A framework for group activity detection and recognition using smartphone sensors and beacons

Hao Chen, Seung Hyun Cha, Tae Wan Kim

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Understanding occupant activities in a building is essential for building management systems to provide occupants with comfort and intelligent indoor environment. However, current occupant activity recognition mainly focuses on individual activity. Group activity recognition indoors has gained little attention, but remains of paramount importance, such as working together, taking classes, and discussions. In this paper, we propose a framework for group activity detection and recognition (i.e., GADAR framework) using smartphone sensors and Bluetooth beacons data. This framework consists of the following four layers: user layer, data package layer, processing layer, and output layer. As individuals within the group show similarity in motion, audio, and proximity, such similarity values are calculated and clustered into groups using hierarchical clustering. The framework then extracts the role, motion, speaking and location features from the clustered groups to distinguish different group activities. Decision tree classifier was selected to recognize the group activity that the group is engaged in. An experiment was conducted to identify the following three common group activities: taking class, seminar, and discussion. The result shows that the proposed GADAR framework could provide more than 89% accuracy in group detection and 89% accuracy in recognizing group activity.

Original languageEnglish
Pages (from-to)205-216
Number of pages12
JournalBuilding and Environment
Volume158
DOIs
StatePublished - 2019 Jul 1

Fingerprint

Smartphones
Bluetooth
Technical presentations
Decision trees
Classifiers
sensor
Sensors
Processing
Group
Experiments
detection
speaking
experiment

Keywords

  • Building management system
  • Group activity recognition
  • Group detection
  • Smart building

Cite this

@article{3a96565ff9ac423fbf1f17b091d3a8b5,
title = "A framework for group activity detection and recognition using smartphone sensors and beacons",
abstract = "Understanding occupant activities in a building is essential for building management systems to provide occupants with comfort and intelligent indoor environment. However, current occupant activity recognition mainly focuses on individual activity. Group activity recognition indoors has gained little attention, but remains of paramount importance, such as working together, taking classes, and discussions. In this paper, we propose a framework for group activity detection and recognition (i.e., GADAR framework) using smartphone sensors and Bluetooth beacons data. This framework consists of the following four layers: user layer, data package layer, processing layer, and output layer. As individuals within the group show similarity in motion, audio, and proximity, such similarity values are calculated and clustered into groups using hierarchical clustering. The framework then extracts the role, motion, speaking and location features from the clustered groups to distinguish different group activities. Decision tree classifier was selected to recognize the group activity that the group is engaged in. An experiment was conducted to identify the following three common group activities: taking class, seminar, and discussion. The result shows that the proposed GADAR framework could provide more than 89{\%} accuracy in group detection and 89{\%} accuracy in recognizing group activity.",
keywords = "Building management system, Group activity recognition, Group detection, Smart building",
author = "Hao Chen and Cha, {Seung Hyun} and Kim, {Tae Wan}",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.buildenv.2019.05.016",
language = "English",
volume = "158",
pages = "205--216",
journal = "Building and Environment",
issn = "0360-1323",

}

A framework for group activity detection and recognition using smartphone sensors and beacons. / Chen, Hao; Cha, Seung Hyun; Kim, Tae Wan.

In: Building and Environment, Vol. 158, 01.07.2019, p. 205-216.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A framework for group activity detection and recognition using smartphone sensors and beacons

AU - Chen, Hao

AU - Cha, Seung Hyun

AU - Kim, Tae Wan

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Understanding occupant activities in a building is essential for building management systems to provide occupants with comfort and intelligent indoor environment. However, current occupant activity recognition mainly focuses on individual activity. Group activity recognition indoors has gained little attention, but remains of paramount importance, such as working together, taking classes, and discussions. In this paper, we propose a framework for group activity detection and recognition (i.e., GADAR framework) using smartphone sensors and Bluetooth beacons data. This framework consists of the following four layers: user layer, data package layer, processing layer, and output layer. As individuals within the group show similarity in motion, audio, and proximity, such similarity values are calculated and clustered into groups using hierarchical clustering. The framework then extracts the role, motion, speaking and location features from the clustered groups to distinguish different group activities. Decision tree classifier was selected to recognize the group activity that the group is engaged in. An experiment was conducted to identify the following three common group activities: taking class, seminar, and discussion. The result shows that the proposed GADAR framework could provide more than 89% accuracy in group detection and 89% accuracy in recognizing group activity.

AB - Understanding occupant activities in a building is essential for building management systems to provide occupants with comfort and intelligent indoor environment. However, current occupant activity recognition mainly focuses on individual activity. Group activity recognition indoors has gained little attention, but remains of paramount importance, such as working together, taking classes, and discussions. In this paper, we propose a framework for group activity detection and recognition (i.e., GADAR framework) using smartphone sensors and Bluetooth beacons data. This framework consists of the following four layers: user layer, data package layer, processing layer, and output layer. As individuals within the group show similarity in motion, audio, and proximity, such similarity values are calculated and clustered into groups using hierarchical clustering. The framework then extracts the role, motion, speaking and location features from the clustered groups to distinguish different group activities. Decision tree classifier was selected to recognize the group activity that the group is engaged in. An experiment was conducted to identify the following three common group activities: taking class, seminar, and discussion. The result shows that the proposed GADAR framework could provide more than 89% accuracy in group detection and 89% accuracy in recognizing group activity.

KW - Building management system

KW - Group activity recognition

KW - Group detection

KW - Smart building

UR - http://www.scopus.com/inward/record.url?scp=85065620233&partnerID=8YFLogxK

U2 - 10.1016/j.buildenv.2019.05.016

DO - 10.1016/j.buildenv.2019.05.016

M3 - Article

VL - 158

SP - 205

EP - 216

JO - Building and Environment

JF - Building and Environment

SN - 0360-1323

ER -