environment has been established, few studies have specifically examined this connection for weekdays and weekends. With the emergence of new data sources, new methodologies have become available for research into this area. For instance, bike-sharing spatio-temporal datasets have made it possible to precisely measure cycling behaviour over time, while street-view images and deep learning techniques now enable researchers to quantify the built environment from a human perspective. In this study, we used 139,018 cycling trips and 14,947 street-view images to examine the connection between the built environment consisting of urban greenways and cycling behaviour. The results indicated that the greenness and enclosure of the level of greenway were positively correlated with increased cycling on both weekdays and weekends. However, the openness of the greenway appears to have opposing effects on cycling behaviour depending on the day of the week, with high levels of openness potentially promoting cycling on weekends but hindering it on weekdays. Based on the findings of this study, policymakers and planners should focus on the cycling environment and prioritise improving its comfort and safety to promote green transportation and bicycle-friendly cities.
... Analyzing starting and ending points of such trips allows to efficiently plan and manage sharing systems (Zhao et al. 2019;Reck et al. 2021). In urban planning, origin-destination data can be used to evaluate the usage of sharing systems in order to learn about their functionality or to create regulations and measures that ensure an efficient integration into the urban transport system (Sun, Li, and Zuo 2019;Caspi, Smart, and Noland 2020;Cheng et al. 2020). The analysis of existing bike-sharing systems can also help cities to estimate usage and locate stations or usage areas before implementing a new system, based on the spatial features of a city (Lee and Sener 2020). ...
Regression models are commonly applied in the analysis of transportation data. This research aims at broadening the range of methods used for this task by modeling the spatial distribution of bike‐sharing trips in Cologne, Germany, applying both parametric regression models and a modified machine learning approach while incorporating measures to account for spatial autocorrelation. Independent variables included in the models consist of land use types, elements of the transport system and sociodemographic characteristics. Out of several regression models with different underlying distributions, a Tweedie generalized additive model is chosen by its values for AIC, RMSE, and sMAPE to be compared to an XGBoost model. To consider spatial relationships, spatial splines are included in the Tweedie model, while the estimations of the XGBoost model are modified using a geographically weighted regression. Both methods entail certain advantages: while XGBoost leads to far better values regarding RMSE and sMAPE and therefore to a better model fit, the Tweedie model allows an easier interpretation of the influence of the independent variables including spatial effects.
... The decisions of bike-sharing station locations often consider potential demand (Frade & Ribeiro, 2015;Ursaki & Aultman-Hall, 2015). Commonly, places with high population density (Ursaki & Aultman-Hall, 2015) and proximate to transit stations and commercial properties (Cheng et al., 2020;Ursaki & Aultman-Hall, 2015) tend to have more stations. Meanwhile, marginalized communities tend to have fewer bike-sharing stations (Hosford & Winters, 2018;Smith et al., 2015), and the reason could be associated with perceived low demand since bike-sharing usage can be unaffordable for low-income people (Hoe & Kaloustian, 2014). ...
The rapid growth of bike-sharing usage spurs a large amount of empirical research. However, much research focuses on existing bike-sharing services, without considering the gaps between revealed and potential demand, while some potential demand cannot be met without a supply of bike-sharing facilities. To address this gap, this research develops a two-step approach: the first step proposes an equitable supply of bike-sharing stations based on neighborhood characteristics, and the second step predicts potential bike-sharing usage with the proposed supply scenario. Using data from a station-based bike-sharing system in the city of Chicago, we specify and evaluate the new methodological approach with transformed spatial regression models. Results identify neighborhoods that have potential demand but are under-served. Our approach provides a tool for providing an equitable supply of bike-sharing services and promoting wide adoption of bike-sharing across diverse neighborhoods.
... In China alone, more than 200 cities have launched FFBS programs, providing a substantial 4 23 million shared bikes for public use (Gu et al., 2019). FFBS bikes are not restricted by 5 fixed docks and can be parked anywhere that is appropriate (as long as parking is permitted) 6 (Cheng et al., 2020b). Each bike in the system has a built-in Global Positioning System (GPS) 7 tracking device that allows users to locate and rent a nearby bike via smartphone applications 8 (Zhao and Ong, 2021). ...
Free-floating bike sharing (FFBS) programs have been put into use in many cities around the world in an effort to provide travel convenience for local inhabitants. However, it is unclear whether the existing administrative subdivisions reflect the most plausible spatial structure for the daily movements of FFBS users. In this study, we first build a spatial interaction network based on FFBS journey data from Nanjing, China. On this basis, urban activity zones are delineated leveraging the Leiden community detection algorithm, and a set of network measures are then utilized to examine the properties of these activity zones. The community detection results show that the identified activity zone borders rarely overlap with existing administrative district borders. Activity zone borders could separate FFBS travel flows more rationally than administrative district borders. In order to quantitatively explore the attenuation effect of activity zone borders on FFBS travel flows, we further subdivide the borders into various types (i.e., administrative, natural, and infrastructural borders) and construct border effect models. The regression results show that, in addition to demographic size, built environment, and distance factors, the activity zone border parameters are also revealed as important predictors of bilateral travel flows. Among the different types of activity zone borders, natural borders consisting of water bodies and mountains have the most significant attenuation effect on FFBS travel flows. The delineation of activity zones could better portray short-distance mobility patterns and urban structures, thereby providing nuanced and appropriate guidance for deliberating related policies.
... The free-floating bikes can be parked anywhere without the limitation of docks or physical stations. The convenience and fashion make DBS widely used and rapidly expanded particularly in recent years [8]. Besides, DBS becomes even more important after and end of truck repositioning are the driver's home. ...
Dockless bike sharing (DBS) has the free-floating feature and large-scale fleet, which poses significant challenges to repositioning. This paper finds the Matthew mechanism of bike floating based on real-world trip data in Nanjing, China, and then proposes an integrated method for the large-scale DBS repositioning problem. Firstly, trip origins are analyzed by the first layer clustering to identify thousands of virtual stations. Secondly, the novel index of bike density and turnover rate are used in target inventory estimation for higher future usage. Lastly, the second-level clustering algorithm assigns workload-balanced tasks to truck drivers, and an advanced neighborhood search algorithm is applied to design the truck route. Results show that there are about three hundred pick-up stations and about three thousand drop-off stations for Nanjing DBS repositioning. And the proposed method is demonstrated to provide a better solution for increasing future usage and improving driver workload balance.
... The built environment is widely recognized to influence the travel behaviors of bike-and-ride users (e.g Böcker et al., 2020 ;Cheng et al., 2020b ;Griffin and Sener, 2016 ;Guo and He, 2021 ;Hua et al., 2021 ;Li et al., 2020 ;Van Acker et al., 2013 ). It is primarily due to the fact that built environment characteristics determine the spatial-temporal constraints of activities and the way travellers perceive the travelling environment. ...
Bikeshare offers a flexible feeder mode to metro and improves the overall connectivity of urban public transport systems. Although bikeshare has received much research attention, the relationship between the built environment and bikeshare-metro integrated use (i.e. the use of bikeshare for the first/last mile) remains underexplored. Using a one-month dataset of bikeshare trip records in Nanjing, China, this research scrutinizes the built environment correlates of the integrated use. A generalized additive mixed model is employed to capture the temporal autocorrelation attributable to repeated observations over time and the spatial autocorrelation resulting from geographical proximity between individual metro stations. The results show that built environment variables do impose salient nonlinear effects on the bikeshare-metro integrated use. For example, population density only increases the integrated use at certain intervals, and interestingly, extremely high density leads to a decline in bikeshare-metro integrated use. The proportion of commercial and greenspace land uses within metro station catchment areas should not be too high or too low. There exists an optimal land use setting that maximizes the utility of land-use interventions. These findings provide useful policy implications for developing an environment that facilitates the integration of bikeshare and urban metro systems.
... A novel finding is that our result indicates that SBBS non-commuters are more affected by the launch of FFBS than SBBS commuters. The reason may be that residents are more inclined to use SBBS (dock-based) for commuting and FFBS (dockless) for leisure or non-commuting related activities (Chen et al., 2021a;Cheng et al., 2020;Mckenzie, 2018). As expected, the number of SBBS users have been hit hard by the COVID-19 pandemic, but the decline in the proportion of commuters was not evident (i.e., from 36.6% to 34.8%). ...
