Towards detection of bad habits by fusing smartphone and smartwatch sensors

M. Shoaib, S. Bosch, Johan Scholten, Paul J.M. Havinga, O. Durmaz

  • 23 Citations

Abstract

Recently, there has been a growing interest in the research community about using wrist-worn devices, such as smartwatches for human activity recognition, since these devices are equipped with various sensors such as an accelerometer and a gyroscope. Similarly, smartphones are already being used for activity recognition. In this paper, we study the fusion of a wrist-worn device (smartwatch) and a smartphone for human activity recognition. We evaluate these two devices for their strengths and weaknesses in recognizing various daily physical activities. We use three classifiers to recognize 13 different activities, such as smoking, eating, typing, writing, drinking coffee, giving a talk, walking, jogging, biking, walking upstairs, walking downstairs, sitting, and standing. Some complex activities, such as smoking, eating, drinking coffee, giving a talk, writing, and typing cannot be recognized with a smartphone in the pocket position alone. We show that the combination of a smartwatch and a smartphone recognizes such activities with a reasonable accuracy. The recognition of such complex activities can enable well-being applications for detecting bad habits, such as smoking, missing a meal, and drinking too much coffee. We also show how to fuse information from these devices in an energy-efficient way by using low sampling rates. We make our dataset publicly available in order to make our work reproducible.
Original languageUndefined
Title of host publicationProceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015
Place of PublicationUSA
PublisherIEEE Computer Society
Pages591 -596
Number of pages6
ISBN (Print)978-1-4799-8425-1
DOIs
StatePublished - 23 Mar 2015
EventIEEE International Conference on Pervasive Computing and Communications, PerCom 2015 - St. Louis, United States

Publication series

Name
PublisherIEEE Computer Society

Workshop

WorkshopIEEE International Conference on Pervasive Computing and Communications, PerCom 2015
Abbreviated titlePerCom
CountryUnited States
CitySt. Louis
Period23/03/1527/03/15
Internet address

Fingerprint

Smartphones
Coffee
Gyroscopes
Electric fuses
Accelerometers
Classifiers
Fusion reactions
Sampling
Sensors

Keywords

  • EWI-26482
  • METIS-315041
  • IR-98394

Cite this

Shoaib, M., Bosch, S., Scholten, J., Havinga, P. J. M., & Durmaz, O. (2015). Towards detection of bad habits by fusing smartphone and smartwatch sensors. In Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015 (pp. 591 -596). USA: IEEE Computer Society. DOI: 10.1109/PERCOMW.2015.7134104

Shoaib, M.; Bosch, S.; Scholten, Johan; Havinga, Paul J.M.; Durmaz, O. / Towards detection of bad habits by fusing smartphone and smartwatch sensors.

Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015. USA : IEEE Computer Society, 2015. p. 591 -596.

Research output: Scientific - peer-reviewConference contribution

@inbook{1816e787f3da4d73998b5fff81c7b42e,
title = "Towards detection of bad habits by fusing smartphone and smartwatch sensors",
abstract = "Recently, there has been a growing interest in the research community about using wrist-worn devices, such as smartwatches for human activity recognition, since these devices are equipped with various sensors such as an accelerometer and a gyroscope. Similarly, smartphones are already being used for activity recognition. In this paper, we study the fusion of a wrist-worn device (smartwatch) and a smartphone for human activity recognition. We evaluate these two devices for their strengths and weaknesses in recognizing various daily physical activities. We use three classifiers to recognize 13 different activities, such as smoking, eating, typing, writing, drinking coffee, giving a talk, walking, jogging, biking, walking upstairs, walking downstairs, sitting, and standing. Some complex activities, such as smoking, eating, drinking coffee, giving a talk, writing, and typing cannot be recognized with a smartphone in the pocket position alone. We show that the combination of a smartwatch and a smartphone recognizes such activities with a reasonable accuracy. The recognition of such complex activities can enable well-being applications for detecting bad habits, such as smoking, missing a meal, and drinking too much coffee. We also show how to fuse information from these devices in an energy-efficient way by using low sampling rates. We make our dataset publicly available in order to make our work reproducible.",
keywords = "EWI-26482, METIS-315041, IR-98394",
author = "M. Shoaib and S. Bosch and Johan Scholten and Havinga, {Paul J.M.} and O. Durmaz",
note = "10.1109/PERCOMW.2015.7134104",
year = "2015",
month = "3",
doi = "10.1109/PERCOMW.2015.7134104",
isbn = "978-1-4799-8425-1",
publisher = "IEEE Computer Society",
pages = "591 --596",
booktitle = "Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015",
address = "United States",

