Towards environment independent device free human activity recognition

Wenjun Jiang, Chenglin Miao, Fenglong Ma, Shuochao Yao, Yaqing Wang, Ye Yuan, Hongfei Xue, Chen Song, Xin Ma, Dimitrios Koutsonikolas, Wenyao Xu, Lu Su

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

15 Citations (Scopus)

Abstract

Driven by a wide range of real-world applications, significant efforts have recently been made to explore device-free human activity recognition techniques that utilize the information collected by various wireless infrastructures to infer human activities without the need for the monitored subject to carry a dedicated device. Existing device free human activity recognition approaches and systems, though yielding reasonably good performance in certain cases, are faced with a major challenge. The wireless signals arriving at the receiving devices usually carry substantial information that is specific to the environment where the activities are recorded and the human subject who conducts the activities. Due to this reason, an activity recognition model that is trained on a specific subject in a specific environment typically does not work well when being applied to predict another subject's activities that are recorded in a different environment. To address this challenge, in this paper, we propose EI, a deep-learning based device free activity recognition framework that can remove the environment and subject specific information contained in the activity data and extract environment/subject-independent features shared by the data collected on different subjects under different environments. We conduct extensive experiments on four different device free activity recognition testbeds: WiFi, ultrasound, 60 GHz mmWave, and visible light. The experimental results demonstrate the superior effectiveness and generalizability of the proposed EI framework.

Original languageEnglish (US)
Title of host publicationMobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking
PublisherAssociation for Computing Machinery
Pages289-304
Number of pages16
ISBN (Electronic)9781450359030
DOIs
StatePublished - Oct 15 2018
Event24th Annual International Conference on Mobile Computing and Networking, MobiCom 2018 - New Delhi, India
Duration: Oct 29 2018Nov 2 2018

Publication series

NameProceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM

Conference

Conference24th Annual International Conference on Mobile Computing and Networking, MobiCom 2018
CountryIndia
CityNew Delhi
Period10/29/1811/2/18

Fingerprint

Testbeds
Ultrasonics
Experiments
Deep learning

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Jiang, W., Miao, C., Ma, F., Yao, S., Wang, Y., Yuan, Y., ... Su, L. (2018). Towards environment independent device free human activity recognition. In MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking (pp. 289-304). (Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM). Association for Computing Machinery. https://doi.org/10.1145/3241539.3241548
Jiang, Wenjun ; Miao, Chenglin ; Ma, Fenglong ; Yao, Shuochao ; Wang, Yaqing ; Yuan, Ye ; Xue, Hongfei ; Song, Chen ; Ma, Xin ; Koutsonikolas, Dimitrios ; Xu, Wenyao ; Su, Lu. / Towards environment independent device free human activity recognition. MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. Association for Computing Machinery, 2018. pp. 289-304 (Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM).
@inproceedings{d9439d5fc8d848399df723856396fec9,
title = "Towards environment independent device free human activity recognition",
abstract = "Driven by a wide range of real-world applications, significant efforts have recently been made to explore device-free human activity recognition techniques that utilize the information collected by various wireless infrastructures to infer human activities without the need for the monitored subject to carry a dedicated device. Existing device free human activity recognition approaches and systems, though yielding reasonably good performance in certain cases, are faced with a major challenge. The wireless signals arriving at the receiving devices usually carry substantial information that is specific to the environment where the activities are recorded and the human subject who conducts the activities. Due to this reason, an activity recognition model that is trained on a specific subject in a specific environment typically does not work well when being applied to predict another subject's activities that are recorded in a different environment. To address this challenge, in this paper, we propose EI, a deep-learning based device free activity recognition framework that can remove the environment and subject specific information contained in the activity data and extract environment/subject-independent features shared by the data collected on different subjects under different environments. We conduct extensive experiments on four different device free activity recognition testbeds: WiFi, ultrasound, 60 GHz mmWave, and visible light. The experimental results demonstrate the superior effectiveness and generalizability of the proposed EI framework.",
author = "Wenjun Jiang and Chenglin Miao and Fenglong Ma and Shuochao Yao and Yaqing Wang and Ye Yuan and Hongfei Xue and Chen Song and Xin Ma and Dimitrios Koutsonikolas and Wenyao Xu and Lu Su",
year = "2018",
month = "10",
day = "15",
doi = "10.1145/3241539.3241548",
language = "English (US)",
series = "Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM",
publisher = "Association for Computing Machinery",
pages = "289--304",
booktitle = "MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking",