Station-based bike sharing (SBBS) not only provides commuters with direct “door-to-door” trips, but also plays a vital role in addressing the “first/last mile” challenges for public transportation system. However, there is a lack of research into portraying year-to-year changes in SBBS commuter behaviors. With five-year (from 2016 to 2020) SBBS smart card data collected in Nanjing, China, a longitudinal analysis is performed in this study to trace yearly dynamics of commuter behaviors at an individual level. We identify two sorts of SBBS commuters (i.e., SBBS-alone and SBBS-metro commuters) based on users’ spatial-temporal travel regularities. The paper finds that (i) the number of SBBS users presented a considerable fluctuation trend over a five-year span, while the proportion of SBBS commuters stabilized at an equilibrium level; (ii) the COVID-19 outbreak accelerated the decline in the proportion of female and young SBBS commuters; (iii) most SBBS commuters were recorded for only one year out of five, while the share of commuters who used SBBS for four years or more is tiny, <5%; (iv) the trip duration of SBBS-alone commuters was significantly longer than that of SBBS-metro commuters, and both showed some increase during the COVID-19 pandemic; (v) the number of non-loop trip chains was dramatically higher than that of loop trip chains, which is more prominent among SBBS-metro commuters. Our findings could provide valuable insights into the behavioral dynamics of SBBS commuters and offer recommendations on how policy makers and transportation planners could respond to these precipitate changes.
... One key finding from the following regression models is that bikesharing usage frequency was not a significant predictor of daily GHGs emissions on both weekdays and weekends. Advocates for shared micromobility programs believe that micromobility activities can yield a notable reduction in GHGs emissions, particularly when they are fully integrated with public transport systems (e.g., Chen et al., 2021;Cheng et al., 2020). However, the 2017 NHTS data shows that young adults who use bikesharing programs more often will not have lower GHGs emissions than their non-user counterparts. ...
This study analyzes the relation between shared mobility services and greenhouse gases (GHGs) emissions by using a nationally representative sample of US young adults. We conduct a comprehensive analysis based on the data collected in the 2017 National Household Travel Survey (NHTS). These trip-level emissions are calculated following MOtor Vehicle Emission Simulators (MOVES) and Greenhouse Gases, Regulated Emissions, and Energy Use in Transportation Model (GREET) workflows. We find that the weekday sample has a significantly higher value in daily GHGs emissions than the weekend sample. Controlling for other factors, shared micromobility services usage is found to have a significant impact on daily GHGs emissions for both weekday and weekend travel. Our analyses further indicate that carsharing complements public transit, and its users are more likely to reside in areas with better public transit supply. We find that the use of transportation network companies (TNCs) has a positive relationship with young adults’ GHGs emissions on weekdays only. The study results and implications may be useful for planners and professionals interested in tracking the impacts of new mobility services on transportation and the relevant environmental outcomes.
... Extensive studies about bike-sharing have explored improving the planning and operation of bike-sharing, to provide better services for users. Previous studies about bike-sharing can be generally classified into three categories: (1) user demand (Wang et al., 2018;Biehl et al., 2019;Cheng et al., 2020;Reilly et al., 2020;Chen et al., 2021); (2) bike rebalancing (Caggiani et al., 2018;Bruck et al., 2019;Huang et al., 2020); and (3) parking allocation (Lin et al., 2018;Loidl et al., 2019;Hua et al., 2020). ...
Introduction:
Coronavirus disease 2019 (COVID-19) has triggered a worldwide outbreak of pandemic, and transportation services have played a key role in coronavirus transmission. Although not crowded in a confined space like a bus or a metro car, bike-sharing users are exposed to the bike surface and take the transmission risk. During the COVID-19 pandemic, how to meet user demand and avoid virus spreading has become an important issue for bike-sharing.
Methods:
Based on the trip data of bike-sharing in Nanjing, China, this study analyzes the travel demand and operation management before and after the pandemic outbreak from the perspectives of stations, users, and bikes. Semi-logarithmic difference-in-differences model, visualization methods, and statistic indexes are applied to explore the transportation service and risk prevention of bike-sharing during the pandemic.
Results:
Pandemic control strategies sharply reduced user demand, and commuting trips decreased more significantly. Some stations around health and religious places become more important. Men and older adults may be more dependent on bike-sharing systems. The declined trips reduce user contacts and transmission risk. Central urban areas have more user close contacts and higher transmission risk than suburban areas. Besides, a new concept of user distancing is proposed to decrease transmission risk and the number of idle bikes.
Conclusions:
This paper is the first research focusing on both user demand and transmission risk of bike-sharing during the COVID-19 pandemic. This study evaluates the mobility role of bike-sharing during the COVID-19 pandemic, and also provides insights into curbing the viral transmission within the city.
... Cheng et al. (2019), Ma and Ye (2019) and Meng et al. (2014) proposed similar methods, such as investing in dedicated cycle and pedestrian lanes, and encouraging compact community design through connected streets and mixed land use. Furthermore, bikesharing systems can provide a flexible and convenient transport mode for short trips, particularly for the first/last mile (Cheng et al., 2020b;Lyu et al., 2020;Zhang and Meng, 2019;Zhang et al., 2021). Second, development of urban public transport within comprehensive urban planning should be prioritised. ...
Studies linking commuting and well-being have received increasing attention in the field of mobility and transport. However, most studies primarily focus on the relationship between commuting and hedonic well-being. Few studies have investigated the commuting experience and eudaimonic well-being. Therefore, the aim of this paper is to explore the relationship between the commuting experience and both hedonic and eudaimonic well-being, using Heze (China) as a case study. The results indicate that, first, educational attainment is related to hedonic well-being, and transport mode is related to both the commuting experience and hedonic well-being. Furthermore, we found that some combinations of individual characteristics and transport mode are related to the commuting experience and hedonic well-being, but none of them relates to eudaimonic well-being. In addition, there are strong positive correlations between the commuting experience and hedonic well-being, between the commuting experience and eudaimonic well-being, and between hedonic and eudaimonic well-being. We also found that commuting by public transport, walking and cycling is more likely to improve the quality of the commuting experience, and both hedonic and eudaimonic well-being. In terms of policy implications, policymakers and transport planners should, therefore, promote people’s well-being by prioritising the development of sustainable transport, and encouraging greater use of public transport and active travel.
Increasing urban traffic congestion and environmental pollution have led to the embrace of bike-sharing for its low-carbon convenience. This study enhances the operational efficiency and environmental benefits of bike-sharing systems by optimizing electronic fences (e-fences). Using bike-sharing order data from Shenzhen, China, a data-driven multi-objective optimization approach is proposed to design the sustainable dynamic capacity of e-fences. A dynamic planning model, solved with an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II), adjusts e-fence capacities to match fluctuating user demand, optimizing resource utilization. The results show that an initial placement of 20 bicycles per e-fence provided a balance between cost efficiency and user convenience, with the enterprise cost being approximately 76,000 CNY and an extra walking distance for users of 15.1 m. The optimal number of e-fence sites was determined to be 40 based on the solution algorithm constructed in the study. These sites are strategically located in high-demand areas, such as residential zones, commercial districts, educational institutions, subway stations, and parks. This strategic placement enhances urban mobility and reduces disorderly parking.
