Efficient computation of image moments for robust cough detection using smartphones

Research output: Contribution to journalArticle

7 Downloads (Pure)

Abstract

Health Monitoring apps for smartphones have the potential to improve quality of life and decrease the cost of health services. However, they have failed to live up to expectation in the context of respiratory disease. This is in part due to poor objective measurements of symptoms such as cough. Real-time cough detection using smartphones faces two main challenges namely, the necessity of dealing with noisy input signals, and the need of the algorithms to be computationally efficient, since a high battery consumption would prevent patients from using them. This paper proposes a robust and efficient smartphone-based cough detection system able to keep the phone battery consumption below 25% (16% if only the detector is considered) during 24h use. The proposed system efficiently calculates local image moments over audio spectrograms to feed an optimized classifier for final cough detection. Our system achieves 88:94% sensitivity and 98:64% specificity in noisy environments with a 5500 speed-up and 4 battery saving compared to the baseline implementation. Power consumption is also reduced by a minimum factor of 6 compared to existing optimized systems in the literature.
Original languageEnglish
Pages (from-to)176-185
Number of pages10
JournalComputers in Biology and Medicine
Volume100
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint

Smartphones
Cough
Health
Pulmonary diseases
Application programs
Electric power utilization
Classifiers
Health Services
Detectors
Monitoring
Quality of Life
Costs and Cost Analysis
Smartphone
Costs

Keywords

  • Event detection
  • Cough detection
  • Mobile health
  • Moment theory
  • Optimization

Cite this

@article{fd290a08137f4e04bf3668c6c5997e6b,
title = "Efficient computation of image moments for robust cough detection using smartphones",
abstract = "Health Monitoring apps for smartphones have the potential to improve quality of life and decrease the cost of health services. However, they have failed to live up to expectation in the context of respiratory disease. This is in part due to poor objective measurements of symptoms such as cough. Real-time cough detection using smartphones faces two main challenges namely, the necessity of dealing with noisy input signals, and the need of the algorithms to be computationally efficient, since a high battery consumption would prevent patients from using them. This paper proposes a robust and efficient smartphone-based cough detection system able to keep the phone battery consumption below 25{\%} (16{\%} if only the detector is considered) during 24h use. The proposed system efficiently calculates local image moments over audio spectrograms to feed an optimized classifier for final cough detection. Our system achieves 88:94{\%} sensitivity and 98:64{\%} specificity in noisy environments with a 5500 speed-up and 4 battery saving compared to the baseline implementation. Power consumption is also reduced by a minimum factor of 6 compared to existing optimized systems in the literature.",
keywords = "Event detection, Cough detection, Mobile health, Moment theory, Optimization",
author = "{Hoyos Barcel{\'o}}, Carlos and Jes{\'u}s Monge-{\'A}lvarez and Zeeshan Pervez and San-Jos´e-Revuelta, {Luis M.} and Casaseca, {Juan Pablo}",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.compbiomed.2018.07.003",
language = "English",
volume = "100",
pages = "176--185",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Efficient computation of image moments for robust cough detection using smartphones

AU - Hoyos Barceló, Carlos

AU - Monge-Álvarez, Jesús

AU - Pervez, Zeeshan

AU - San-Jos´e-Revuelta, Luis M.

AU - Casaseca, Juan Pablo

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Health Monitoring apps for smartphones have the potential to improve quality of life and decrease the cost of health services. However, they have failed to live up to expectation in the context of respiratory disease. This is in part due to poor objective measurements of symptoms such as cough. Real-time cough detection using smartphones faces two main challenges namely, the necessity of dealing with noisy input signals, and the need of the algorithms to be computationally efficient, since a high battery consumption would prevent patients from using them. This paper proposes a robust and efficient smartphone-based cough detection system able to keep the phone battery consumption below 25% (16% if only the detector is considered) during 24h use. The proposed system efficiently calculates local image moments over audio spectrograms to feed an optimized classifier for final cough detection. Our system achieves 88:94% sensitivity and 98:64% specificity in noisy environments with a 5500 speed-up and 4 battery saving compared to the baseline implementation. Power consumption is also reduced by a minimum factor of 6 compared to existing optimized systems in the literature.

AB - Health Monitoring apps for smartphones have the potential to improve quality of life and decrease the cost of health services. However, they have failed to live up to expectation in the context of respiratory disease. This is in part due to poor objective measurements of symptoms such as cough. Real-time cough detection using smartphones faces two main challenges namely, the necessity of dealing with noisy input signals, and the need of the algorithms to be computationally efficient, since a high battery consumption would prevent patients from using them. This paper proposes a robust and efficient smartphone-based cough detection system able to keep the phone battery consumption below 25% (16% if only the detector is considered) during 24h use. The proposed system efficiently calculates local image moments over audio spectrograms to feed an optimized classifier for final cough detection. Our system achieves 88:94% sensitivity and 98:64% specificity in noisy environments with a 5500 speed-up and 4 battery saving compared to the baseline implementation. Power consumption is also reduced by a minimum factor of 6 compared to existing optimized systems in the literature.

KW - Event detection

KW - Cough detection

KW - Mobile health

KW - Moment theory

KW - Optimization

U2 - 10.1016/j.compbiomed.2018.07.003

DO - 10.1016/j.compbiomed.2018.07.003

M3 - Article

VL - 100

SP - 176

EP - 185

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -