Dmodel: Online taxicab demand model from big sensor data in a roving sensor network

Desheng Zhang; Tian He; Shan Lin; Sirajum Munir; John A. Stankovic

doi:10.1109/BigData.Congress.2014.30

Dmodel: Online taxicab demand model from big sensor data in a roving sensor network

Desheng Zhang, Tian He, Shan Lin, Sirajum Munir, John A. Stankovic

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

24 Scopus citations

Abstract

Investigating passenger demand is essential for the taxicab business. Existing solutions are typically based on dated and inaccurate offline data collected by manual investigations. To address this issue, we propose Dmodel, using roving taxicabs as real-time mobile sensors to (i) infer passenger arriving moments by interactions of vacant taxicabs, and (ii) infer passenger demand by a customized online training with both historical and real-time data. Such huge taxicab data (almost 1TB per year) pose a big data challenge. To address this challenge, model employs a novel parameter called pickup pattern (accounts for various real-world logical information, e.g., bad weather) to increase the inference accuracy. We evaluate Dmodel with a real-world 450 GB dataset of 14, 000 taxicabs, and results show that compared to the ground truth, Dmodel achieves a 76% accuracy on the demand inference and outperforms a statistical model by 39%.

Original language	English (US)
Title of host publication	Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014
Editors	Peter Chen, Peter Chen, Hemant Jain
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	152-159
Number of pages	8
ISBN (Electronic)	9781479950577
DOIs	https://doi.org/10.1109/BigData.Congress.2014.30
State	Published - Sep 22 2014
Event	3rd IEEE International Congress on Big Data, BigData Congress 2014 - Anchorage, United States Duration: Jun 27 2014 → Jul 2 2014

Publication series

Name	Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014

Other

Other	3rd IEEE International Congress on Big Data, BigData Congress 2014
Country/Territory	United States
City	Anchorage
Period	6/27/14 → 7/2/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Access

10.1109/BigData.Congress.2014.30

OpenUrl availability

Full text

Cite this

Zhang, D., He, T., Lin, S., Munir, S., & Stankovic, J. A. (2014). Dmodel: Online taxicab demand model from big sensor data in a roving sensor network. In P. Chen, P. Chen, & H. Jain (Eds.), Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014 (pp. 152-159). Article 6906773 (Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData.Congress.2014.30

Dmodel: Online taxicab demand model from big sensor data in a roving sensor network. / Zhang, Desheng; He, Tian; Lin, Shan et al.
Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014. ed. / Peter Chen; Peter Chen; Hemant Jain. Institute of Electrical and Electronics Engineers Inc., 2014. p. 152-159 6906773 (Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, D, He, T, Lin, S, Munir, S & Stankovic, JA 2014, Dmodel: Online taxicab demand model from big sensor data in a roving sensor network. in P Chen, P Chen & H Jain (eds), Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014., 6906773, Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014, Institute of Electrical and Electronics Engineers Inc., pp. 152-159, 3rd IEEE International Congress on Big Data, BigData Congress 2014, Anchorage, United States, 6/27/14. https://doi.org/10.1109/BigData.Congress.2014.30

Zhang D, He T, Lin S, Munir S, Stankovic JA. Dmodel: Online taxicab demand model from big sensor data in a roving sensor network. In Chen P, Chen P, Jain H, editors, Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 152-159. 6906773. (Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014). doi: 10.1109/BigData.Congress.2014.30

Zhang, Desheng ; He, Tian ; Lin, Shan et al. / Dmodel : Online taxicab demand model from big sensor data in a roving sensor network. Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014. editor / Peter Chen ; Peter Chen ; Hemant Jain. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 152-159 (Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014).

@inproceedings{437d2d365d3e463f849ab2f20c090963,

title = "Dmodel: Online taxicab demand model from big sensor data in a roving sensor network",

abstract = "Investigating passenger demand is essential for the taxicab business. Existing solutions are typically based on dated and inaccurate offline data collected by manual investigations. To address this issue, we propose Dmodel, using roving taxicabs as real-time mobile sensors to (i) infer passenger arriving moments by interactions of vacant taxicabs, and (ii) infer passenger demand by a customized online training with both historical and real-time data. Such huge taxicab data (almost 1TB per year) pose a big data challenge. To address this challenge, model employs a novel parameter called pickup pattern (accounts for various real-world logical information, e.g., bad weather) to increase the inference accuracy. We evaluate Dmodel with a real-world 450 GB dataset of 14, 000 taxicabs, and results show that compared to the ground truth, Dmodel achieves a 76% accuracy on the demand inference and outperforms a statistical model by 39%.",

author = "Desheng Zhang and Tian He and Shan Lin and Sirajum Munir and Stankovic, {John A.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 3rd IEEE International Congress on Big Data, BigData Congress 2014 ; Conference date: 27-06-2014 Through 02-07-2014",

year = "2014",

month = sep,

day = "22",

doi = "10.1109/BigData.Congress.2014.30",

language = "English (US)",

series = "Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "152--159",

editor = "Peter Chen and Peter Chen and Hemant Jain",

booktitle = "Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014",

}

TY - GEN

T1 - Dmodel

T2 - 3rd IEEE International Congress on Big Data, BigData Congress 2014

AU - Zhang, Desheng

AU - He, Tian

AU - Lin, Shan

AU - Munir, Sirajum

AU - Stankovic, John A.

PY - 2014/9/22

Y1 - 2014/9/22

N2 - Investigating passenger demand is essential for the taxicab business. Existing solutions are typically based on dated and inaccurate offline data collected by manual investigations. To address this issue, we propose Dmodel, using roving taxicabs as real-time mobile sensors to (i) infer passenger arriving moments by interactions of vacant taxicabs, and (ii) infer passenger demand by a customized online training with both historical and real-time data. Such huge taxicab data (almost 1TB per year) pose a big data challenge. To address this challenge, model employs a novel parameter called pickup pattern (accounts for various real-world logical information, e.g., bad weather) to increase the inference accuracy. We evaluate Dmodel with a real-world 450 GB dataset of 14, 000 taxicabs, and results show that compared to the ground truth, Dmodel achieves a 76% accuracy on the demand inference and outperforms a statistical model by 39%.

AB - Investigating passenger demand is essential for the taxicab business. Existing solutions are typically based on dated and inaccurate offline data collected by manual investigations. To address this issue, we propose Dmodel, using roving taxicabs as real-time mobile sensors to (i) infer passenger arriving moments by interactions of vacant taxicabs, and (ii) infer passenger demand by a customized online training with both historical and real-time data. Such huge taxicab data (almost 1TB per year) pose a big data challenge. To address this challenge, model employs a novel parameter called pickup pattern (accounts for various real-world logical information, e.g., bad weather) to increase the inference accuracy. We evaluate Dmodel with a real-world 450 GB dataset of 14, 000 taxicabs, and results show that compared to the ground truth, Dmodel achieves a 76% accuracy on the demand inference and outperforms a statistical model by 39%.

UR - http://www.scopus.com/inward/record.url?scp=84923857064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923857064&partnerID=8YFLogxK

U2 - 10.1109/BigData.Congress.2014.30

DO - 10.1109/BigData.Congress.2014.30

M3 - Conference contribution

AN - SCOPUS:84923857064

T3 - Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014

SP - 152

EP - 159

BT - Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014

A2 - Chen, Peter

A2 - Jain, Hemant

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 27 June 2014 through 2 July 2014

ER -

Dmodel: Online taxicab demand model from big sensor data in a roving sensor network

Abstract

Publication series

Other

Bibliographical note

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this