Automated cough assessment on a mobile platform

Mark Sterling, Hyekyun Rhee, Mark Bocko

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

The development of an Automated System for Asthma Monitoring (ADAM) is described.This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithmis based upon standard speech recognition andmachine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples froma variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarmas determined in a cross-validation test.

Original languageEnglish
Article number951621
JournalJournal of Medical Engineering
Volume2014
DOIs
Publication statusPublished - 2014

Fingerprint

Hidden Markov models
Microphones
Consumer electronics
Digital to analog conversion
Speech recognition
Feature extraction
Topology
Acoustic waves
Monitoring

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Automated cough assessment on a mobile platform. / Sterling, Mark; Rhee, Hyekyun; Bocko, Mark.

In: Journal of Medical Engineering, Vol. 2014, 951621, 2014.

Research output: Contribution to journalArticle

@article{88257294bac24c7eabef2dd69c3f5176,
title = "Automated cough assessment on a mobile platform",
abstract = "The development of an Automated System for Asthma Monitoring (ADAM) is described.This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithmis based upon standard speech recognition andmachine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples froma variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarmas determined in a cross-validation test.",
author = "Mark Sterling and Hyekyun Rhee and Mark Bocko",
year = "2014",
doi = "10.1155/2014/951621",
language = "English",
volume = "2014",
journal = "Journal of Medical Engineering",
issn = "2314-5129",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Automated cough assessment on a mobile platform

AU - Sterling, Mark

AU - Rhee, Hyekyun

AU - Bocko, Mark

PY - 2014

Y1 - 2014

N2 - The development of an Automated System for Asthma Monitoring (ADAM) is described.This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithmis based upon standard speech recognition andmachine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples froma variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarmas determined in a cross-validation test.

AB - The development of an Automated System for Asthma Monitoring (ADAM) is described.This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithmis based upon standard speech recognition andmachine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples froma variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarmas determined in a cross-validation test.

UR - http://www.scopus.com/inward/record.url?scp=85000401627&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000401627&partnerID=8YFLogxK

U2 - 10.1155/2014/951621

DO - 10.1155/2014/951621

M3 - Article

AN - SCOPUS:85000401627

VL - 2014

JO - Journal of Medical Engineering

JF - Journal of Medical Engineering

SN - 2314-5129

M1 - 951621

ER -