Home > Research > Publications & Outputs > CrossSense

Electronic data

  • paper

    Accepted author manuscript, 19 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

CrossSense: towards cross-site and large-scale WiFi sensing

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

CrossSense: towards cross-site and large-scale WiFi sensing. / Zhang, Jie; Tang, Zhanyong; Li, Meng et al.
The 24th ACM International Conference on Mobile Computing and Networking (MobiCom) . ACM, 2018. p. 305-320.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Zhang, J, Tang, Z, Li, M, Fang, D, Nurmi, PT & Wang, Z 2018, CrossSense: towards cross-site and large-scale WiFi sensing. in The 24th ACM International Conference on Mobile Computing and Networking (MobiCom) . ACM, pp. 305-320, 24th Annual International Conference on Mobile Computing and Networking, New Delhi, India, 29/10/18. https://doi.org/10.1145/3241539.3241570

APA

Zhang, J., Tang, Z., Li, M., Fang, D., Nurmi, P. T., & Wang, Z. (2018). CrossSense: towards cross-site and large-scale WiFi sensing. In The 24th ACM International Conference on Mobile Computing and Networking (MobiCom) (pp. 305-320). ACM. https://doi.org/10.1145/3241539.3241570

Vancouver

Zhang J, Tang Z, Li M, Fang D, Nurmi PT, Wang Z. CrossSense: towards cross-site and large-scale WiFi sensing. In The 24th ACM International Conference on Mobile Computing and Networking (MobiCom) . ACM. 2018. p. 305-320 doi: 10.1145/3241539.3241570

Author

Zhang, Jie ; Tang, Zhanyong ; Li, Meng et al. / CrossSense : towards cross-site and large-scale WiFi sensing. The 24th ACM International Conference on Mobile Computing and Networking (MobiCom) . ACM, 2018. pp. 305-320

Bibtex

@inproceedings{cd33c8a3372c4ea3b6fc7ba32143e9fa,
title = "CrossSense: towards cross-site and large-scale WiFi sensing",
abstract = "We present CrossSense, a novel system for scaling up WiFi sensing to new environments and larger problems. To reduce the cost of sensing model training data collection, CrossSense employs machine learning to train, off-line, a roaming model that generates from one set of measurements synthetic training samples for each target environment. To scale up to a larger problem size, CrossSense adopts a mixture-of-experts approach where multiple specialized sensing models, or experts, are used to capture the mapping from diverse WiFi inputs to the desired outputs. The experts are trained offline and at runtime the appropriate expert for a given input is automatically chosen. We evaluate CrossSense by applying it to two representative WiFi sensing applications, gait identification and gesture recognition, in controlled single-link environments. We show that CrossSense boosts the accuracy of state-of-the-art WiFi sensing techniques from 20% to over 80% and 90% for gait identification and gesture recognition respectively, delivering consistently good performance – particularly when the problem size is significantly greater than that current approaches can effectively handle.",
author = "Jie Zhang and Zhanyong Tang and Meng Li and Dingyi Fang and Nurmi, {Petteri Tapio} and Zheng Wang",
year = "2018",
month = oct,
day = "15",
doi = "10.1145/3241539.3241570",
language = "English",
isbn = "9781450359030",
pages = "305--320",
booktitle = "The 24th ACM International Conference on Mobile Computing and Networking (MobiCom)",
publisher = "ACM",
note = "24th Annual International Conference on Mobile Computing and Networking, MobiCom '18 ; Conference date: 29-10-2018 Through 02-11-2018",

}

RIS

TY - GEN

T1 - CrossSense

T2 - 24th Annual International Conference on Mobile Computing and Networking

AU - Zhang, Jie

AU - Tang, Zhanyong

AU - Li, Meng

AU - Fang, Dingyi

AU - Nurmi, Petteri Tapio

AU - Wang, Zheng

PY - 2018/10/15

Y1 - 2018/10/15

N2 - We present CrossSense, a novel system for scaling up WiFi sensing to new environments and larger problems. To reduce the cost of sensing model training data collection, CrossSense employs machine learning to train, off-line, a roaming model that generates from one set of measurements synthetic training samples for each target environment. To scale up to a larger problem size, CrossSense adopts a mixture-of-experts approach where multiple specialized sensing models, or experts, are used to capture the mapping from diverse WiFi inputs to the desired outputs. The experts are trained offline and at runtime the appropriate expert for a given input is automatically chosen. We evaluate CrossSense by applying it to two representative WiFi sensing applications, gait identification and gesture recognition, in controlled single-link environments. We show that CrossSense boosts the accuracy of state-of-the-art WiFi sensing techniques from 20% to over 80% and 90% for gait identification and gesture recognition respectively, delivering consistently good performance – particularly when the problem size is significantly greater than that current approaches can effectively handle.

AB - We present CrossSense, a novel system for scaling up WiFi sensing to new environments and larger problems. To reduce the cost of sensing model training data collection, CrossSense employs machine learning to train, off-line, a roaming model that generates from one set of measurements synthetic training samples for each target environment. To scale up to a larger problem size, CrossSense adopts a mixture-of-experts approach where multiple specialized sensing models, or experts, are used to capture the mapping from diverse WiFi inputs to the desired outputs. The experts are trained offline and at runtime the appropriate expert for a given input is automatically chosen. We evaluate CrossSense by applying it to two representative WiFi sensing applications, gait identification and gesture recognition, in controlled single-link environments. We show that CrossSense boosts the accuracy of state-of-the-art WiFi sensing techniques from 20% to over 80% and 90% for gait identification and gesture recognition respectively, delivering consistently good performance – particularly when the problem size is significantly greater than that current approaches can effectively handle.

U2 - 10.1145/3241539.3241570

DO - 10.1145/3241539.3241570

M3 - Conference contribution/Paper

SN - 9781450359030

SP - 305

EP - 320

BT - The 24th ACM International Conference on Mobile Computing and Networking (MobiCom)

PB - ACM

Y2 - 29 October 2018 through 2 November 2018

ER -