Wearable sensor-based human activity recognition from environmental background sounds

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Understanding individual's activities, social interaction, and group dynamics of a certain society is one of fundamental problems that the social and community intelligence (SCI) research faces. Environmental background sound is a rich information source for identifying individual and social behaviors. Therefore, many power-aware wearable devices with sound recognition function are widely used to trace and understand human activities. The design of these sound recognition algorithms has two major challenges: limited computation resources and a strict power consumption requirement. In this paper, a new method for recognizing environmental background sounds with a power-aware wearable sensor is presented. By employing a novel low calculation one-dimensional (1-D) Haar-like sound feature with hidden Markov model (HMM) classification, this method can achieve high recognition accuracy while still meeting the wearable sensor's power requirement. Our experimental results indicate an average recognition accuracy of 96.9 % has been achieved when testing with 22 typical environmental sounds related to personal and social activities. It outperforms other commonly used sound recognition algorithms in terms of both accuracy and power consumption. This is very helpful and promising for future integration with other sensor(s) to provide more trustworthy activity recognition results for the SCI system.

Original languageEnglish
Pages (from-to)77-89
Number of pages13
JournalJournal of Ambient Intelligence and Humanized Computing
Volume5
Issue number1
DOIs
Publication statusPublished - 2014

Fingerprint

Acoustic waves
Electric power utilization
Hidden Markov models
Wearable sensors
Sensors
Testing

Keywords

  • Digital footprint
  • Haar-like feature
  • HMM
  • Social and community intelligence
  • Sound recognition
  • WSNs

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

@article{c49841268ea24be8a14f21e97decda60,
title = "Wearable sensor-based human activity recognition from environmental background sounds",
abstract = "Understanding individual's activities, social interaction, and group dynamics of a certain society is one of fundamental problems that the social and community intelligence (SCI) research faces. Environmental background sound is a rich information source for identifying individual and social behaviors. Therefore, many power-aware wearable devices with sound recognition function are widely used to trace and understand human activities. The design of these sound recognition algorithms has two major challenges: limited computation resources and a strict power consumption requirement. In this paper, a new method for recognizing environmental background sounds with a power-aware wearable sensor is presented. By employing a novel low calculation one-dimensional (1-D) Haar-like sound feature with hidden Markov model (HMM) classification, this method can achieve high recognition accuracy while still meeting the wearable sensor's power requirement. Our experimental results indicate an average recognition accuracy of 96.9 {\%} has been achieved when testing with 22 typical environmental sounds related to personal and social activities. It outperforms other commonly used sound recognition algorithms in terms of both accuracy and power consumption. This is very helpful and promising for future integration with other sensor(s) to provide more trustworthy activity recognition results for the SCI system.",
keywords = "Digital footprint, Haar-like feature, HMM, Social and community intelligence, Sound recognition, WSNs",
author = "Yi Zhan and Tadahiro Kuroda",
year = "2014",
doi = "10.1007/s12652-012-0122-2",
language = "English",
volume = "5",
pages = "77--89",
journal = "Journal of Ambient Intelligence and Humanized Computing",
issn = "1868-5137",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Wearable sensor-based human activity recognition from environmental background sounds

AU - Zhan, Yi

AU - Kuroda, Tadahiro

PY - 2014

Y1 - 2014

N2 - Understanding individual's activities, social interaction, and group dynamics of a certain society is one of fundamental problems that the social and community intelligence (SCI) research faces. Environmental background sound is a rich information source for identifying individual and social behaviors. Therefore, many power-aware wearable devices with sound recognition function are widely used to trace and understand human activities. The design of these sound recognition algorithms has two major challenges: limited computation resources and a strict power consumption requirement. In this paper, a new method for recognizing environmental background sounds with a power-aware wearable sensor is presented. By employing a novel low calculation one-dimensional (1-D) Haar-like sound feature with hidden Markov model (HMM) classification, this method can achieve high recognition accuracy while still meeting the wearable sensor's power requirement. Our experimental results indicate an average recognition accuracy of 96.9 % has been achieved when testing with 22 typical environmental sounds related to personal and social activities. It outperforms other commonly used sound recognition algorithms in terms of both accuracy and power consumption. This is very helpful and promising for future integration with other sensor(s) to provide more trustworthy activity recognition results for the SCI system.

AB - Understanding individual's activities, social interaction, and group dynamics of a certain society is one of fundamental problems that the social and community intelligence (SCI) research faces. Environmental background sound is a rich information source for identifying individual and social behaviors. Therefore, many power-aware wearable devices with sound recognition function are widely used to trace and understand human activities. The design of these sound recognition algorithms has two major challenges: limited computation resources and a strict power consumption requirement. In this paper, a new method for recognizing environmental background sounds with a power-aware wearable sensor is presented. By employing a novel low calculation one-dimensional (1-D) Haar-like sound feature with hidden Markov model (HMM) classification, this method can achieve high recognition accuracy while still meeting the wearable sensor's power requirement. Our experimental results indicate an average recognition accuracy of 96.9 % has been achieved when testing with 22 typical environmental sounds related to personal and social activities. It outperforms other commonly used sound recognition algorithms in terms of both accuracy and power consumption. This is very helpful and promising for future integration with other sensor(s) to provide more trustworthy activity recognition results for the SCI system.

KW - Digital footprint

KW - Haar-like feature

KW - HMM

KW - Social and community intelligence

KW - Sound recognition

KW - WSNs

UR - http://www.scopus.com/inward/record.url?scp=84894089084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894089084&partnerID=8YFLogxK

U2 - 10.1007/s12652-012-0122-2

DO - 10.1007/s12652-012-0122-2

M3 - Article

AN - SCOPUS:84894089084

VL - 5

SP - 77

EP - 89

JO - Journal of Ambient Intelligence and Humanized Computing

JF - Journal of Ambient Intelligence and Humanized Computing

SN - 1868-5137

IS - 1

ER -