Exploring human mobility with multi-source data at extremely large metropolitan scales

Stankovic, John A.; Huang, Jun; Li, Ye; Zhang, Fan; Xu, Cheng‐Zhong; He, Tian

doi:10.1145/2639108.2639116

Cited by 137 publications

(66 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One intuitive idea is to improve the existing models by integrating bike-sharing data. In [15], authors have demonstrated the reduced bias of mobility modeling by exploiting the inherent diversities from multi-source data (i.e., taxi, bus, subway and smartphone CDR).…”

Section: Mobility Model Fusion With Multi-source Datamentioning

confidence: 99%

“…In addition to bike-sharing data, researchers analyzed human mobility based on other empirical data from taxicabs [36], buses [37], subways [38], private cars [39], WiFi APs [40,41], cellular carriers [15,42] and social networks [43]. Due to the unique intrinsic properties such as the decentralized structure, ondemand usage and unattended vehicles in BSS, our work provides a fundamentally different model from these designs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Mobility Modeling and Prediction in Bike-Sharing Systems

Yang

Shu

et al. 2016

Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services

155

View full text Add to dashboard Cite

As an innovative mobility strategy, public bike-sharing has grown dramatically worldwide. Though providing convenient, low-cost and environmental-friendly transportation, the unique features of bike-sharing systems give rise to problems to both users and operators. The primary issue among these problems is the uneven distribution of bicycles caused by the ever-changing usage and (available) supply. This bicycle imbalance issue necessitates efficient bike re-balancing strategies, which depends highly on bicycle mobility modeling and prediction. In this paper, for the first time, we propose a spatio-temporal bicycle mobility model based on historical bike-sharing data, and devise a traffic prediction mechanism on a per-station basis with sub-hour granularity. We extensively evaluated the performance of our design through a oneyear dataset from the world's largest public bike-sharing system (BSS) with more than 2800 stations and over 103 million check in/out records. Evaluation results show an 85 percentile relative error of 0.6 for both check in and check out prediction. We believe this new mobility modeling and prediction approach can advance the bike re-balancing algorithm design and pave the way for the rapid deployment and adoption of bike-sharing systems across the globe.

show abstract

Section: Mobility Model Fusion With Multi-source Datamentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Mobility Modeling and Prediction in Bike-Sharing Systems

Yang

Shu

et al. 2016

Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services

155

View full text Add to dashboard Cite

show abstract

“…Zheng and Xie () have argued that more experienced tourists should be given more weight when extracting attractive travel sequences. The diversity‐attentive popularity indicator can therefore be compelling, because the inclusion of the number of tracks in the cost function can be interpreted as giving more weight to the tracks of frequent cyclists.…”

Section: Discussionmentioning

confidence: 99%

Conflation of OpenStreetMap and Mobile Sports Tracking Data for Automatic Bicycle Routing

Bergman

Oksanen

2016

Transactions in GIS

View full text Add to dashboard Cite

This article investigates how workout trajectories from a mobile sports tracking application can be used to provide automatic route suggestions for bicyclists. We apply a Hidden Markov Model (HMM)-based method for matching cycling tracks to a "bicycle network" extracted from crowdsourced OpenStreetMap (OSM) data, and evaluate its effective differences in terms of optimal routing compared with a simple geometric point-to-curve method. OSM has quickly established itself as a popular resource for bicycle routing; however, its high-level of detail presents challenges for its applicability to popularity-based routing. We propose a solution where bikeways are prioritized in map-matching, achieving good performance; the HMM-based method matched correctly on average 94% of the route length. In addition, we show that the extremely biased nature of the trajectory dataset, which is typical of volunteered user-generated data, can be of high importance in terms of popularity-based routing. Most computed routes diverged depending on whether the number of users or number of tracks was used as an indicator of popularity, which may imply varying preferences among different types of cyclists. Revising the number of tracks by diversity of users to surmount local biases in the data had a more limited effect on routing.

show abstract

“…Tao et al [13] demonstrated a multistage ways in order to render more insightful spatial-temporal patterns of urban public transport (UPT) passenger's behavior. Zhang et al [14] proposed and implemented a novel architecture called mPat to investigate people movement utilizing various data source, including SCD feeds from 24 thousands vehicle, 16 million smart cards and 10 million cellphones. Yen et al [15] explored the effects of the two principal features of the fare policies applied in SEQ, using smart card transaction records.…”

Section: Literature Reviewmentioning

confidence: 99%

Analyzing Large-Scale Smart Card Data to Investigate Public Transport Travel Behaviour Using Big Data Analytics

Maktoubian¹

2017

J Inform Tech Softw Eng

View full text Add to dashboard Cite

In urban public transport, Smart card data have been used more and more in order to collect fare automatically. They allowed passengers to access almost all type of public transportation system modes (bus, train, tram, funiculars, LRT, metro, and ferryboats) with a single card that is valid for the complete journey. Although Smart card major concentration is in revenue collection, they also generate massive amounts of passive data from the technological devices installed to control the operation of them. Generated data could be beneficial to transit planners which could rise the better understanding of passengers' behavioral patterns for short and long term service planning. However, one of the major challenges is the fact that traditional infrastructures and methods are inefficient when processing or analyzing a large volume of data. Thus, as an alternative, big data technology could be employed to enhance collecting, storing, processing, and analyzing the data. Moreover, the main motivation would be cost-efficiency of this methodology as the cost of processing and analyzing large-scale data is huge. This experience demonstrates that a combination of planning knowledge, big data, and data mining tool allows to produce travel behaviors indicators, public transport policies, operational performance, and fare policies.

show abstract

Exploring human mobility with multi-source data at extremely large metropolitan scales

Cited by 137 publications

References 14 publications

Mobility Modeling and Prediction in Bike-Sharing Systems

Mobility Modeling and Prediction in Bike-Sharing Systems

Conflation of OpenStreetMap and Mobile Sports Tracking Data for Automatic Bicycle Routing

Analyzing Large-Scale Smart Card Data to Investigate Public Transport Travel Behaviour Using Big Data Analytics

Contact Info

Product

Resources

About