Indoor Occupancy Estimation via Location-Aware HMM

An IoT Approach

Masahiro Yoshida, Sofia Kleisarchaki, Levent Gtirgen, Hiroaki Nishi

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

Abstract

Indoor occupancy estimation is a critical analytical task for several applications (e.g., social isolation of elderlies). The proliferation of Internet of Things (IoT) devices enabled the occupancy estimation, as it provided access to a mass amount of data. Several works have been proposed exploiting the IoT Passive Inference (PIR) or environmental (e.g., CO2) features. These works however are traditionally selecting the feature space at the learning phase and passively using it over time. Hence, they ignore the dynamics of indoor occupancy, such as the location of the occupant or his motion patterns, leading to a decreasing accuracy over time. In this paper, we study those dynamics and show that motion patterns, along with environmental features favor the occupancy estimation. We design a Location-Aware Hidden Markov Model (HMM), which dynamically adapts the feature space based on the occupant's location. Our experiments on real data show that Location-Aware HMM can reach up to 10% better accuracy than Conventional HMM.

Original languageEnglish
Title of host publication19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781538647257
DOIs
Publication statusPublished - 2018 Aug 28
Event19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018 - Chania, Greece
Duration: 2018 Jun 122018 Jun 15

Other

Other19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018
CountryGreece
CityChania
Period18/6/1218/6/15

Fingerprint

Hidden Markov models
Internet of things
Experiments

Keywords

  • Internet of Things (IoT)
  • Location-Aware Hidden Markov Model
  • Occupancy Estimation

ASJC Scopus subject areas

  • Media Technology
  • Computer Networks and Communications

Cite this

Yoshida, M., Kleisarchaki, S., Gtirgen, L., & Nishi, H. (2018). Indoor Occupancy Estimation via Location-Aware HMM: An IoT Approach. In 19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018 [8449765] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WoWMoM.2018.8449765

Indoor Occupancy Estimation via Location-Aware HMM : An IoT Approach. / Yoshida, Masahiro; Kleisarchaki, Sofia; Gtirgen, Levent; Nishi, Hiroaki.

19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8449765.

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

Yoshida, M, Kleisarchaki, S, Gtirgen, L & Nishi, H 2018, Indoor Occupancy Estimation via Location-Aware HMM: An IoT Approach. in 19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018., 8449765, Institute of Electrical and Electronics Engineers Inc., 19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018, Chania, Greece, 18/6/12. https://doi.org/10.1109/WoWMoM.2018.8449765
Yoshida M, Kleisarchaki S, Gtirgen L, Nishi H. Indoor Occupancy Estimation via Location-Aware HMM: An IoT Approach. In 19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8449765 https://doi.org/10.1109/WoWMoM.2018.8449765
Yoshida, Masahiro ; Kleisarchaki, Sofia ; Gtirgen, Levent ; Nishi, Hiroaki. / Indoor Occupancy Estimation via Location-Aware HMM : An IoT Approach. 19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018. Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{37a036b9dfd4454bab5329165c560f22,
title = "Indoor Occupancy Estimation via Location-Aware HMM: An IoT Approach",
abstract = "Indoor occupancy estimation is a critical analytical task for several applications (e.g., social isolation of elderlies). The proliferation of Internet of Things (IoT) devices enabled the occupancy estimation, as it provided access to a mass amount of data. Several works have been proposed exploiting the IoT Passive Inference (PIR) or environmental (e.g., CO2) features. These works however are traditionally selecting the feature space at the learning phase and passively using it over time. Hence, they ignore the dynamics of indoor occupancy, such as the location of the occupant or his motion patterns, leading to a decreasing accuracy over time. In this paper, we study those dynamics and show that motion patterns, along with environmental features favor the occupancy estimation. We design a Location-Aware Hidden Markov Model (HMM), which dynamically adapts the feature space based on the occupant's location. Our experiments on real data show that Location-Aware HMM can reach up to 10{\%} better accuracy than Conventional HMM.",
keywords = "Internet of Things (IoT), Location-Aware Hidden Markov Model, Occupancy Estimation",
author = "Masahiro Yoshida and Sofia Kleisarchaki and Levent Gtirgen and Hiroaki Nishi",
year = "2018",
month = "8",
day = "28",
doi = "10.1109/WoWMoM.2018.8449765",
language = "English",
isbn = "9781538647257",
booktitle = "19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Indoor Occupancy Estimation via Location-Aware HMM

T2 - An IoT Approach

AU - Yoshida, Masahiro

AU - Kleisarchaki, Sofia

AU - Gtirgen, Levent

AU - Nishi, Hiroaki

PY - 2018/8/28

Y1 - 2018/8/28

N2 - Indoor occupancy estimation is a critical analytical task for several applications (e.g., social isolation of elderlies). The proliferation of Internet of Things (IoT) devices enabled the occupancy estimation, as it provided access to a mass amount of data. Several works have been proposed exploiting the IoT Passive Inference (PIR) or environmental (e.g., CO2) features. These works however are traditionally selecting the feature space at the learning phase and passively using it over time. Hence, they ignore the dynamics of indoor occupancy, such as the location of the occupant or his motion patterns, leading to a decreasing accuracy over time. In this paper, we study those dynamics and show that motion patterns, along with environmental features favor the occupancy estimation. We design a Location-Aware Hidden Markov Model (HMM), which dynamically adapts the feature space based on the occupant's location. Our experiments on real data show that Location-Aware HMM can reach up to 10% better accuracy than Conventional HMM.

AB - Indoor occupancy estimation is a critical analytical task for several applications (e.g., social isolation of elderlies). The proliferation of Internet of Things (IoT) devices enabled the occupancy estimation, as it provided access to a mass amount of data. Several works have been proposed exploiting the IoT Passive Inference (PIR) or environmental (e.g., CO2) features. These works however are traditionally selecting the feature space at the learning phase and passively using it over time. Hence, they ignore the dynamics of indoor occupancy, such as the location of the occupant or his motion patterns, leading to a decreasing accuracy over time. In this paper, we study those dynamics and show that motion patterns, along with environmental features favor the occupancy estimation. We design a Location-Aware Hidden Markov Model (HMM), which dynamically adapts the feature space based on the occupant's location. Our experiments on real data show that Location-Aware HMM can reach up to 10% better accuracy than Conventional HMM.

KW - Internet of Things (IoT)

KW - Location-Aware Hidden Markov Model

KW - Occupancy Estimation

UR - http://www.scopus.com/inward/record.url?scp=85053771895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053771895&partnerID=8YFLogxK

U2 - 10.1109/WoWMoM.2018.8449765

DO - 10.1109/WoWMoM.2018.8449765

M3 - Conference contribution

SN - 9781538647257

BT - 19th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -