Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage

Ik Hyun Youn, Jong-Hoon Youn, Jung Min Lee, Chol Seong Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

During a sea voyage, seafarers live on an unstable surface that demands unusual physical activity patterns. Previous studies recognized physical inactivity patterns in their special living environment. This study aims to develop a new sit-to-stand transition detection method based on physical activity classification models using wearable sensors to objectively assess the unstable physical activity patterns of seafarers. The sit-to-stand event detection was selected to improve the classification accuracy of the static activities including sitting and standing during the physical inactivity patterns. Anomaly detection was applied to handle imbalanced training data of sit-to-stand events. A single wearable sensor was attached in a chest pocket of the uniform to extract the upper trunk motion features such as body angle and dynamics. Two classification models with and without sit-to-stand event detection were developed and compared with each other to evaluate the efficacy of the sit-to-stand event detection in classifying the mariners’ physical activity. Our experimental results showed that the sit-to-stand event detection-based model significantly improved the classification accuracy of static activities. We expect that the proposed model can be integrated into a continuous physical activity monitoring system for the objective assessment of mariner’s physical health in an unstable living environment.

Original languageEnglish (US)
Pages (from-to)S444-S447
JournalBiomedical Research (India)
Volume2018
Issue numberSpecial Issue MedicalDiagnosisandStudyofBiomedicalImagingSys...
StatePublished - Jan 1 2018

Fingerprint

Oceans and Seas
Thorax
Health
Monitoring
Wearable sensors

Keywords

  • Imbalance data training
  • Seafarer’s physical activity classification
  • Sit-to-stand detection
  • Unstable living environment
  • Wearable sensor

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Youn, I. H., Youn, J-H., Lee, J. M., & Kim, C. S. (2018). Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage. Biomedical Research (India), 2018(Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys...), S444-S447.

Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage. / Youn, Ik Hyun; Youn, Jong-Hoon; Lee, Jung Min; Kim, Chol Seong.

In: Biomedical Research (India), Vol. 2018, No. Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys..., 01.01.2018, p. S444-S447.

Research output: Contribution to journalArticle

Youn, IH, Youn, J-H, Lee, JM & Kim, CS 2018, 'Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage', Biomedical Research (India), vol. 2018, no. Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys..., pp. S444-S447.
Youn IH, Youn J-H, Lee JM, Kim CS. Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage. Biomedical Research (India). 2018 Jan 1;2018(Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys...):S444-S447.
Youn, Ik Hyun ; Youn, Jong-Hoon ; Lee, Jung Min ; Kim, Chol Seong. / Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage. In: Biomedical Research (India). 2018 ; Vol. 2018, No. Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys... pp. S444-S447.
@article{023dd5640bdf48cbb586bd9eb199296c,
title = "Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage",
abstract = "During a sea voyage, seafarers live on an unstable surface that demands unusual physical activity patterns. Previous studies recognized physical inactivity patterns in their special living environment. This study aims to develop a new sit-to-stand transition detection method based on physical activity classification models using wearable sensors to objectively assess the unstable physical activity patterns of seafarers. The sit-to-stand event detection was selected to improve the classification accuracy of the static activities including sitting and standing during the physical inactivity patterns. Anomaly detection was applied to handle imbalanced training data of sit-to-stand events. A single wearable sensor was attached in a chest pocket of the uniform to extract the upper trunk motion features such as body angle and dynamics. Two classification models with and without sit-to-stand event detection were developed and compared with each other to evaluate the efficacy of the sit-to-stand event detection in classifying the mariners’ physical activity. Our experimental results showed that the sit-to-stand event detection-based model significantly improved the classification accuracy of static activities. We expect that the proposed model can be integrated into a continuous physical activity monitoring system for the objective assessment of mariner’s physical health in an unstable living environment.",
keywords = "Imbalance data training, Seafarer’s physical activity classification, Sit-to-stand detection, Unstable living environment, Wearable sensor",
author = "Youn, {Ik Hyun} and Jong-Hoon Youn and Lee, {Jung Min} and Kim, {Chol Seong}",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2018",
pages = "S444--S447",
journal = "Biomedical Research",
issn = "0970-938X",
publisher = "Scientific Publishers of India",
number = "Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys...",

}

TY - JOUR

T1 - Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage

AU - Youn, Ik Hyun

AU - Youn, Jong-Hoon

AU - Lee, Jung Min

AU - Kim, Chol Seong

PY - 2018/1/1

Y1 - 2018/1/1

N2 - During a sea voyage, seafarers live on an unstable surface that demands unusual physical activity patterns. Previous studies recognized physical inactivity patterns in their special living environment. This study aims to develop a new sit-to-stand transition detection method based on physical activity classification models using wearable sensors to objectively assess the unstable physical activity patterns of seafarers. The sit-to-stand event detection was selected to improve the classification accuracy of the static activities including sitting and standing during the physical inactivity patterns. Anomaly detection was applied to handle imbalanced training data of sit-to-stand events. A single wearable sensor was attached in a chest pocket of the uniform to extract the upper trunk motion features such as body angle and dynamics. Two classification models with and without sit-to-stand event detection were developed and compared with each other to evaluate the efficacy of the sit-to-stand event detection in classifying the mariners’ physical activity. Our experimental results showed that the sit-to-stand event detection-based model significantly improved the classification accuracy of static activities. We expect that the proposed model can be integrated into a continuous physical activity monitoring system for the objective assessment of mariner’s physical health in an unstable living environment.

AB - During a sea voyage, seafarers live on an unstable surface that demands unusual physical activity patterns. Previous studies recognized physical inactivity patterns in their special living environment. This study aims to develop a new sit-to-stand transition detection method based on physical activity classification models using wearable sensors to objectively assess the unstable physical activity patterns of seafarers. The sit-to-stand event detection was selected to improve the classification accuracy of the static activities including sitting and standing during the physical inactivity patterns. Anomaly detection was applied to handle imbalanced training data of sit-to-stand events. A single wearable sensor was attached in a chest pocket of the uniform to extract the upper trunk motion features such as body angle and dynamics. Two classification models with and without sit-to-stand event detection were developed and compared with each other to evaluate the efficacy of the sit-to-stand event detection in classifying the mariners’ physical activity. Our experimental results showed that the sit-to-stand event detection-based model significantly improved the classification accuracy of static activities. We expect that the proposed model can be integrated into a continuous physical activity monitoring system for the objective assessment of mariner’s physical health in an unstable living environment.

KW - Imbalance data training

KW - Seafarer’s physical activity classification

KW - Sit-to-stand detection

KW - Unstable living environment

KW - Wearable sensor

UR - http://www.scopus.com/inward/record.url?scp=85044201765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044201765&partnerID=8YFLogxK

M3 - Article

VL - 2018

SP - S444-S447

JO - Biomedical Research

JF - Biomedical Research

SN - 0970-938X

IS - Special Issue MedicalDiagnosisandStudyofBiomedicalImagingSys...

ER -