Unsupervised activity recognition with user's physical characteristics data

Takuya Maekawa, Shinji Watanabe

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

54 Citations (Scopus)

Abstract

This paper proposes an activity recognition method that models an end user's activities without using any la-beled/unlabeled acceleration sensor data obtained from the user. Our method employs information about the end user's physical characteristics such as height and gender to find other users whose sensor data prepared in advance may be similar to those of the end user. Then, we model the end user's activities by using the labeled sensor data from the similar users. Therefore, our method does not require the end user to collect and label her training sensor data. We confirmed the effectiveness of our method by using 100 hours of sensor data obtained from 40 participants, and achieved a good recognition accuracy almost identical to that of a recognition method employing an end user's labeled training data.

Original languageEnglish
Title of host publicationProceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011
Pages89-96
Number of pages8
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event15th Annual International Symposium on Wearable Computers, ISWC 2011 - San Francisco, CA, United States
Duration: 2011 Jun 122011 Jun 15

Other

Other15th Annual International Symposium on Wearable Computers, ISWC 2011
CountryUnited States
CitySan Francisco, CA
Period11/6/1211/6/15

Fingerprint

Sensors
Labels

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Maekawa, T., & Watanabe, S. (2011). Unsupervised activity recognition with user's physical characteristics data. In Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011 (pp. 89-96). [5959600] https://doi.org/10.1109/ISWC.2011.24

Unsupervised activity recognition with user's physical characteristics data. / Maekawa, Takuya; Watanabe, Shinji.

Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011. 2011. p. 89-96 5959600.

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

Maekawa, T & Watanabe, S 2011, Unsupervised activity recognition with user's physical characteristics data. in Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011., 5959600, pp. 89-96, 15th Annual International Symposium on Wearable Computers, ISWC 2011, San Francisco, CA, United States, 11/6/12. https://doi.org/10.1109/ISWC.2011.24
Maekawa T, Watanabe S. Unsupervised activity recognition with user's physical characteristics data. In Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011. 2011. p. 89-96. 5959600 https://doi.org/10.1109/ISWC.2011.24
Maekawa, Takuya ; Watanabe, Shinji. / Unsupervised activity recognition with user's physical characteristics data. Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011. 2011. pp. 89-96
@inproceedings{7b5f14f37079447dadddf058251eff4d,
title = "Unsupervised activity recognition with user's physical characteristics data",
abstract = "This paper proposes an activity recognition method that models an end user's activities without using any la-beled/unlabeled acceleration sensor data obtained from the user. Our method employs information about the end user's physical characteristics such as height and gender to find other users whose sensor data prepared in advance may be similar to those of the end user. Then, we model the end user's activities by using the labeled sensor data from the similar users. Therefore, our method does not require the end user to collect and label her training sensor data. We confirmed the effectiveness of our method by using 100 hours of sensor data obtained from 40 participants, and achieved a good recognition accuracy almost identical to that of a recognition method employing an end user's labeled training data.",
author = "Takuya Maekawa and Shinji Watanabe",
year = "2011",
doi = "10.1109/ISWC.2011.24",
language = "English",
isbn = "9780769544380",
pages = "89--96",
booktitle = "Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011",

}

TY - GEN

T1 - Unsupervised activity recognition with user's physical characteristics data

AU - Maekawa, Takuya

AU - Watanabe, Shinji

PY - 2011

Y1 - 2011

N2 - This paper proposes an activity recognition method that models an end user's activities without using any la-beled/unlabeled acceleration sensor data obtained from the user. Our method employs information about the end user's physical characteristics such as height and gender to find other users whose sensor data prepared in advance may be similar to those of the end user. Then, we model the end user's activities by using the labeled sensor data from the similar users. Therefore, our method does not require the end user to collect and label her training sensor data. We confirmed the effectiveness of our method by using 100 hours of sensor data obtained from 40 participants, and achieved a good recognition accuracy almost identical to that of a recognition method employing an end user's labeled training data.

AB - This paper proposes an activity recognition method that models an end user's activities without using any la-beled/unlabeled acceleration sensor data obtained from the user. Our method employs information about the end user's physical characteristics such as height and gender to find other users whose sensor data prepared in advance may be similar to those of the end user. Then, we model the end user's activities by using the labeled sensor data from the similar users. Therefore, our method does not require the end user to collect and label her training sensor data. We confirmed the effectiveness of our method by using 100 hours of sensor data obtained from 40 participants, and achieved a good recognition accuracy almost identical to that of a recognition method employing an end user's labeled training data.

UR - http://www.scopus.com/inward/record.url?scp=80051981740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051981740&partnerID=8YFLogxK

U2 - 10.1109/ISWC.2011.24

DO - 10.1109/ISWC.2011.24

M3 - Conference contribution

SN - 9780769544380

SP - 89

EP - 96

BT - Proceedings - 15th Annual International Symposium on Wearable Computers, ISWC 2011

ER -