Bike-sharing systems (BSSs) have become commonplace in most cities worldwide as an important part of many smart cities. These systems generate a continuous amount of large data volumes. The effectiveness of these BSS systems depends on making decisions at the proper time. Thus, there is a vital need to build predictive models on the BSS data for the sake of improving the process of decision-making. The overwhelming majority of BSS users register before utilizing the service. Thus, several BSSs have prior knowledge of the user's data, such as age, gender, and other relevant details. Several machine learning and deep learning models, for instance, are used to predict urban flows, trip duration, and other factors. The standard practice for these models is to train on the entire dataset to build a predictive model, whereas the biking patterns of various users are intuitively distinct. For instance, the user's age influences the duration of a trip. This endeavor was motivated by the existence of distinct user patterns. In this work, we proposed divide-and-train, a new method for training predictive models on station-based BSS datasets by dividing the original datasets on the values of a given dataset attribute. Then, the proposed method was validated on different machine learning and deep learning models. All employed models were trained on both the complete and split datasets. The enhancements made to the evaluation metric were then reported. Results demonstrated that the proposed method outperformed the conventional training approach. Specifically, the root mean squared error (RMSE) and mean absolute error (MAE) metrics have shown improvements in both trip duration and distance prediction, with an average accuracy of 85% across the divided sub-datasets for the best performing model, i.e., random forest.
In this study, we examine the impact of a new mobile-based, dockless bike-sharing service on public transportation usage. This new bike-sharing model removes the constraint of having fixed stations and gives users full flexibility on where to pick up and return bikes. This innovative feature of dockless bike sharing potentially disrupts the current norms of how people commute. The dockless shared bikes offer easy connections between destinations and public transportation stations. They can potentially promote public transportation, by improving its flexibility and outreach. To examine this impact, we collaborate with one of the largest dockless bike-sharing companies in China and collect unique daily-station-level panel data of shared-bike rides and subway traffic. Our findings indicate that a 1% increase in shared-bike rides leads to an increase of 0.35% in subway traffic. Further analyses show that this positive effect is stronger when people need to travel a longer distance to reach subway stations. These results suggest one potential underlying mechanism for the positive relationship we observe, that is, dockless shared bikes alleviate the “last-mile problem” for public transportation, making it a more appealing mode of transportation, compared with alternatives. Overall, we find that dockless shared bikes, in contrast to ridesharing or traditional bike sharing, act as a complement, rather than a substitute, for public transportation. Dockless shared bikes present a greener way of commuting, with significant environmental and societal impacts.
This research considered the uncertainty of the operation time of shared bicycle, constructed the urban coupling network, and established the optimization model for the cooperative operation of conventional buses, subways and shared bikes. In the programming model, the optimization objective is to minimize the total travel time of passengers, and by optimizing and adjusting the departure intervals of conventional buses and subways as well as the stopping time of vehicles, the travel efficiency of passengers is improved. The interchange cooperative system composed of Nanchang Metro Line 1 and Bus 520 and the surrounding shared bicycle concentration area was taken as the case study. According to the optimization results, the passenger waiting time, passenger transfer time, and total passenger on-board time are effectively reduced by 21.5%, 23.2%, and 7.37%; ultimately, the total travel time is reduced by 8.2% at a confidence level of 95%. Case analyses show that the conventional bus stopping time has the greatest impact on the total travel time of the passengers as compared to the other variables. The research is of positive practical significance for promoting the efficient and coordinated development of urban transportation networks and facilitating the travel of residents.
Bike-sharing systems (BSSs) have been adopted in various places, and many primary studies have been conducted to design and establish station locations. However, there has been no attempt to compile and summarize these in a systematic literature review (SLR) related to long-term BSS design. This paper presents an SLR that identifies and interprets studies published from January 1st, 2001, to January 1st, 2023. The main research question this paper seeks to answer is “What key factors are used to design BSSs?” those factors are supported by criteria such as methods for interpreting and using data from several sources. In this context, both automatic and manual searches for literature were conducted, resulting in 96 studies related to the design of a BSS being included in this review. The methodology used objectively assesses the research topic in a reliable, repeatable, and replicable manner. It allows us to determine what factors, methods, and data were used in the strategic planning of the BSS design. The review results show that although many solutions to problems have been devised, gaps need to be filled in this research field. This study aims to help researchers detect weaknesses and gaps and open new horizons regarding the BSS long-term design.
In the bicycle-sharing operation network, the mismatch between supply and demand as well as indiscriminate bicycle parking have caused the waste of resources and increased management costs for operators. This study presents design of a bike-sharing electronic fences location developed for Hunan University of Technology and Business. In this paper, we constructed Site Selection Model with Constrained Service Level and use Hybrid Genetic & Annealing algorithm (HGAA) to adjust the location of electronic fences to balance the supply and demand of sharing bicycles with the objective function of minimizing the cost and ensuring the service level, and we use Hunan University of Technology and Industry as an example to verify the effectiveness of the method.
Shared micromobillity has been extensively developed globally in the past few decades, but its impact on the environment remains unclear. This study quantitatively estimates the effects of global shared micromobillity programs on greenhouse gas (GHG) emissions using a life cycle assessment (LCA) perspective. Specifically, it takes major countries and cities around the world as examples to empirically analyze the impact of station-based bike-sharing (SBBS), free-floating bike-sharing (FFBS), free-floating e-bike sharing (FFEBS), and free-floating e-scooter sharing (FFESS) programs on the GHG emissions of urban transportation. The results show that, with the exception of SBBS, the other shared micromobillity programs have not achieved desirable GHG emissions reduction benefits. Contrarily to subjective expectations, although the rapid progress of technology in recent years has promoted the vigorous development of shared micromobility, it has brought negative impacts on the GHG emissions rather than the positive benefits claimed by related promoters and operators. The overcommercialization and low utilization rate makes shared micromobility more likely to be an environmentally-unfriendly mode of transportation. In addition, the regional differences in mode choice, operational efficiency, fleet scale, and market potential of shared micromobility and the corresponding impacts on GHG emissions vary greatly. Therefore, authorities should formulate appropriate shared micromobility plans based on the current conditions and goals of the region. This empirical study helps to better understand the environmental impact of the global shared micromobility program and offers valuable references for improving urban sustainability.
This research has established a set of methods to use the data of existing docked bike sharing system to pre-estimate the emission reduction effects of docked electric bike sharing system that will be built in the future. It extracted demand through the non-homogeneous Poisson process, and used coarse-grained methods and complex network to estimate total riding distance. Tolerance assumptions were given to accurately estimate the emission reduction effect. Compared with the existing threshold assumption, it can better describe the emission reduction caused by the substitution effect. It is found that the emission reduction caused by the substitution effect after upgrading the docked bike sharing system to the docked electric bike sharing system is 4.19 times of the original. While the reduction in emissions caused by its substitution effect on taxis is three times of the original. This contains a huge emission reduction effect. If 1% of the permanent residents of Nanjing change their commuting vehicles from cars to electric bicycles, the one-way emission reduction will exceed 9.55 tonnes of carbon dioxide. This only requires them to tolerate 5 min in average.
Shared micromobility modes have increasingly penetrated the mobility environment of cities in the U.S. and the world over. At the same time, to best integrate these emerging modes within the fabric of the existing (and larger) transportation ecosystem, it is critical to understand how individuals may respond and “who” the likely users of these relatively new modes may be. In this paper, we develop a model to analyze first-use and use frequency of two micromobility modes: E-scooter sharing systems (ESS) and Bike sharing systems (BSS). The model employs psycho-social constructs, built environment attributes, as well as individual-level demographics as determinants. In doing so, we explicitly recognize the role played by awareness/first-use of new technologies as a cognitive antecedent to subsequent frequency decisions. The main data source for this analysis is drawn from a 2019 survey of Austin, Texas area residents. Our results highlight the importance of considering psycho-social attitudes to both gain better insights into the behavioral process leading up to ESS/BSS adoption/use as well as ensure an accurate data fit. In particular, there are distinctive pathways of adoption/use frequency for each of the ESS and BSS modes, but also complementary processes and behavioral spillover effects at play that warrant a joint modeling of the ESS and BSS modes. Our results suggest that addressing safety concerns of micromobility modes should be the top priority of providers and public agencies. Efforts solely directed toward extoling the “green” virtues of micromobility modes is likely to have limited returns.
