Tracking human queues using single-point signal monitoring

Yan Wang, Jie Yang, Yingying Chen, Hongbo Liu, Marco Gruteser, Richard Martin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

39 Citations (Scopus)

Abstract

We investigate using smartphone WiFi signals to track human queues, which are common in many business areas such as retail stores, airports, and theme parks. Real-time monitoring of such queues would enable a wealth of new applications, such as bottleneck analysis, shift assignments, and dynamic workflow scheduling. We take a minimum infrastructure approach and thus utilize a single monitor placed close to the service area along with transmitting phones. Our strategy extracts unique features embedded in signal traces to infer the critical time points when a person reaches the head of the queue and finishes service, and from these inferences we derive a person's waiting and service times. We develop two approaches in our system, one is directly feature-driven and the second uses a simple Bayesian network. Extensive experiments conducted both in the laboratory as well as in two public facilities demonstrate that our system is robust to real-world environments. We show that in spite of noisy signal readings, our methods can measure service and waiting times to within a 10 second resolution.

Original languageEnglish (US)
Title of host publicationMobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services
PublisherAssociation for Computing Machinery
Pages42-54
Number of pages13
ISBN (Print)9781450327930
DOIs
StatePublished - Jan 1 2014
Event12th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2014 - Bretton Woods, NH, United States
Duration: Jun 16 2014Jun 19 2014

Publication series

NameMobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services

Other

Other12th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2014
CountryUnited States
CityBretton Woods, NH
Period6/16/146/19/14

Fingerprint

Retail stores
Smartphones
Bayesian networks
Airports
Scheduling
Monitoring
Industry
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

Keywords

  • human queue monitoring
  • received signal strength
  • smartphones
  • wifi

Cite this

Wang, Y., Yang, J., Chen, Y., Liu, H., Gruteser, M., & Martin, R. (2014). Tracking human queues using single-point signal monitoring. In MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (pp. 42-54). (MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services). Association for Computing Machinery. https://doi.org/10.1145/2594368.2594382
Wang, Yan ; Yang, Jie ; Chen, Yingying ; Liu, Hongbo ; Gruteser, Marco ; Martin, Richard. / Tracking human queues using single-point signal monitoring. MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services. Association for Computing Machinery, 2014. pp. 42-54 (MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services).
@inproceedings{b3ac6ae4fe7a45f0912b77c048e3277b,
title = "Tracking human queues using single-point signal monitoring",
abstract = "We investigate using smartphone WiFi signals to track human queues, which are common in many business areas such as retail stores, airports, and theme parks. Real-time monitoring of such queues would enable a wealth of new applications, such as bottleneck analysis, shift assignments, and dynamic workflow scheduling. We take a minimum infrastructure approach and thus utilize a single monitor placed close to the service area along with transmitting phones. Our strategy extracts unique features embedded in signal traces to infer the critical time points when a person reaches the head of the queue and finishes service, and from these inferences we derive a person's waiting and service times. We develop two approaches in our system, one is directly feature-driven and the second uses a simple Bayesian network. Extensive experiments conducted both in the laboratory as well as in two public facilities demonstrate that our system is robust to real-world environments. We show that in spite of noisy signal readings, our methods can measure service and waiting times to within a 10 second resolution.",
keywords = "human queue monitoring, received signal strength, smartphones, wifi",
author = "Yan Wang and Jie Yang and Yingying Chen and Hongbo Liu and Marco Gruteser and Richard Martin",
year = "2014",
month = "1",
day = "1",
doi = "https://doi.org/10.1145/2594368.2594382",
language = "English (US)",
isbn = "9781450327930",
series = "MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services",
publisher = "Association for Computing Machinery",
pages = "42--54",
booktitle = "MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services",

}

Wang, Y, Yang, J, Chen, Y, Liu, H, Gruteser, M & Martin, R 2014, Tracking human queues using single-point signal monitoring. in MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services. MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services, Association for Computing Machinery, pp. 42-54, 12th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2014, Bretton Woods, NH, United States, 6/16/14. https://doi.org/10.1145/2594368.2594382

Tracking human queues using single-point signal monitoring. / Wang, Yan; Yang, Jie; Chen, Yingying; Liu, Hongbo; Gruteser, Marco; Martin, Richard.

MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services. Association for Computing Machinery, 2014. p. 42-54 (MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Tracking human queues using single-point signal monitoring

AU - Wang, Yan

AU - Yang, Jie

AU - Chen, Yingying

AU - Liu, Hongbo

AU - Gruteser, Marco

AU - Martin, Richard

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We investigate using smartphone WiFi signals to track human queues, which are common in many business areas such as retail stores, airports, and theme parks. Real-time monitoring of such queues would enable a wealth of new applications, such as bottleneck analysis, shift assignments, and dynamic workflow scheduling. We take a minimum infrastructure approach and thus utilize a single monitor placed close to the service area along with transmitting phones. Our strategy extracts unique features embedded in signal traces to infer the critical time points when a person reaches the head of the queue and finishes service, and from these inferences we derive a person's waiting and service times. We develop two approaches in our system, one is directly feature-driven and the second uses a simple Bayesian network. Extensive experiments conducted both in the laboratory as well as in two public facilities demonstrate that our system is robust to real-world environments. We show that in spite of noisy signal readings, our methods can measure service and waiting times to within a 10 second resolution.

AB - We investigate using smartphone WiFi signals to track human queues, which are common in many business areas such as retail stores, airports, and theme parks. Real-time monitoring of such queues would enable a wealth of new applications, such as bottleneck analysis, shift assignments, and dynamic workflow scheduling. We take a minimum infrastructure approach and thus utilize a single monitor placed close to the service area along with transmitting phones. Our strategy extracts unique features embedded in signal traces to infer the critical time points when a person reaches the head of the queue and finishes service, and from these inferences we derive a person's waiting and service times. We develop two approaches in our system, one is directly feature-driven and the second uses a simple Bayesian network. Extensive experiments conducted both in the laboratory as well as in two public facilities demonstrate that our system is robust to real-world environments. We show that in spite of noisy signal readings, our methods can measure service and waiting times to within a 10 second resolution.

KW - human queue monitoring

KW - received signal strength

KW - smartphones

KW - wifi

UR - http://www.scopus.com/inward/record.url?scp=84903212721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903212721&partnerID=8YFLogxK

U2 - https://doi.org/10.1145/2594368.2594382

DO - https://doi.org/10.1145/2594368.2594382

M3 - Conference contribution

SN - 9781450327930

T3 - MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services

SP - 42

EP - 54

BT - MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services

PB - Association for Computing Machinery

ER -

Wang Y, Yang J, Chen Y, Liu H, Gruteser M, Martin R. Tracking human queues using single-point signal monitoring. In MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services. Association for Computing Machinery. 2014. p. 42-54. (MobiSys 2014 - Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services). https://doi.org/10.1145/2594368.2594382