Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions

Kenki Ueda, Hirohiko Suwa, Yutaka Arakawa, Keiichi Yasumoto

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

11 Citations (Scopus)

Abstract

Advanced context-aware services at home such as elderly monitoring requires highly accurate living activity recognition in a home environment. Existing studies on living activity recognition suffer from high deployment and maintenance costs, privacy intrusion due to utilization of cameras and microphones, and few recognizable activities or low recognition accuracy. In this paper, to solve these problems, we propose a new living activity recognition method. Our method utilizes only power meters attached to appliances and a positioning sensor attached to a resident of a home to mitigate privacy intrusion. We target 10 different living activities which cover most of our daily lives at home and construct activity recognition models based on machineleaning. To accurately recognize the activities from the sensor data by power meters and position sensor, we explore the best combination of time window width for samples of training/test data, features, and machine-learning algorithms. Furthermore, we thoroughly investigate the tradeoff between the sensor data granularity and the consequent recognition accuracy. Through experiments using sensor data collected by four participants in our smart home, the proposed method achieved 97.8 % average F-measure of recognizing 10 target activities with the finest sensor data granularity (position estimation error ≤ 0.1m, 16 power meters) and 86.9 % F-measure with room-level position accuracy and one power meter for each of four rooms.

Original languageEnglish
Title of host publicationProceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015
EditorsLuigi Atzori, Xiaolong Jin, Stephen Jarvis, Lei Liu, Ramon Aguero Calvo, Jia Hu, Geyong Min, Nektarios Georgalas, Yulei Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1130-1137
Number of pages8
ISBN (Electronic)9781509001545
DOIs
Publication statusPublished - Dec 22 2015
Externally publishedYes
Event15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015 - Liverpool, United Kingdom
Duration: Oct 26 2015Oct 28 2015

Publication series

NameProceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015

Conference

Conference15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015
CountryUnited Kingdom
CityLiverpool
Period10/26/1510/28/15

Fingerprint

Electric power utilization
Sensors
Costs
Microphones
Error analysis
Learning algorithms
Learning systems
Cameras
Monitoring
Experiments

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Ueda, K., Suwa, H., Arakawa, Y., & Yasumoto, K. (2015). Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions. In L. Atzori, X. Jin, S. Jarvis, L. Liu, R. A. Calvo, J. Hu, G. Min, N. Georgalas, ... Y. Wu (Eds.), Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015 (pp. 1130-1137). [7363213] (Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.169

Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions. / Ueda, Kenki; Suwa, Hirohiko; Arakawa, Yutaka; Yasumoto, Keiichi.

Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015. ed. / Luigi Atzori; Xiaolong Jin; Stephen Jarvis; Lei Liu; Ramon Aguero Calvo; Jia Hu; Geyong Min; Nektarios Georgalas; Yulei Wu. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1130-1137 7363213 (Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015).

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

Ueda, K, Suwa, H, Arakawa, Y & Yasumoto, K 2015, Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions. in L Atzori, X Jin, S Jarvis, L Liu, RA Calvo, J Hu, G Min, N Georgalas & Y Wu (eds), Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015., 7363213, Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015, Institute of Electrical and Electronics Engineers Inc., pp. 1130-1137, 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015, Liverpool, United Kingdom, 10/26/15. https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.169
Ueda K, Suwa H, Arakawa Y, Yasumoto K. Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions. In Atzori L, Jin X, Jarvis S, Liu L, Calvo RA, Hu J, Min G, Georgalas N, Wu Y, editors, Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1130-1137. 7363213. (Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015). https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.169
Ueda, Kenki ; Suwa, Hirohiko ; Arakawa, Yutaka ; Yasumoto, Keiichi. / Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions. Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015. editor / Luigi Atzori ; Xiaolong Jin ; Stephen Jarvis ; Lei Liu ; Ramon Aguero Calvo ; Jia Hu ; Geyong Min ; Nektarios Georgalas ; Yulei Wu. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1130-1137 (Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015).
@inproceedings{fa00356c7f8649cd85d64c2d36ee2d65,
title = "Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions",
abstract = "Advanced context-aware services at home such as elderly monitoring requires highly accurate living activity recognition in a home environment. Existing studies on living activity recognition suffer from high deployment and maintenance costs, privacy intrusion due to utilization of cameras and microphones, and few recognizable activities or low recognition accuracy. In this paper, to solve these problems, we propose a new living activity recognition method. Our method utilizes only power meters attached to appliances and a positioning sensor attached to a resident of a home to mitigate privacy intrusion. We target 10 different living activities which cover most of our daily lives at home and construct activity recognition models based on machineleaning. To accurately recognize the activities from the sensor data by power meters and position sensor, we explore the best combination of time window width for samples of training/test data, features, and machine-learning algorithms. Furthermore, we thoroughly investigate the tradeoff between the sensor data granularity and the consequent recognition accuracy. Through experiments using sensor data collected by four participants in our smart home, the proposed method achieved 97.8 {\%} average F-measure of recognizing 10 target activities with the finest sensor data granularity (position estimation error ≤ 0.1m, 16 power meters) and 86.9 {\%} F-measure with room-level position accuracy and one power meter for each of four rooms.",
author = "Kenki Ueda and Hirohiko Suwa and Yutaka Arakawa and Keiichi Yasumoto",
year = "2015",
month = "12",
day = "22",
doi = "10.1109/CIT/IUCC/DASC/PICOM.2015.169",
language = "English",
series = "Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1130--1137",
editor = "Luigi Atzori and Xiaolong Jin and Stephen Jarvis and Lei Liu and Calvo, {Ramon Aguero} and Jia Hu and Geyong Min and Nektarios Georgalas and Yulei Wu",
booktitle = "Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015",
address = "United States",