The free-floating bicycle sharing system (FFBSS) service has been becoming an important and popular mode for travel in the urban mobility ecosystem. Although many studies conducted surveys to understand the usage characteristics of FFBSS service for the general population, few studies focus on the usage behavior of university students. A total of 228 valid responses from Huai’yin Institute of Technology (HYIT) were collected to examine the usage behavior of FFBSS service and identify the key service attributes driving satisfaction levels among Chinese university students. Undergraduate and graduate university students are an important and novel population, as they are still forming their values and beliefs, and therefore are more open to engaging in sustainability efforts (e.g., not owning a car or choices towards green travel modes). Descriptive analysis was performed
to analyze FFBSS service usage frequency, FFBSS trip characteristics, and the motivation to use FFBSS service. The results show that the socio-demographic information (e.g., age, gender, year of study, and monthly expense) and e-bike/bike ownership significantly influence the usage frequency. Time-saving and convenience are two of the main motivations driving FFBSS service usage. Multivariate regression and importance-performance analysis (IPA) are conducted to identify important FFBSS service attributes impacting user satisfaction levels and identify priority service attributes for improvement. It highlights the importance of the density of the designated location for bike returns, the number of available bicycles, the position accuracy of bicycles, and the good functioning
condition of bicycles. The findings provide useful insights into the planning and management of FFBSS services on campus and in cities.
Dockless bike sharing (DBS), as an emerging bike sharing scheme, effectively promotes active travel and improves the mobility of users. Travel behavior analysis of DBS users is a key basis of service improvement, and the data sources include user surveys and trip records. User surveys are widely applied but have the drawback of perceptual errors. Thus, there is a compelling need for exploring travel behavior using automatically-collected trip records. This study examines DBS users' travel frequency and purpose with five semi-annual user surveys and trip record data in Nanjing, China. User surveys reflect user perception of travel behavior, while trip records can be used to calculate actual travel frequency and infer travel purpose. The results show that perceptual travel frequency based on user surveys has a central tendency, and actual travel frequency based on trip records follows a heavy-tailed distribution. Older people tend to underestimate their travel frequency, but other age groups tend to overestimate their frequency. In addition, a dockless bike sharing's travel purpose inferring (DBS-TPI) model is proposed to infer the travel purpose based on trip record data and points of interest data. The DBS-TPI model is reliable and transferable under different scenarios, which could complement user surveys. This study provides insights into improving data collection for better understanding of travel behaviors among DBS users.
Integration between bike sharing and rail transit provides users with a more flexible travel pattern in an effort to address the "first/last mile" problem. This study aims to examine the determinants influencing the ridership of station-based bike sharing (SBBS) and free-floating bike sharing (FFBS) at rail transit stations. The empirical analysis is based on user transaction records of two bike sharing systems in Nanjing, China. We first apply the k-means cluster method to classify rail transit stations into five types according to the temporal profiles of bike sharing usage for rail transit access. Later, ordinary least squares (OLS) and partial least squares (PLS) regression models are developed respectively by differentiating SBBS and FFBS. Compared with the OLS models, PLS models could address the issue of multi-collinearity and generally have better interpretation abilities. The PLS results reveal that the usage of SBBS for rail transit access shares similarities with FFBS. For example, both of them are positively influenced by population density and the number of restaurants. Meanwhile, different types of rail transit stations exhibit different impacts on the ridership of the two bike sharing systems. Our results show that there exists a substitution effect for rail transit access between two bike sharing systems, that is, SBBS may be more frequently used for commuting trips than FFBS. The findings of this study provide a better understanding of the impact of various factors on the SBBS and FFBS ridership at rail transit stations, thereby helping to promote the integration of rail transit and bike sharing systems.
The emergence of dockless bike-sharing services has revolutionised bike-sharing markets in recent years, and the dramatic growth of shared bike fleets in China, as well as their rapid expansion throughout the world, exceeds prior expectations. An understanding of the impacts of these new dockless bike-sharing systems is of vital importance for system operations, transportation and urban planning research. This paper provides a first overview of the emerging literature on implications of dockless bike-sharing systems for users' travel behaviour, user experience, and relevant social impacts of dockless bike-sharing systems. Our review suggests that the dockless design of bike-sharing systems significantly improves users' experiences at the end of their bike trips. Individuals can instantly switch to a dockless shared bike without the responsibility of returning it back to a designated dock. Additionally, the high flexibility and efficiency of dockless bike-sharing often makes the bike-sharing systems' integration with public transit even tighter than that of traditional public bikes, providing an efficient option for first/last-mile trips. The GPS tracking device embedded in each dockless shared bike enables the unprecedented collection of large-scale riding trajectory data, which allow scholars to analyse people's travel behaviour in new ways. Although many studies have investigated travel satisfaction amongst cyclists, there is a lack of knowledge of the satisfaction with bikeshare trips, including both station-based and dockless bikeshare systems. The availability and usage rates of dockless bike-sharing systems implies that they may seriously impact on individuals' subjective well-being by influencing their satisfaction with their travel experiences, health and social participation, which requires further exploration. The impact of dockless bike-sharing on users' access to services and social activities and the related decreases in social exclusion are also relevant issues about which knowledge is lacking. With the increases in popularity of dockless shared bikes in some cities, issues related to the equity and access and the implications for social exclusion and inequality are also raised.
In this paper, we forecast air, road, and train transportation demand for the U.S. domestic market based on econometric and machine learning methodologies. More specifically, we forecast transportation demand for various horizons up to 18 months ahead, for the period 2000:1-2015:03, employing, from the domain of machine learning, a Support Vector Regression (SVR) and from econometrics, the Least Absolute Shrinkage and Selection Operator and the Ordinary Least Squares regression. In doing so, we follow the relevant literature and consider the contribution of selected variables as potential regressors in forecasting. Our empirical findings suggest that while all models outperform the Random Walk benchmark, the machine learning applications adhere more closely to the data generating process, producing more accurate out-of-sample forecasts than the classical econometric models. In most cases, we find that the transportation demand is driven by fuel costs, except for road transportation where macroeconomic conditions affect transportation volumes only for specific forecasting horizons. This finding deviates from the existing literature, given the support of previous studies to macroeconomic conditions are driving factors of transportation demand. Our work relates directly to decisions on transport infrastructure improvement, while it can also be used as a forecasting tool in shaping transportation-oriented policies.
The paper takes station-based bikesharing system (SBS) with docks and dockless free-floating bikesharing system (FBS) as two targets to dig out the relationship between users and use frequency of the services for each scheme, and how the relationship varies from scheme to scheme. To achieve this, studies are carried out focusing on three questions: “who are using these two bicycle services?”; “what are the factors influencing the use frequency of both bicycle systems?”; and “which specific level of the factors influencing the use frequency of both bicycle schemes?” To collect data from users, a survey was designed containing questions for user attributes and service experience and conducted jointly on-line and on-site at four locations with mixed land use in Hangzhou, China. Analysis results show that SBS and FBS have similar user structure but different factors influence use frequency. Based on analysis results, from the user perspective, SBS’s strength is to have good quality with low cost while FBS is more flexible and free to use. Finally, recommendations for SBS are to involve more technology to expand its range to aided bikes for senior citizens and open the access for a mobile renting system, whereas for FBS, it is critical to get government cooperation and for operators to add parking area restrictions into the cellphone application, and create an on-line platform where users can find all the free-floating bike information.
In order to explore the factors affecting users’ behaviors in a free-floating bike sharing (FFBS) system in China, a survey was conducted in Jiangsu province, China in 2017, and the travel characteristics of FFBS users were analyzed. A binary logistic model was applied to quantify the impact of various variables regarding residents’ usage preference based on 30401 valid questionnaires. The findings show that (1) FFBS was mainly used for short-distance travel in cities, especially for commuting and schooling, and the time period of travel in FFBS coincided with the rush-hour in urban areas; (2) a higher level of education, a higher daily transportation cost, the convenience of picking up and parking, and the contribution to users’ health could promote the usage of FFBS, while malfunctioning bicycles and limited regulations were major obstacles restricting the development of FFBS; (3) interestingly, people with high-incomes rather than those with low-incomes showed an inclination for FFBS owing to the charge mode. This research provides empirical evidence to facilitate the formulation of urban transportation policies and to improve the management of FFBS for the operators.
