Context-aware taxi demand hotspots prediction

Chang, Hsing Cheng; Tai, Yu-chin; Hsu, Jane Yung-jen

doi:10.1504/ijbidm.2010.030296

Cited by 180 publications

(107 citation statements)

References 8 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…As observed in [11], [13] and our real-world dataset (Fig. 1a), a mobility demand pattern over a large service area in an urban city is typically characterized by spatiotemporally correlated demand measurements and contains a few smallscale hotspots exhibiting extreme measurements and much higher spatiotemporal variability than the rest of the demand pattern.…”

Section: Modeling Mobility Demand Pattern With Log-gaussian Processupporting

confidence: 57%

“…. , K to form the global summary (z U ,Σ U U ) (i.e., (11) and (12) of Definition 3) makes it amenable to be approximated using consensus filters [34]- [36]. In this subsection, we will discuss how a distributed algorithm called band-pass consensus filter (BCF), which is previously utilized in distributed Kalman filters [34], [35], can be used to approximate the global summary.…”

Section: Gp-ddf and Gp-ddfmentioning

confidence: 99%

“…while true do / * Data fusion (Section III) * / Construct local summary by ( (9) and (10), and subsequently the global summary in O |U | 2 K time by (11) and (12). To construct the assignment function for any unobserved set S ⊂ V , vehicle k first computes |S| number of γ k sU for all unobserved regions s ∈ S in O |S||U | 2 + |S|(|D|/K) 2 time by (20).…”

Section: Time and Communication Analysismentioning

confidence: 99%

“…The second equality is due to (40). The third equality is due to the definition of global summary (11). The fourth and fifth equalities are due to (43) and (44) The first equality is by definition (24).…”

Section: Appendix B Proof Of Theorem 2bmentioning

confidence: 99%

See 3 more Smart Citations

Gaussian Process Decentralized Data Fusion and Active Sensing for Spatiotemporal Traffic Modeling and Prediction in Mobility-on-Demand Systems

Chen

Low

Yao

et al. 2015

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Abstract-Mobility-on-demand (MoD) systems have recently emerged as a promising paradigm of one-way vehicle sharing for sustainable personal urban mobility in densely populated cities. We assume the capability of a MoD system to be enhanced by deploying robotic shared vehicles that can autonomously cruise the streets to be hailed by users. A key challenge of the MoD system is that of real-time, fine-grained mobility demand and traffic flow sensing and prediction. This paper presents novel Gaussian process (GP) decentralized data fusion and active sensing algorithms for real-time, fine-grained traffic modeling and prediction with a fleet of MoD vehicles. The predictive performance of our decentralized data fusion algorithms are theoretically guaranteed to be equivalent to that of sophisticated centralized sparse GP approximations. We derive consensus filtering variants requiring only local communication between neighboring vehicles. We theoretically guarantee the performance of our decentralized active sensing algorithms. When they are used to gather informative data for mobility demand prediction, they can achieve a dual effect of fleet rebalancing to service mobility demands. Empirical evaluation on real-world datasets shows that our algorithms are significantly more time-efficient and scalable in the size of data and fleet while achieving predictive performance comparable to that of state-of-the-art algorithms.

show abstract

Section: Modeling Mobility Demand Pattern With Log-gaussian Processupporting

confidence: 57%

Section: Gp-ddf and Gp-ddfmentioning

confidence: 99%

Section: Time and Communication Analysismentioning

confidence: 99%

Section: Appendix B Proof Of Theorem 2bmentioning

confidence: 99%

See 2 more Smart Citations

Gaussian Process Decentralized Data Fusion and Active Sensing for Spatiotemporal Traffic Modeling and Prediction in Mobility-on-Demand Systems

Chen

Low

Yao

et al. 2015

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…However, at the same time, taxi occupancy is still very low even in busy time [11]. This contradictory phenomenon leads to great requirements for customers vehicle transportation.…”

Section: Introductionmentioning

confidence: 99%

A Method for Private Car Transportation Dispatching Based on a Passenger Demand Model

Jiang

Zhang

et al. 2015

Internet of Vehicles - Safe and Intelligent Mobility

View full text Add to dashboard Cite

Abstract. Although the demand for taxis is increasing rapidly with the soaring population in big cities, the taxi number grows relatively slowly during these years. In this context, private transportation such as Uber is emerging as a flexible business model, supplementary to the regular forms of taxis. At present, many works mainly focus on how to effectively reduce the taxi cruising miles. However, these taxi-based approaches still have some limitations in private car transportation scenario because they do not fully utilize the sufficient order information introduced by the new type of business model. In this paper, we present a dispatching method based on a passenger demand model to further reduce the private car cruising mileage. In particular, we firstly split the urban areas into many separate regions by using spatial clustering algorithm and partition one day into several time slots according to statistics of historical orders. Secondly, Locally Weighted Linear Regression is adopted to depict the passenger demand model in one specified region over a time slot. Finally, a dispatching process is formalized as a weighted bipartite graph matching problem and we leverage this dispatching approach to schedule private vehicles. To evaluate the effectiveness of our methods, we conduct several experiments based on real datasets derived from a private car hiring company in China. The experimental results illustrate that at most 74% accuracy could be achieved on passenger demand inference. Additionally, the cruising mileage could be reduced by 22.5% in simulation test.

show abstract

Survey and empirical evaluation of nonhomogeneous arrival process models with taxi data

Sayarshad

Chow

2016

J of Advced Transportation

View full text Add to dashboard Cite

Summary Arrival processes are important inputs to many transportation system functions, such as vehicle prepositioning, taxi dispatch, bus holding strategies, and dynamic pricing. We conduct a comprehensive survey of the literature which shows that many transport systems employ basic homogeneous arrival process models or static nonhomogeneous processes. We conduct an empirical experiment to compare five state of the art arrival process short term prediction models using a common transportation system data set: New York taxi passenger pickups in 2013. Pickup data is split between 672 observations for model estimation and 96 observations for validation. From our experiment, we obtain evidence to support a recent model called FM‐IntGARCH, which is able to combine the benefits of both time series models and discrete count processes. Using a set of seven performance metrics from the literature, FM‐IntGARCH is shown to outperform the offline models—seasonal factor method, piecewise linear model—as well as the online models—ARIMA, Gaussian Cox process. Implications for operating data‐driven “smart” transit systems and urban informatics are discussed. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Context-aware taxi demand hotspots prediction

Cited by 180 publications

References 8 publications

Gaussian Process Decentralized Data Fusion and Active Sensing for Spatiotemporal Traffic Modeling and Prediction in Mobility-on-Demand Systems

Gaussian Process Decentralized Data Fusion and Active Sensing for Spatiotemporal Traffic Modeling and Prediction in Mobility-on-Demand Systems

A Method for Private Car Transportation Dispatching Based on a Passenger Demand Model

Survey and empirical evaluation of nonhomogeneous arrival process models with taxi data

Contact Info

Product

Resources

About