Energy-based decision engine for household human activity recognition

Anastasios Vafeiadis; Thanasis Vafeiadis; Stelios Zikos; Stelios Krinidis; Konstantinos Votis; Dimitrios Giakoumis; Dimosthenis Ioannidis; Dimitrios Tzovaras; Liming Chen; Raouf Hamzaoui

doi:10.1109/PERCOMW.2018.8480314

Energy-based decision engine for household human activity recognition

Anastasios Vafeiadis
, Thanasis Vafeiadis
, Stelios Zikos
, Stelios Krinidis
, Konstantinos Votis
, Dimitrios Giakoumis
, Dimosthenis Ioannidis
, Dimitrios Tzovaras
, Liming Chen
, Raouf Hamzaoui

Research output: Contribution to conference › Paper › peer-review

6 Citations (Scopus)

Abstract

We propose a framework for energy-based human activity recognition in a household environment. We apply machine learning techniques to infer the state of household appliances from their energy consumption data and use rule- based scenarios that exploit these states to detect human activity. Our decision engine achieved a 99.1% accuracy for real-world data collected in the kitchens of two smart homes.

Original language	English
Pages	704-709
DOIs	https://doi.org/10.1109/PERCOMW.2018.8480314
Publication status	Published (in print/issue) - Mar 2018
Event	2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) - Athens Duration: 19 Mar 2018 → 23 Mar 2018

Conference

Conference	2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)
Period	19/03/18 → 23/03/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access to Document

10.1109/PERCOMW.2018.8480314

https://ieeexplore.ieee.org/document/8480314/

Cite this

Vafeiadis, A., Vafeiadis, T., Zikos, S., Krinidis, S., Votis, K., Giakoumis, D., Ioannidis, D., Tzovaras, D., Chen, L., & Hamzaoui, R. (2018). Energy-based decision engine for household human activity recognition. 704-709. Paper presented at 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). https://doi.org/10.1109/PERCOMW.2018.8480314

@conference{4b84a0ba333b464db7b1f2e63273aa23,

title = "Energy-based decision engine for household human activity recognition",

abstract = "We propose a framework for energy-based human activity recognition in a household environment. We apply machine learning techniques to infer the state of household appliances from their energy consumption data and use rule- based scenarios that exploit these states to detect human activity. Our decision engine achieved a 99.1\% accuracy for real-world data collected in the kitchens of two smart homes.",

author = "Anastasios Vafeiadis and Thanasis Vafeiadis and Stelios Zikos and Stelios Krinidis and Konstantinos Votis and Dimitrios Giakoumis and Dimosthenis Ioannidis and Dimitrios Tzovaras and Liming Chen and Raouf Hamzaoui",

year = "2018",

month = mar,

doi = "10.1109/PERCOMW.2018.8480314",

language = "English",

pages = "704--709",

note = "2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) ; Conference date: 19-03-2018 Through 23-03-2018",

}

Vafeiadis, A, Vafeiadis, T, Zikos, S, Krinidis, S, Votis, K, Giakoumis, D, Ioannidis, D, Tzovaras, D, Chen, L & Hamzaoui, R 2018, 'Energy-based decision engine for household human activity recognition', Paper presented at 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 19/03/18 - 23/03/18 pp. 704-709. https://doi.org/10.1109/PERCOMW.2018.8480314

TY - CONF

T1 - Energy-based decision engine for household human activity recognition

AU - Vafeiadis, Anastasios

AU - Vafeiadis, Thanasis

AU - Zikos, Stelios

AU - Krinidis, Stelios

AU - Votis, Konstantinos

AU - Giakoumis, Dimitrios

AU - Ioannidis, Dimosthenis

AU - Tzovaras, Dimitrios

AU - Chen, Liming

AU - Hamzaoui, Raouf

PY - 2018/3

Y1 - 2018/3

N2 - We propose a framework for energy-based human activity recognition in a household environment. We apply machine learning techniques to infer the state of household appliances from their energy consumption data and use rule- based scenarios that exploit these states to detect human activity. Our decision engine achieved a 99.1% accuracy for real-world data collected in the kitchens of two smart homes.

AB - We propose a framework for energy-based human activity recognition in a household environment. We apply machine learning techniques to infer the state of household appliances from their energy consumption data and use rule- based scenarios that exploit these states to detect human activity. Our decision engine achieved a 99.1% accuracy for real-world data collected in the kitchens of two smart homes.

U2 - 10.1109/PERCOMW.2018.8480314

DO - 10.1109/PERCOMW.2018.8480314

M3 - Paper

SP - 704

EP - 709

T2 - 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)

Y2 - 19 March 2018 through 23 March 2018

ER -

Energy-based decision engine for household human activity recognition

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Cite this