}

Shoaib, M, Bosch, S, Scholten, J, Havinga, PJM & Durmaz, O 2015, Towards detection of bad habits by fusing smartphone and smartwatch sensors. in Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015. IEEE Computer Society, USA, pp. 591 -596, IEEE International Conference on Pervasive Computing and Communications, PerCom 2015, St. Louis, United States, 23-27 March. DOI: 10.1109/PERCOMW.2015.7134104

Towards detection of bad habits by fusing smartphone and smartwatch sensors. / Shoaib, M.; Bosch, S.; Scholten, Johan; Havinga, Paul J.M.; Durmaz, O.

Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015. USA : IEEE Computer Society, 2015. p. 591 -596.

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - Towards detection of bad habits by fusing smartphone and smartwatch sensors

AU - Shoaib,M.

AU - Bosch,S.

AU - Scholten,Johan

AU - Havinga,Paul J.M.

AU - Durmaz,O.

N1 - 10.1109/PERCOMW.2015.7134104

PY - 2015/3/23

Y1 - 2015/3/23

N2 - Recently, there has been a growing interest in the research community about using wrist-worn devices, such as smartwatches for human activity recognition, since these devices are equipped with various sensors such as an accelerometer and a gyroscope. Similarly, smartphones are already being used for activity recognition. In this paper, we study the fusion of a wrist-worn device (smartwatch) and a smartphone for human activity recognition. We evaluate these two devices for their strengths and weaknesses in recognizing various daily physical activities. We use three classifiers to recognize 13 different activities, such as smoking, eating, typing, writing, drinking coffee, giving a talk, walking, jogging, biking, walking upstairs, walking downstairs, sitting, and standing. Some complex activities, such as smoking, eating, drinking coffee, giving a talk, writing, and typing cannot be recognized with a smartphone in the pocket position alone. We show that the combination of a smartwatch and a smartphone recognizes such activities with a reasonable accuracy. The recognition of such complex activities can enable well-being applications for detecting bad habits, such as smoking, missing a meal, and drinking too much coffee. We also show how to fuse information from these devices in an energy-efficient way by using low sampling rates. We make our dataset publicly available in order to make our work reproducible.

AB - Recently, there has been a growing interest in the research community about using wrist-worn devices, such as smartwatches for human activity recognition, since these devices are equipped with various sensors such as an accelerometer and a gyroscope. Similarly, smartphones are already being used for activity recognition. In this paper, we study the fusion of a wrist-worn device (smartwatch) and a smartphone for human activity recognition. We evaluate these two devices for their strengths and weaknesses in recognizing various daily physical activities. We use three classifiers to recognize 13 different activities, such as smoking, eating, typing, writing, drinking coffee, giving a talk, walking, jogging, biking, walking upstairs, walking downstairs, sitting, and standing. Some complex activities, such as smoking, eating, drinking coffee, giving a talk, writing, and typing cannot be recognized with a smartphone in the pocket position alone. We show that the combination of a smartwatch and a smartphone recognizes such activities with a reasonable accuracy. The recognition of such complex activities can enable well-being applications for detecting bad habits, such as smoking, missing a meal, and drinking too much coffee. We also show how to fuse information from these devices in an energy-efficient way by using low sampling rates. We make our dataset publicly available in order to make our work reproducible.

KW - EWI-26482

KW - METIS-315041

KW - IR-98394

U2 - 10.1109/PERCOMW.2015.7134104

DO - 10.1109/PERCOMW.2015.7134104

M3 - Conference contribution

SN - 978-1-4799-8425-1

SP - 591

EP - 596

BT - Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015

PB - IEEE Computer Society

ER -

Shoaib M, Bosch S, Scholten J, Havinga PJM, Durmaz O. Towards detection of bad habits by fusing smartphone and smartwatch sensors. In Proceedings of the IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2015. USA: IEEE Computer Society. 2015. p. 591 -596. Available from, DOI: 10.1109/PERCOMW.2015.7134104