A Hierarchical Demand Prediction Method with Station Clustering for Bike Sharing System

Feng, Sijia; Chen, Hao; Chun, Du; Li, Jun; Jing, Ning

doi:10.1109/dsc.2018.00133

Cited by 31 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This approach may fail in situations where clusters are non-convex and there are physical barriers such as rivers. For this reason, the authors in [ 21 ] processed data collected from the New York City Bike System and proposed a spectral clustering algorithm that operates in conjunction with a label propagation algorithm, which controls the geographical extension of the obtained clusters. According to the obtained results, it seems that imposing geographical proximity as a requirement for clustering somehow fades the information regarding the actual behaviour shown at docking stations.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing

Díaz

Pozo

González

et al. 2020

Sensors

View full text Add to dashboard Cite

Bicycle sharing systems (BSSs) have established a new shared-economy mobility model. After a rapid growth they are evolving into a fully-functional mobile sensor platform for cities. The viability of BSSs is floored by their operational costs, mainly due to rebalancing operations. Rebalancing implies transporting bicycles to and from docking stations in order to guarantee the service. Rebalancing performs clustering to group docking stations by behaviour and proximity. In this paper we propose a Hierarchical Agglomerative Clustering based on an Ultra-Light Edge Computing Algorithm (HAC-ULECA). We eliminate the proximity and let Hierarchical Agglomerative Clustering (HAC) focus on behaviour. Behaviour is represented by ULECA as an activity profile based on the net flow of arrivals and departures in a docking station. This drastically reduces the computing requirements which allows ULECA to run as an edge computing functionality embedded into the physical layer of the Internet of Shared Bikes (IoSB) architecture. We have applied HAC-ULECA to real data from BiciMAD, the public BSS in Madrid (Spain). Our results, presented as dendograms, graphs, geographical maps, and colour maps, show that HAC-ULECA is capable of separating behaviour profiles related to business and residential areas and extracting meaningful spatio-temporal information about the BSS and the city’s mobility.

show abstract

Section: Related Workmentioning

confidence: 99%

Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing

Díaz

Pozo

González

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…More than half of the listed papers take into account user demand characteristics (e.g., gender, age and population density) and mobility patterns [21,23,30,31,37,42]. These data are usually difficult to estimate in a design phase and to obtain when the BSS is operational.…”

Section: Input Datamentioning

confidence: 99%

Attractiveness of Bike-Sharing Stations from a Multi-Modal Perspective: The Role of Objective and Subjective Features

Nogal

Jiménez

2020

Sustainability

View full text Add to dashboard Cite

When analysing the performance of bike-sharing scheme (BSS) stations, it is common to find stations that are located in specific points that capture the interest of users, whereas nearby stations are clearly underused. This uneven behaviour is not totally understood. This paper discusses the potential factors influencing station attractiveness, supported by the related literature on cyclists’ and pedestrians’ preferences and the characteristics of the stations themselves. The existing literature addresses these topics independently, while this work unites them by proposing a non data-extensive methodology that allows the attractiveness of BSS stations to be assessed. Attractiveness in this context is understood as the set of physical, environmental and service-related features of a bike station that make it more appealing for BSS users than nearby stations. Special attention is paid to differentiating objective features, based on facts, from subjective features, those influenced by personal perceptions. This classification becomes important in this context because subjective aspects can change from one geographical location to another, making the findings related to these aspects difficult to apply to other regions. Moreover, the assessment of the stations’ levels of safety and security is included. Thus, the proposed measure of attractiveness of BSS stations provides a balanced overview of several features. The consideration of station attractiveness when designing BSS layouts will help to refine the design of new layouts and will assist in conducting an appropriate diagnostic evaluation of the existing ones. This tool will allow urban and transportation planners to reduce re-balancing costs and to maximise user satisfaction at a low cost, which have a direct impact on improving the urban sustainability. The proposed method is applied to the Dublin bike sharing scheme, Dublinbikes, with good performance results.

show abstract

“…Here are some examples of the former type: support vector regression (SVR) methods for traffic flow predictions [8][9][10], gradient boosting regression tree (GBRT) and multi-similarity-based inference models for bike-sharing demand forecasting [11,12], ensemble framework with time-varying Poisson models and the auto-regressive integrated moving average (ARIMA) model for taxi-passenger demand forecasting [13]. For multi-output models, some examples include: the probabilistic graphical models (PGM)-based hybrid framework for citywide traffic volume estimation [14], intrinsic Gaussian Markov random field (IGMRF) model, one of the PGM models with cluster-based adjustment for cluster-level crowd flow forecast [1], vector auto-regressive moving average (VARMA) with a spatio-temporal correlations matrix for real-time traffic predictions [15], ν-SVR (the modified multi-output SVR (M-SVR) method) for traffic speed predictions in large road networks [16], deep spatio-temporal residual networks (with convolutional neural network (CNNs) as kernels) for region-level crowd flow predictions [2], and multi-graph convolutional networks for station-level bike flow predictions [17].…”

Section: Introductionmentioning

confidence: 99%

Large-Scale Station-Level Crowd Flow Forecast with ST-Unet

Zhou

Chen

et al. 2019

IJGI

Self Cite

View full text Add to dashboard Cite

High crowd mobility is a characteristic of transportation hubs such as metro/bus/bike stations in cities worldwide. Forecasting the crowd flow for such places, known as station-level crowd flow forecast (SLCFF) in this paper, would have many benefits, for example traffic management and public safety. Concretely, SLCFF predicts the number of people that will arrive at or depart from stations in a given period. However, one challenge is that the crowd flows across hundreds of stations irregularly scattered throughout a city are affected by complicated spatio-temporal events. Additionally, some external factors such as weather conditions or holidays may change the crowd flow tremendously. In this paper, a spatio-temporal U-shape network model (ST-Unet) for SLCFF is proposed. It is a neural network-based multi-output regression model, handling hundreds of target variables, i.e., all stations’ in and out flows. ST-Unet emphasizes stations’ spatial dependence by integrating the crowd flow information from neighboring stations and the cluster it belongs to after hierarchical clustering. It learns the temporal dependence by modeling the temporal closeness, period, and trend of crowd flows. With proper modifications on the network structure, ST-Unet is easily trained and has reliable convergency. Experiments on four real-world datasets were carried out to verify the proposed method’s performance and the results show that ST-Unet outperforms seven baselines in terms of SLCFF.

show abstract

A Hierarchical Demand Prediction Method with Station Clustering for Bike Sharing System

Cited by 31 publications

References 12 publications

Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing

Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing

Attractiveness of Bike-Sharing Stations from a Multi-Modal Perspective: The Role of Objective and Subjective Features

Large-Scale Station-Level Crowd Flow Forecast with ST-Unet

Contact Info

Product

Resources

About