In recent years, free-floating bike sharing (FFBS) has become a significant travel mode to satisfy urban residents' travel demands in China. This paper was designed to better understand the characteristics and influential factors of different travel patterns in FFBS. Firstly, travel patterns were divided into three categories: Origin to Destination Pattern (ODP), Travel Cycle Pattern (TCP) and Transfer Pattern (TP). Then, the characteristics of these patterns were analyzed based on a survey of 4939 valid questionnaires in Nanjing, China. A multinomial logit (MNL) model was established to explore the influential factors associated with the three patterns. The results showed the following. (1) Employees and students were more inclined to choose TP and ODP, and the selection probability of employees was larger than that of students. (2) The evening peak was more significant than the morning peak. (3) Residents with short travel distances were more likely to choose TCP and ODP, and when the travel distance reached 4 km, there was a significant transfer to TP. (4) Price had an impact on residents' travel patterns, with residents showing an inclination toward FFBS when making short distance trips, if they were quickly found. Malfunctioning bicycles were an important factor restricting FFBS development. Several policy recommendations are proposed based on these results, for government and FFBS businesses to improve their management of FFBS systems.
Feature selection can directly ascertain causes of faults by selecting useful features for fault diagnosis, which can simplify the procedures of fault diagnosis. As an efficient feature selection method, the linear kernel support vector machine recursive feature elimination (SVM-RFE) has been successfully applied to fault diagnosis. However, fault diagnosis is not a linear issue. Thus, this paper introduces the Gaussian kernel SVM-RFE to extract nonlinear features for fault diagnosis. The key issue is the selection of the kernel parameter for the Gaussian kernel SVM-RFE. We introduce three classical and simple kernel parameter selection methods and compare them in experiments. The proposed fault diagnosis framework combines the Gaussian kernel SVM-RFE and the SVM classifier, which can improve the performance of fault diagnosis. Experimental results on the Tennessee Eastman process indicate that the proposed framework for fault diagnosis is an advanced technique.
A new generation of bike-sharing services without docking stations is currently revolutionizing the traditional bike-sharing market as it dramatically expands around the world. This study aims at understanding the usage of new dockless bike-sharing services through the lens of Singapore's prevalent service. We collected the GPS data of all dockless bikes from one of the largest bike sharing operators in Singapore for nine consecutive days, for a total of over 14 million records. We adopted spatial autoregressive models to analyze the spatiotemporal patterns of bike usage during the study period. The models explored the impact of bike fleet size, surrounding built environment, access to public transportation, bicycle infrastructure, and weather conditions on the usage of dockless bikes. Larger bike fleet is associated with higher usage but with diminishing marginal impact. In addition, high land use mixtures, easy access to public transportation, more supportive cycling facilities, and free-ride promotions positively impact the usage of dockless bikes. The negative influence of rainfall and high temperatures on bike utilization is also exhibited. The study also offered some guidance to urban planners, policy makers, and transportation practitioners who wish to promote bike-sharing service while ensuring its sustainability.
As urban populations grow, there is a growing need for efficient and sustainable modes, such as bicycling. Unfortunately, the lack of bicycle demand data stands as a barrier to design, planning, and research efforts in bicycle transportation. Estimating bicycle demand is difficult not only due to limited count data, but to the fact that bicyclists are highly responsive to a multitude of factors, particularly seasonal weather. Current estimation methods capable of accurately adjusting for seasonal demand change often require substantial data for ongoing calibration. This makes it difficult or impossible to utilize those methods in locations with minimal continuous count data. This research aims to help mitigate this challenge by developing an estimation method using sinusoidal model to fit the typical pattern of seasonal bicycle demand. This sinusoidal model requires only a single calibration factor to adjust for scale of seasonal demand change and is capable of estimating monthly average daily bicycle counts and average annual daily bicycle counts . This calibration factor can be established using a minimum of two short-term counts to represent the maximum and minimum monthly MADB in summer and winter. To develop the model, this research use data from bike-share systems in four cities and 47 permanent bicycle counters in six cities. Although this model is not suitable for locations with mild or atypical seasons, it successfully models MADB and serves as a useful alternative or supportive estimation method in locations where minimal demand data exist.
China leads the world in both public bikeshare and private electric bike (e-bike) growth. Current trajectories indicate the viability of deploying large-scale shared e-bike (e-bikeshare) systems in China. We employ a stated preference survey and multinomial logit to model the factors influencing the choice to switch from an existing transportation mode to bikeshare or e-bikeshare in Beijing. Demand is influenced by distinct sets of factors: the bikeshare choice is most sensitive to measures of effort and comfort while the e-bikeshare choice is more sensitive to user heterogeneities. Bikeshare demand is strongly negatively impacted by trip distance, temperature, precipitation, and poor air quality. User demographics however do not factor strongly on the bikeshare choice, indicating the mode will draw users from across the social spectrum. The e-bikeshare choice is much more tolerant of trip distance, high temperatures and poor air quality, though precipitation is also a highly negative factor. User demographics do play a significant role in e-bikeshare demand. Analysis of impact to the existing transportation system finds that both bikeshare and e-bikeshare will tend to draw users away from the “unsheltered modes”, walk, bike, and e-bike. Although it is unclear if shared bikes are an attractive “first-and-last-mile solution”, it is clear that e-bikeshare is attractive as a bus replacement.
Bike Share Toronto is Canada’s second largest public bike share system. It provides a unique case study as it is one of the few bike share programs located in a relatively cold North American setting, yet operates throughout the entire year. Using year-round historical trip data, this study analyzes the factors affecting Toronto’s bike share ridership. A comprehensive spatial analysis provides meaningful insights on the influences of socio-demographic attributes, land use and built environment, as well as different weather measures on bike share ridership. Empirical models also reveal significant effects of road network configuration (intersection density and spatial dispersion of stations) on bike sharing demands. The effect of bike infrastructure (bike lane, paths etc.) is also found to be crucial in increasing bike sharing demand. Temporal changes in bike share trip making behavior were also investigated using a multilevel framework. The study reveals a significant correlation between temperature, land use and bike share trip activity. The findings of the paper can be translated to guidelines with the aim of increasing bike share activity in urban centers.
The purpose of this research is to identify correlates of bike station activity for Nice Ride Minnesota, a bike share system in the Minneapolis-St. Paul Metropolitan Area in Minnesota. The number of trips to and from each of the 116 bike share stations operating in 2011 was obtained from Nice Ride Minnesota. Data for independent variables included in the proposed models come from a variety of sources, including the 2010 U.S. Census; the Metropolitan Council, a regional planning agency; and the Cities of Minneapolis and St. Paul. Log-linear and negative binomial regression models are used to evaluate the marginal effects of these factors on average daily station trips. The models have high goodness of fit, and each of 13 independent variables is significant at the 10% level or higher. The number of trips at Nice Ride stations is associated with neighborhood sociodemographics (i.e., age and race), proximity to the central business district, proximity to water, accessibility to trails, distance to other bike share stations, and measures of economic activity. Analysts can use these results to optimize bike share operations, locate new stations, and evaluate the potential of new bike share programs.
Recently, support vector machine (SVM) has excellent performance on classification and prediction and is widely used on disease diagnosis or medical assistance. However, SVM only functions well on two-group classification problems. This study combines feature selection and SVM recursive feature elimination (SVM-RFE) to investigate the classification accuracy of multiclass problems for Dermatology and Zoo databases. Dermatology dataset contains 33 feature variables, 1 class variable, and 366 testing instances; and the Zoo dataset contains 16 feature variables, 1 class variable, and 101 testing instances. The feature variables in the two datasets were sorted in descending order by explanatory power, and different feature sets were selected by SVM-RFE to explore classification accuracy. Meanwhile, Taguchi method was jointly combined with SVM classifier in order to optimize parameters C and γ to increase classification accuracy for multiclass classification. The experimental results show that the classification accuracy can be more than 95% after SVM-RFE feature selection and Taguchi parameter optimization for Dermatology and Zoo databases.
