Robust Automated Human Activity Recognition and Its Application to Sleep Research

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

6 Citations (Scopus)

Abstract

Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Pervasive sensors, such as wearable devices, have an increasing market penetration and generate a tremendous amount of data. The myriad of available clinical and consumer-grade wearables generate a continuous time series of a person's daily physical exertion and rest. Applying HAR to the activity time series can provide new insights by enriching the feature set in health studies, and enhancing the personalisation and effectiveness of health, wellness, and fitness applications. The analyses of complex health behaviours such as sleep, traditionally require a time-consuming manual interpretation by experts. This manual work is necessary due to the erratic periodicity and persistent noisiness of human behaviour. In this paper, we present a robust automated human activity recognition algorithm, which we call RAHAR. We test our algorithm in the application area of sleep research by providing a novel framework for evaluating sleep quality and examining the correlation between the aforementioned and an individual's physical activity. Our results improve the state-of-The-Art procedure in sleep research by 15% for area under ROC and by 30% for F1 score on average. However, application of RAHAR is not limited to sleep analysis and can be used for understanding other health problems such as obesity, diabetes, and cardiac diseases.

Original languageEnglish
Title of host publicationProceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016
PublisherIEEE Computer Society
Pages495-502
Number of pages8
ISBN (Electronic)9781509054725
DOIs
Publication statusPublished - 30 Jan 2017
Event16th IEEE International Conference on Data Mining Workshops, ICDMW 2016 - Barcelona, Spain
Duration: 12 Dec 201615 Dec 2016

Other

Other16th IEEE International Conference on Data Mining Workshops, ICDMW 2016
CountrySpain
CityBarcelona
Period12/12/1615/12/16

Fingerprint

Sleep research
Health
Medical problems
Time series
Sensors
Sleep

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Sathyanarayana, A., Ofli, F., Fernandez, L., Srivastava, J., Elmagarmid, A., Arora, T., & Taheri, S. (2017). Robust Automated Human Activity Recognition and Its Application to Sleep Research. In Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016 (pp. 495-502). [7836708] IEEE Computer Society. https://doi.org/10.1109/ICDMW.2016.0077

Robust Automated Human Activity Recognition and Its Application to Sleep Research. / Sathyanarayana, Aarti; Ofli, Ferda; Fernandez, Luis; Srivastava, Jaideep; Elmagarmid, Ahmed; Arora, Teresa; Taheri, Shahrad.

Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016. IEEE Computer Society, 2017. p. 495-502 7836708.

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

Sathyanarayana, A, Ofli, F, Fernandez, L, Srivastava, J, Elmagarmid, A, Arora, T & Taheri, S 2017, Robust Automated Human Activity Recognition and Its Application to Sleep Research. in Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016., 7836708, IEEE Computer Society, pp. 495-502, 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016, Barcelona, Spain, 12/12/16. https://doi.org/10.1109/ICDMW.2016.0077
Sathyanarayana A, Ofli F, Fernandez L, Srivastava J, Elmagarmid A, Arora T et al. Robust Automated Human Activity Recognition and Its Application to Sleep Research. In Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016. IEEE Computer Society. 2017. p. 495-502. 7836708 https://doi.org/10.1109/ICDMW.2016.0077
Sathyanarayana, Aarti ; Ofli, Ferda ; Fernandez, Luis ; Srivastava, Jaideep ; Elmagarmid, Ahmed ; Arora, Teresa ; Taheri, Shahrad. / Robust Automated Human Activity Recognition and Its Application to Sleep Research. Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016. IEEE Computer Society, 2017. pp. 495-502
@inproceedings{9c95fd5524494082a7affef184b116b2,
title = "Robust Automated Human Activity Recognition and Its Application to Sleep Research",
abstract = "Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Pervasive sensors, such as wearable devices, have an increasing market penetration and generate a tremendous amount of data. The myriad of available clinical and consumer-grade wearables generate a continuous time series of a person's daily physical exertion and rest. Applying HAR to the activity time series can provide new insights by enriching the feature set in health studies, and enhancing the personalisation and effectiveness of health, wellness, and fitness applications. The analyses of complex health behaviours such as sleep, traditionally require a time-consuming manual interpretation by experts. This manual work is necessary due to the erratic periodicity and persistent noisiness of human behaviour. In this paper, we present a robust automated human activity recognition algorithm, which we call RAHAR. We test our algorithm in the application area of sleep research by providing a novel framework for evaluating sleep quality and examining the correlation between the aforementioned and an individual's physical activity. Our results improve the state-of-The-Art procedure in sleep research by 15{\%} for area under ROC and by 30{\%} for F1 score on average. However, application of RAHAR is not limited to sleep analysis and can be used for understanding other health problems such as obesity, diabetes, and cardiac diseases.",
author = "Aarti Sathyanarayana and Ferda Ofli and Luis Fernandez and Jaideep Srivastava and Ahmed Elmagarmid and Teresa Arora and Shahrad Taheri",
year = "2017",
month = "1",
day = "30",
doi = "10.1109/ICDMW.2016.0077",
language = "English",
pages = "495--502",
booktitle = "Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Robust Automated Human Activity Recognition and Its Application to Sleep Research