}

Jiang, W, Miao, C, Ma, F, Yao, S, Wang, Y, Yuan, Y, Xue, H, Song, C, Ma, X, Koutsonikolas, D, Xu, W & Su, L 2018, Towards environment independent device free human activity recognition. in MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM, Association for Computing Machinery, pp. 289-304, 24th Annual International Conference on Mobile Computing and Networking, MobiCom 2018, New Delhi, India, 10/29/18. https://doi.org/10.1145/3241539.3241548

Towards environment independent device free human activity recognition. / Jiang, Wenjun; Miao, Chenglin; Ma, Fenglong; Yao, Shuochao; Wang, Yaqing; Yuan, Ye; Xue, Hongfei; Song, Chen; Ma, Xin; Koutsonikolas, Dimitrios; Xu, Wenyao; Su, Lu.

MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. Association for Computing Machinery, 2018. p. 289-304 (Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM).

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

TY - GEN

T1 - Towards environment independent device free human activity recognition

AU - Jiang, Wenjun

AU - Miao, Chenglin

AU - Ma, Fenglong

AU - Yao, Shuochao

AU - Wang, Yaqing

AU - Yuan, Ye

AU - Xue, Hongfei

AU - Song, Chen

AU - Ma, Xin

AU - Koutsonikolas, Dimitrios

AU - Xu, Wenyao

AU - Su, Lu

PY - 2018/10/15

Y1 - 2018/10/15

N2 - Driven by a wide range of real-world applications, significant efforts have recently been made to explore device-free human activity recognition techniques that utilize the information collected by various wireless infrastructures to infer human activities without the need for the monitored subject to carry a dedicated device. Existing device free human activity recognition approaches and systems, though yielding reasonably good performance in certain cases, are faced with a major challenge. The wireless signals arriving at the receiving devices usually carry substantial information that is specific to the environment where the activities are recorded and the human subject who conducts the activities. Due to this reason, an activity recognition model that is trained on a specific subject in a specific environment typically does not work well when being applied to predict another subject's activities that are recorded in a different environment. To address this challenge, in this paper, we propose EI, a deep-learning based device free activity recognition framework that can remove the environment and subject specific information contained in the activity data and extract environment/subject-independent features shared by the data collected on different subjects under different environments. We conduct extensive experiments on four different device free activity recognition testbeds: WiFi, ultrasound, 60 GHz mmWave, and visible light. The experimental results demonstrate the superior effectiveness and generalizability of the proposed EI framework.

AB - Driven by a wide range of real-world applications, significant efforts have recently been made to explore device-free human activity recognition techniques that utilize the information collected by various wireless infrastructures to infer human activities without the need for the monitored subject to carry a dedicated device. Existing device free human activity recognition approaches and systems, though yielding reasonably good performance in certain cases, are faced with a major challenge. The wireless signals arriving at the receiving devices usually carry substantial information that is specific to the environment where the activities are recorded and the human subject who conducts the activities. Due to this reason, an activity recognition model that is trained on a specific subject in a specific environment typically does not work well when being applied to predict another subject's activities that are recorded in a different environment. To address this challenge, in this paper, we propose EI, a deep-learning based device free activity recognition framework that can remove the environment and subject specific information contained in the activity data and extract environment/subject-independent features shared by the data collected on different subjects under different environments. We conduct extensive experiments on four different device free activity recognition testbeds: WiFi, ultrasound, 60 GHz mmWave, and visible light. The experimental results demonstrate the superior effectiveness and generalizability of the proposed EI framework.

UR - http://www.scopus.com/inward/record.url?scp=85056908152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056908152&partnerID=8YFLogxK

U2 - 10.1145/3241539.3241548

DO - 10.1145/3241539.3241548

M3 - Conference contribution

AN - SCOPUS:85056908152

T3 - Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM

SP - 289

EP - 304

BT - MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking

PB - Association for Computing Machinery

ER -

Jiang W, Miao C, Ma F, Yao S, Wang Y, Yuan Y et al. Towards environment independent device free human activity recognition. In MobiCom 2018 - Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. Association for Computing Machinery. 2018. p. 289-304. (Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM). https://doi.org/10.1145/3241539.3241548