Since the mid-2000s, public bikesharing (also known as “bike hire”) has developed and spread into a new form of mobility in cities across the globe. This paper presents an analysis of the recent increase in the number of public bikesharing systems. Bikesharing is the shared use of a bicycle fleet, which is accessible to the public and serves as a form of public transportation. The initial system designs were pioneered in Europe and, after a series of technological innovations, appear to have matured into a system experiencing widespread adoption. There are also signs that the policy of public bikesharing systems is transferable and is being adopted in other contexts outside Europe. In public policy, the technologies that are transferred can be policies, technologies, ideals or systems. This paper seeks to describe the nature of these systems, how they have spread in time and space, how they have matured in different contexts, and why they have been adopted.
As a pinnacle of green transportation with transit attributes, bikesharing has become particularly popular since the mid-2000s. Two crucial questions for the success of bikesharing adoption are how many riders can bikesharing attract, and what influences its effectiveness. To shed light on answers to these questions, this paper models the impacts of urban features and system characteristics on bikesharing daily use and turnover rate, using data constructed on 69 bikesharing systems in China. Prior to modeling, we provide an overview of bikesharing adoption in China, describing why they have been adopted, how they have matured, and how they have expanded. Results from data regression and comparison indicate that bikesharing ridership and turnover rate tend to increase with urban population, government expenditure, the number of bikesharing members and docking stations, whilst the number of public bikes shows significant but adverse signs in impacting bikesharing ridership and turnover rate. Data comparison shows that, to pursue an ideal bikesharing turnover rate in most Chinese cities, the bike-member (supply-demand) ratio should be better controlled within 0.2. Moreover, this study suggests that personal credit cards (allowing bikesharing members to pay “personal credit” rather than money if they do not return public bikes within the free use hours) and universal cards (integrating bikesharing systems into other urban transit systems through the use of a rechargeable smart card that can cover a range of payments and trips) can significantly raise bikesharing daily use and turnover rate. We recommend that bikesharing operators and transit agencies take the supply-demand thresholds and the adoption of personal credit cards and universal cards into consideration in the future bikesharing operation and development policy.
Growing concerns over global motorization and climate change have led to increasing interest in sustainable transportation alternatives, such as bikesharing (the shared use of a bicycle fleet). Since 1965, bikesharing has grown across the globe on four continents including: Europe, North America, South America, and Asia (including Australia). Today, there are approximately 100 bikesharing programs operating in an estimated 125 cities around the world with over 139,300 bicycles. Bikesharing’s evolution is categorized into three generations: 1) White Bikes (or Free Bike Systems); 2) Coin-Deposit Systems; and 3) IT-Based Systems. In this paper, the authors propose a fourth-generation: “Demand-Responsive, Multi-Modal Systems.†A range of existing bikesharing business models (e.g., advertising) and lessons learned are discussed including: 1) bicycle theft and vandalism; 2) bicycle redistribution; 3) information systems (e.g., real-time information); 4) insurance and liability concerns; and 5) pre-launch considerations. While limited in number, several studies have documented bikesharing’s social and environmental benefits including reduced auto use, increased bicycle use, and a growing awareness of bikesharing as a daily mobility option. Despite bikesharing’s ongoing growth, obstacles and uncertainty remain, including: future demand; safety; sustainability of business models; limited cycling infrastructure; challenges to integrating with public transportation systems; technology costs; and user convenience (e.g., limited height adjustment on bicycles, lack of cargo space, and exposure to weather conditions). In the future, more research is needed to better understand bikesharing’s impacts, operations, and business models in light of its reported growth and benefits.
This study attempts to evaluate the injury risk of pedestrian casualties in traffic crashes and to explore the factors that contribute to mortality and severe injury, using the comprehensive historical crash record that is maintained by the Hong Kong Transport Department. The injury, demographic, crash, environmental, geometric, and traffic characteristics of 73,746 pedestrian casualties that were involved in traffic crashes from 1991 to 2004 are considered. Binary logistic regression is used to determine the associations between the probability of fatality and severe injury and all contributory factors. A consideration of the influence of implicit attributes on the trend of pedestrian injury risk, temporal confounding, and interaction effects is progressively incorporated into the predictive model. To verify the goodness-of-fit of the proposed model, the Hosmer-Lemeshow test and logistic regression diagnostics are conducted. It is revealed that there is a decreasing trend in pedestrian injury risk, controlling for the influences of demographic, road environment, and other risk factors. In addition, the influences of pedestrian behavior, traffic congestion, and junction type on pedestrian injury risk are subject to temporal variation.
High levels of car dependence have caused tremendous challenges for sustainable transport development. Transport planners, therefore, seek ways of replacing motor vehicles, as well as increasing the proportion of active travel. The bike-sharing scheme can be seen as an effective way of doing so, particularly in Asian cities. The aim of this paper is to investigate users’ perspectives on the development of bike-sharing using Shanghai as an example. Semi-structured interviews are used to examine the main factors motivating and impeding the development of the bike-sharing scheme in Shanghai. Our findings show that convenience, saving time and financial savings are the major motivations; whereas problems with bicycles being poorly maintained and abused by users, operational issues, financial issues and an unsuitable business model are the major obstacles. In addition, the findings also suggest that a public and private partnership could be the best option for running a sustainable bike-sharing scheme with clear areas of responsibility. Financial incentives, a bicycle-friendly infrastructure, regular operational management and supportive policies should be prioritised. In order to achieve the targets set by the Shanghai Master Plan 2035, transport planners and policymakers should integrate the bike-sharing scheme within the wider active travel system.
Shared micromobility – the shared use of bicycles, scooters, or other low-speed modes – is an innovative transportation strategy growing across the United States that includes various service models such as docked, dockless, and e-bike service models. This research focuses on understanding how docked bikesharing and dockless e-bikesharing models complement and compete with respect to user travel behaviors. To inform our analysis, we used two datasets from February 2018 of Ford GoBike (docked) and JUMP (dockless electric) bikesharing trips in San Francisco. We employed three methodological approaches: 1) travel behavior analysis, 2) discrete choice analysis with a destination choice model, and 3) geospatial suitability analysis based on the Spatial Temporal Economic Physiological Social (STEPS) to Transportation Equity framework. We found that dockless e-bikesharing trips were longer in distance and duration than docked trips. The average JUMP trip was about a third longer in distance and about twice as long in duration than the average GoBike trip. JUMP users were far less sensitive to estimated total elevation gain than were GoBike users, making trips with total elevation gain about three times larger than those of GoBike users, on average. The JUMP system achieved greater usage rates than GoBike, with 0.8 more daily trips per bike and 2.3 more miles traveled on each bike per day, on average. The destination choice model results suggest that JUMP users traveled to lower-density destinations, and GoBike users were largely traveling to dense employment areas. Bike rack density was a significant positive factor for JUMP users. The location of GoBike docking stations may attract users and/or be well-placed to the destination preferences of users. The STEPS-based bikeability analysis revealed opportunities for the expansion of both bikesharing systems in areas of the city where high-job density and bike facility availability converge with older resident populations.
Free-floating bikesharing (FFBS) is a fairly new mobility service. It spread rapidly throughout Europe’s major urban areas in 2017; a development accompanied by a variety of problems that soon culminated in a retreat of providers from most cities. The main characteristic of FFBS is the absence of fixed docking stations; instead, users can borrow and leave the bikes wherever they want as long as they adhere to traffic rules and the operators’ regulations. Its market entry has caused controversial public debates, although – or even because – little is known about this new mobility service, its users, their motivators as well as usage patterns. One of the FFBS pioneer cities in Europe was Vienna with two FFBS operators providing their services from summer 2017 onwards. Although both withdrew from the city within a year, it was possible to collect and analyse user data in order to gain an understanding of the factors supporting FFBS usage. For this purpose, the research uses a series of discrete choice models explaining why some people (i) share bikes (including FFBS and the established Viennese station-based scheme), (ii) try out the new FFBS scheme and (iii) remain with the new FFBS scheme or quit the membership. Reasons for users to try FFBS are very similar to those of station-based bikesharing as reported in literature. Subjective factors including attitudes and degree of satisfaction with system features are gaining in importance within the series of models. They are particularly decisive for remaining with the FFBS scheme.