AU - Sathyanarayana, Aarti

AU - Ofli, Ferda

AU - Fernandez, Luis

AU - Srivastava, Jaideep

AU - Elmagarmid, Ahmed

AU - Arora, Teresa

AU - Taheri, Shahrad

PY - 2017/1/30

Y1 - 2017/1/30

N2 - Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Pervasive sensors, such as wearable devices, have an increasing market penetration and generate a tremendous amount of data. The myriad of available clinical and consumer-grade wearables generate a continuous time series of a person's daily physical exertion and rest. Applying HAR to the activity time series can provide new insights by enriching the feature set in health studies, and enhancing the personalisation and effectiveness of health, wellness, and fitness applications. The analyses of complex health behaviours such as sleep, traditionally require a time-consuming manual interpretation by experts. This manual work is necessary due to the erratic periodicity and persistent noisiness of human behaviour. In this paper, we present a robust automated human activity recognition algorithm, which we call RAHAR. We test our algorithm in the application area of sleep research by providing a novel framework for evaluating sleep quality and examining the correlation between the aforementioned and an individual's physical activity. Our results improve the state-of-The-Art procedure in sleep research by 15% for area under ROC and by 30% for F1 score on average. However, application of RAHAR is not limited to sleep analysis and can be used for understanding other health problems such as obesity, diabetes, and cardiac diseases.

AB - Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Pervasive sensors, such as wearable devices, have an increasing market penetration and generate a tremendous amount of data. The myriad of available clinical and consumer-grade wearables generate a continuous time series of a person's daily physical exertion and rest. Applying HAR to the activity time series can provide new insights by enriching the feature set in health studies, and enhancing the personalisation and effectiveness of health, wellness, and fitness applications. The analyses of complex health behaviours such as sleep, traditionally require a time-consuming manual interpretation by experts. This manual work is necessary due to the erratic periodicity and persistent noisiness of human behaviour. In this paper, we present a robust automated human activity recognition algorithm, which we call RAHAR. We test our algorithm in the application area of sleep research by providing a novel framework for evaluating sleep quality and examining the correlation between the aforementioned and an individual's physical activity. Our results improve the state-of-The-Art procedure in sleep research by 15% for area under ROC and by 30% for F1 score on average. However, application of RAHAR is not limited to sleep analysis and can be used for understanding other health problems such as obesity, diabetes, and cardiac diseases.

UR - http://www.scopus.com/inward/record.url?scp=85015227318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015227318&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2016.0077

DO - 10.1109/ICDMW.2016.0077

M3 - Conference contribution

AN - SCOPUS:85015227318

SP - 495

EP - 502

BT - Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016

PB - IEEE Computer Society

ER -