Human activity recognition by wearable sensors in the smart home control problem

Standard

Human activity recognition by wearable sensors in the smart home control problem. / Nebogatikov, I. Y.; Soloviev, I. P.

In: Journal of Physics: Conference Series, Vol. 1864, No. 1, 012112, 20.05.2021.

Research output: Contribution to journal › Conference article › peer-review

BibTeX

@article{1911d087e3fa44ac87ed220e377e179f,

title = "Human activity recognition by wearable sensors in the smart home control problem",

abstract = "In this work we analyze and compare machine learning methods for recognizing human activity in the context of smart home by using data obtained from an optical heartbeat sensor and an accelerometer embedded in a smart watch, and find a number of activity classes that can be predicted. The conclusion is made that for such type of problems the random forest method with about 10 classes shows the best results.",

author = "Nebogatikov, {I. Y.} and Soloviev, {I. P.}",

note = "Publisher Copyright: {\textcopyright} Published under licence by IOP Publishing Ltd.; 13th Multiconference on Control Problems, MCCP 2020 ; Conference date: 06-10-2020 Through 08-10-2020",

year = "2021",

month = may,

day = "20",

doi = "10.1088/1742-6596/1864/1/012112",

language = "English",

volume = "1864",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "1",

url = "http://www.elektropribor.spb.ru/nauchnaya-deyatelnost/xiii-mkpu/index3.php",

}

RIS

TY - JOUR

T1 - Human activity recognition by wearable sensors in the smart home control problem

AU - Nebogatikov, I. Y.

AU - Soloviev, I. P.

N1 - Conference code: 13

PY - 2021/5/20

Y1 - 2021/5/20

N2 - In this work we analyze and compare machine learning methods for recognizing human activity in the context of smart home by using data obtained from an optical heartbeat sensor and an accelerometer embedded in a smart watch, and find a number of activity classes that can be predicted. The conclusion is made that for such type of problems the random forest method with about 10 classes shows the best results.

AB - In this work we analyze and compare machine learning methods for recognizing human activity in the context of smart home by using data obtained from an optical heartbeat sensor and an accelerometer embedded in a smart watch, and find a number of activity classes that can be predicted. The conclusion is made that for such type of problems the random forest method with about 10 classes shows the best results.

UR - http://www.scopus.com/inward/record.url?scp=85107398151&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/1864/1/012112

DO - 10.1088/1742-6596/1864/1/012112

M3 - Conference article

AN - SCOPUS:85107398151

VL - 1864

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012112

T2 - 13th Multiconference on Control Problems, MCCP 2020

Y2 - 6 October 2020 through 8 October 2020

ER -

ID: 86377540