In recent years, free-floating bike sharing (FFBS) has been rapidly promoted in China, attracting numerous users and consuming many resources. The extensive supply and inefficient repositioning of FFBS are challenges for sustainable development, and put forward higher requirements for parking planning. This paper estimates the parking demand of all three FFBS companies by combining the journey data of Mobike in Nanjing and the Nanjing FFBS bike survey. Three clustering methods were applied to determine the virtual stations of bike aggregation. The maximum number of bikes in a day is recognized as the parking demand in each virtual station. The results show that more than half of bikes are in low turnover rate, and the management of FFBS should be improved. The K-means method turns out to observe the best clustering result for determining virtual stations. The demand for parking spaces of all FFBS companies in Nanjing is estimated accordingly. In addition, the relations of bicycle supply, repositioning and parking are discussed, showing the impact of parking demand on greenhouse gas (GHG) emissions. The research could help to propose an appropriate plan for meeting FFBS parking demand, and have enlightening sight of emissions reduction and sustainable development in the FFBS services.
The recent boom of sharing economy along with its technological underpinnings have brought new opportunities to urban transport ecosystems. Today, a new mobility option that provides station-less bike rental services is emerging. While previous studies mainly focus on analyzing station-based systems, little is known about how this new mobility service is used in cities. This research proposes an analytical framework to unravel the landscape and pulses of cycling activities from a dockless bike-sharing system. Using a four-month GPS dataset collected from a major bike-sharing operator in Singapore, we reconstruct the temporal usage patterns of shared bikes at different places and apply an eigendecomposition approach to uncover their hidden structures. Several key built environment indicators are then derived and correlated with bicycle usage patterns. According to the analysis results, cycling activities on weekdays possess a variety of temporal profiles at both trip origins and destinations, highlighting substantial variations of bicycle usage across urban locations. Strikingly, a significant proportion of these variations is explained by the cycling activeness in the early morning. On weekends, the overall variations are much smaller, indicating a more uniform distribution of temporal patterns across the city. The correlation analysis reveals the role of shared bikes in facilitating the first- and last-mile trips, while the contribution of the latter (last-mile) is observed to a limited extent. Some built environment indicators, such as residential density, commercial density, and number of road intersections, are correlated with the temporal usage patterns. While others, such as land use mixture and length of cycling path, seem to have less impact. The study demonstrates the effectiveness of eigendecomposition for uncovering the system dynamics. The workflow developed in this research can be applied in other cities to understand this new-generation system as well as the implications for urban design and transport planning.
This paper discusses the development of shared bike programs in China, especially the innovative dockless bikeshare (DBS) system, using up-to-date empirical analysis. Bicycle sharing programs had existed in China since 2008 but overall bicycle mode share decreased until 2016 when DBS emerged. A comparison of classical city docked bikeshare (BS) programs found that government-oriented operators and a low financial threshold for users were the keys to the success of docked BS in China. In less than two years, a new, innovative, flexible, shared bicycling system – the DBS – has grown from nothing to a substantial 23 million fleets, covering over 200 cities and regions, making docked BS appear insignificant. It is a highly capital-driven, privately-operated business model, largely deployed in cities in conjunction with urban railway systems and has achieved high penetration in mega cites (e.g., 0.135 fleet/resident in Beijing). The development of DBS has experienced “free growth”, “regulated” and “limited” phases in a short time. While the central government initially held a “neutral-positive” policy towards this new system, the rapid expansion of dockless fleets soon exceeded cities’ limits and resulted in local government policies changing from “neutral-positive” to “neutral-negative”, and from August 2017, forceful limiting regulations have been implemented. DBS systems have advantages such as easy access using a smart phone, convenience of pickup and park and low cost. These merits attract its main users, who are found to be young, highly educated with almost equal numbers of males and females. DBS trips are mainly short, with high frequency and used for commuting purposes. DBS systems have burgeoned due to three factors: (1) those promoting user demands, (2) those winning partial support of government, and (3) those promoting operators’ supply. The results show that rapid growth of dockless bikeshare programs is mainly “supply-driven by operators” rather than by “user demand” or “triggered by government policy”. Financial sustainability, vandalism and threat to bicycle industry by DBS are the three main challenges that require investigation, especially, the fact that the booming DBS market may cause low profitability for local bicycle manufacturers and thus make the entire industry fragile. Feasibility of docked bikeshare and dockless bikeshare are compared and concluded in the end.
The analysis of travel mode choice is important in transportation planning and policy-making in order to understand and forecast travel demands. Research in the field of machine learning has been exploring the use of random forest as a framework within which many traffic and transport problems can be investigated. The random forest (RF) is a powerful method for constructing an ensemble of random decision trees. It de-correlates the decision trees in the ensemble via randomization that leads to an improvement of forecasting and reduces the variance when averaged over the trees. However, the usefulness of RF for travel mode choice behavior remains largely unexplored. This paper proposes a robust random forest method to analyze travel mode choices for examining the prediction capability and model interpretability. Using the travel diary data from Nanjing, China in 2013, enriched with variables on the built environment, the effects of different model parameters on the prediction performance are investigated. The comparison results show that the random forest method performs significantly better in travel mode choice prediction for higher accuracy and less computation cost. In addition, the proposed method estimates the relative importance of explanatory variables and how they relate to mode choices. This is fundamental for a better understanding and effective modeling of people's travel behavior.
The station-free sharing bike is a new sharing traffic mode that has been deployed in a large scale in China in the early 2017. Without docking stations, this system allows the sharing bike to be parked in any proper places. This study aimed to develop a dynamic demand forecasting model for station-free bike sharing using the deep learning approach. The spatial and temporal analyses were first conducted to investigate the mobility pattern of the station-free bike sharing. The result indicates the imbalanced spatial and temporal demand of bike sharing trips. The long short-term memory neural networks (LSTM NNs) were then developed to predict the bike sharing trip production and attraction at TAZ for different time intervals, including the 10-min, 15-min, 20-min and 30-min intervals. The validation results suggested that the developed LSTM NNs have reasonable good prediction accuracy in trip productions and attractions for different time intervals. The statistical models and recently developed machine learning methods were also developed to benchmark the LSTM NN. The comparison results suggested that the LSTM NNs provide better prediction accuracy than both conventional statistical models and advanced machine learning methods for different time intervals. The developed LSTM NNs can be used to predict the gap between the inflow and outflow of the sharing bike trips at a TAZ, which provide useful information for rebalancing the sharing bike in the system.
The real-time and accurate prediction of road traffic states is the basis of information service for road traffic participants. An algorithm based on Kernel K-nearest neighbors (Kernel-KNN) is presented to predict road traffic states in time series in this paper. First, representative road traffic state data are extracted to build the road traffic running characteristics reference sequences (RTRCRS). Then, kernel function of the road traffic state data sequence in time series is constructed. The current and referenced road traffic state data sequences are matched, based on which k nearest referenced road traffic states are selected and the road traffic states are predicted. Several typical road links in Beijing are considered for a series of case studies. The final experiments results prove that the road traffic states prediction approach based on Kernel-KNN presented herein is feasible and can achieve a high level of accuracy.
Low-income commuters have distinct activity-travel characteristics from non-low-income commuters. This study examines low-income commuters’ activity-travel pattern for a better understanding the mechanism of activity participation and travel behaviour based on the travel survey data collected in Nanjing, China. Structural equations modelling (SEM) methodology was adopted to estimate the complex relationships among socio-demographics, accessibility, activity participation, trip generation and mode choice. Results show that strong relationships do exist among socio-demographics, activity engagement and travel behavior. Specifically, we can understand travel behaviour better by including activity participation endogenously in the model. Furthermore, it allows us to better forecast how increasing any one type of activity will affect demand for other activities, as well as trip generation and mode choice. Lastly, the results reveal the effects of accessibility variables on activity participation and travel behaviour in which population density measure has more ubiquitous effects. Findings in this study might provide insightful policy implications for improving the travel environment of the low-income commuters.