}

TY - GEN

T1 - Exploring accuracy-cost tradeoff in in-home living activity recognition based on power consumptions and user positions

AU - Ueda, Kenki

AU - Suwa, Hirohiko

AU - Arakawa, Yutaka

AU - Yasumoto, Keiichi

PY - 2015/12/22

Y1 - 2015/12/22

N2 - Advanced context-aware services at home such as elderly monitoring requires highly accurate living activity recognition in a home environment. Existing studies on living activity recognition suffer from high deployment and maintenance costs, privacy intrusion due to utilization of cameras and microphones, and few recognizable activities or low recognition accuracy. In this paper, to solve these problems, we propose a new living activity recognition method. Our method utilizes only power meters attached to appliances and a positioning sensor attached to a resident of a home to mitigate privacy intrusion. We target 10 different living activities which cover most of our daily lives at home and construct activity recognition models based on machineleaning. To accurately recognize the activities from the sensor data by power meters and position sensor, we explore the best combination of time window width for samples of training/test data, features, and machine-learning algorithms. Furthermore, we thoroughly investigate the tradeoff between the sensor data granularity and the consequent recognition accuracy. Through experiments using sensor data collected by four participants in our smart home, the proposed method achieved 97.8 % average F-measure of recognizing 10 target activities with the finest sensor data granularity (position estimation error ≤ 0.1m, 16 power meters) and 86.9 % F-measure with room-level position accuracy and one power meter for each of four rooms.

AB - Advanced context-aware services at home such as elderly monitoring requires highly accurate living activity recognition in a home environment. Existing studies on living activity recognition suffer from high deployment and maintenance costs, privacy intrusion due to utilization of cameras and microphones, and few recognizable activities or low recognition accuracy. In this paper, to solve these problems, we propose a new living activity recognition method. Our method utilizes only power meters attached to appliances and a positioning sensor attached to a resident of a home to mitigate privacy intrusion. We target 10 different living activities which cover most of our daily lives at home and construct activity recognition models based on machineleaning. To accurately recognize the activities from the sensor data by power meters and position sensor, we explore the best combination of time window width for samples of training/test data, features, and machine-learning algorithms. Furthermore, we thoroughly investigate the tradeoff between the sensor data granularity and the consequent recognition accuracy. Through experiments using sensor data collected by four participants in our smart home, the proposed method achieved 97.8 % average F-measure of recognizing 10 target activities with the finest sensor data granularity (position estimation error ≤ 0.1m, 16 power meters) and 86.9 % F-measure with room-level position accuracy and one power meter for each of four rooms.

UR - http://www.scopus.com/inward/record.url?scp=84964310792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964310792&partnerID=8YFLogxK

U2 - 10.1109/CIT/IUCC/DASC/PICOM.2015.169

DO - 10.1109/CIT/IUCC/DASC/PICOM.2015.169

M3 - Conference contribution

AN - SCOPUS:84964310792

T3 - Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015

SP - 1130

EP - 1137

BT - Proceedings - 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 14th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2015, 13th IEEE International Conference on Dependable, Autonomic and Secure Computing, DASC 2015 and 13th IEEE International Conference on Pervasive Intelligence and Computing, PICom 2015

A2 - Atzori, Luigi

A2 - Jin, Xiaolong

A2 - Jarvis, Stephen

A2 - Liu, Lei

A2 - Calvo, Ramon Aguero

A2 - Hu, Jia

A2 - Min, Geyong

A2 - Georgalas, Nektarios

A2 - Wu, Yulei

PB - Institute of Electrical and Electronics Engineers Inc.

ER -