Public Bike Sharing Systems provide a progressive option for urban mobility, not only for commuters but also for spontaneous users and tourists. Such systems are only reasonable, if the bikes are available where the users need them at a certain time though. In so-called free-floating systems as it's implemented in Munich, the user is allowed to rent and return a bike within a clearly defined operating area. However, on one hand there are zones, where a shortage of returned bikes occurs. No bikes are available but needed there. On the other hand there are zones, where too many bikes were returned but the demand for renting a bike there is too low. Based on a detailed GPS-Data Analysis for the bike sharing system, mobility patterns of the usage were identified. Depending on different factors like weather conditions, time of the day and holidays/weekends, a demand model was created in order to obtain an optimal distribution of bikes within the operating area. At the end of this paper an application of an operater-based relocation strategy is given. By relocating at least some part of the fleet, it's ensured that the demand for bikes is optimally satisfied in time and space.
This study investigated the effects on bikesharing ridership levels of demographic and built environment characteristics near bikesharing stations in three operational U.S. systems. Although earlier studies focused on the analysis of a single system, the increasing availability of station-level ridership data has created the opportunity to compare experiences across systems. In this study, particular attention was paid to data quality and consistency issues raised by a multicity analysis. This project also expanded on earlier studies with the inclusion of the network effects of the size and spatial distribution of the bikesharing station network, which contributed to a more robust regression model for the prediction of station ridership. The regression analysis identified a number of variables that had statistically significant correlations with station-level bikesharing ridership: population density; retail job density; bike, walk, and transit commuters; median income; education; presence of bikeways; nonwhite population (negative association); days of precipitation (negative association); and proximity to a network of other bikesharing stations. Proximity to a greater number of other bikesharing stations exhibited a strong positive correlation with ridership in a variety of model specifications. This finding suggested that, with the other demographic and built environment variables controlled for, access to a comprehensive network of stations was a critical factor to support ridership. Compared with earlier models, this model is more widely applicable to a diverse range of communities and can help those interested in the adoption of bikesharing systems to predict potential levels of ridership and to identify station locations that serve the greatest number of riders.
Installed in 2009, BIXI is the first major public bicycle-sharing system in Montreal, Canada. The BIXI system has been a success, accounting for more than one million trips annually. This success has increased the interest in exploring the factors affecting bicycle-sharing flows and usage. Using data compiled as minute-by-minute readings of bicycle availability at all the stations of the BIXI system between April and August 2012, this study contributes to the literature on bicycle-sharing. We examine the influence of meteorological data, temporal characteristics, bicycle infrastructure, land use and built environment attributes on arrival and departure flows at the station level using a multilevel approach to statistical modeling, which could easily be applied to other regions. The findings allow us to identify factors contributing to increased usage of bicycle-sharing in Montreal and to provide recommendations pertaining to station size and location decisions. The developed methodology and findings can be of benefit to city planners and engineers who are designing or modifying bicycle-sharing systems with the goal of maximizing usage and availability.
This paper discusses the history of bike-sharing from the early 1st generation program to present day rd generation programs. Included are a detailed examination of models of provision, with benefits and detriments of each, and a description of capital and operating costs. The paper concludes with a look into the future through discussion about what a th generation bike-sharing program could be.
Real-time crash risk evaluation models will likely play a key role in Active Traffic Management (ATM). Models have been developed to predict crash occurrence in order to proactively improve traffic safety. Previous real-time crash risk evaluation studies mainly employed logistic regression and neural network models which have a linear functional form and over-fitting drawbacks, respectively. Moreover, these studies mostly focused on estimating the models but barely investigated the models' predictive abilities. In this study, support vector machine (SVM), a recently proposed statistical learning model was introduced to evaluate real-time crash risk. The data has been split into a training dataset (used for developing the models) and scoring datasets (meant for assessing the models' predictive power). Classification and regression tree (CART) model has been developed to select the most important explanatory variables and based on the results, three candidates Bayesian logistic regression models have been estimated with accounting for different levels unobserved heterogeneity. Then SVM models with different kernel functions have been developed and compared to the Bayesian logistic regression model. Model comparisons based on areas under the ROC curve (AUC) demonstrated that the SVM model with Radial-basis kernel function outperformed the others. Moreover, several extension analyses have been conducted to evaluate the effect of sample size on SVM models' predictive capability; the importance of variable selection before developing SVM models; and the effect of the explanatory variables in the SVM models. Results indicate that (1) smaller sample size would enhance the SVM model's classification accuracy, (2) variable selection procedure is needed prior to the SVM model estimation, and (3) explanatory variables have identical effects on crash occurrence for the SVM models and logistic regression models.
Selecting relevant features for support vector machine (SVM) classifiers is important for a variety of reasons such as generalization performance, computational efficiency, and feature interpretability. Traditional SVM approaches to feature selection typically extract features and learn SVM parameters independently. Independently performing these two steps might result in a loss of information related to the classification process. This paper proposes a convex energy-based framework to jointly perform feature selection and SVM parameter learning for linear and non-linear kernels. Experiments on various databases show significant reduction of features used while maintaining classification performance.
DNA micro-arrays now permit scientists to screen thousands of genes simultaneously and determine whether those genes are active, hyperactive or silent in normal or cancerous tissue. Because these new micro-array devices generate bewildering amounts of raw data, new analytical methods must be developed to sort out whether cancer tissues have distinctive signatures of gene expression over normal tissues or other types of cancer tissues.
In this paper, we address the problem of selection of a small subset of genes from broad patterns of gene expression data, recorded on DNA micro-arrays. Using available training examples from cancer and normal patients, we build a classifier suitable for genetic diagnosis, as well as drug discovery. Previous attempts to address this problem select genes with correlation techniques. We propose a new method of gene selection utilizing Support Vector Machine methods based on Recursive Feature Elimination (RFE). We demonstrate experimentally that the genes selected by our techniques yield better classification performance and are biologically relevant to cancer.
In contrast with the baseline method, our method eliminates gene redundancy automatically and yields better and more compact gene subsets. In patients with leukemia our method discovered 2 genes that yield zero leave-one-out error, while 64 genes are necessary for the baseline method to get the best result (one leave-one-out error). In the colon cancer database, using only 4 genes our method is 98% accurate, while the baseline method is only 86% accurate.
Breast cancer is the second largest cause of cancer deaths among women. At the same time, it is also among the most curable cancer types if it can be diagnosed early. Research efforts have reported with increasing confirmation that the support vector machines (SVM) have greater accurate diagnosis ability. In this paper, breast cancer diagnosis based on a SVM-based method combined with feature selection has been proposed. Experiments have been conducted on different training-test partitions of the Wisconsin breast cancer dataset (WBCD), which is commonly used among researchers who use machine learning methods for breast cancer diagnosis. The performance of the method is evaluated using classification accuracy, sensitivity, specificity, positive and negative predictive values, receiver operating characteristic (ROC) curves and confusion matrix. The results show that the highest classification accuracy (99.51%) is obtained for the SVM model that contains five features, and this is very promising compared to the previously reported results.
Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning community over the past decade, and this book provides a long-needed systematic and unified treatment of theoretical and practical aspects of GPs in machine learning. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics. The book deals with the supervised-learning problem for both regression and classification, and includes detailed algorithms. A wide variety of covariance (kernel) functions are presented and their properties discussed. Model selection is discussed both from a Bayesian and a classical perspective. Many connections to other well-known techniques from machine learning and statistics are discussed, including support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Theoretical issues including learning curves and the PAC-Bayesian framework are treated, and several approximation methods for learning with large datasets are discussed. The book contains illustrative examples and exercises, and code and datasets are available on the Web. Appendixes provide mathematical background and a discussion of Gaussian Markov processes.
Bike lanes and other determinants of capital bikeshare trips
- D Buck
- R Buehler
Buck, D., Buehler, R., 2012. Bike lanes and other determinants of capital bikeshare trips.
In: Paper Presented at the 91 st Transportation Research Board Annual Meeting,
Washington D.C., USA.
A deep reinforcement learning framework for rebalancing dockless bike sharing systems
- L Pan
- Q Cai
- Z Fang
- P Tang
- L Huang
Pan, L., Cai, Q., Fang, Z., Tang, P., Huang, L., 2019. A deep reinforcement learning
framework for rebalancing dockless bike sharing systems. In: Proceedings of the 33 rd
AAAI Conference on Artificial Intelligence, Honolulu, USA.