Classification between normal and abnormal respiratory sounds based on stochastic approach

Hitoshi Yamamoto, Shoichi Matsunaga, Masaru Yamashita, Katsuya Yamauchi, Sueharu Miyahara

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

8 Citations (Scopus)

Abstract

In this paper, we propose a novel classification procedure for distinguishing between normal and abnormal respiratory sounds on the basis of stochastic approach. The main characteristic of our procedure is that two stochastic models are used to detect abnormal respiratory sounds precisely: (1) hidden Markov models (HMMs) for acoustic spectral features and (2) bigram models for the occurrence of acoustic segments in each inspiratory/expiratory period. The classification procedure comprises a training process and a test process. In the training process, acoustic models for normal and abnormal respiratory sounds are trained using a transcribed database. In the test process, the classification procedure detects the segment sequence with the highest total likelihood and yields the classification results. Our procedure achieved a classification rate of 84.2% between normal and abnormal respiratory sounds. Experimental results revealed that for the classification, use of the segment bigram led to a 4.8% reduction of error rate in comparison with the classification rate of a conventional method that uses deterministic rules to describe segment sequences instead of the segment bigram.

Original languageEnglish
Title of host publication20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society
Pages4144-4148
Number of pages5
Volume5
Publication statusPublished - 2010
Externally publishedYes
Event20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society - Sydney, NSW, Australia
Duration: Aug 23 2010Aug 27 2010

Other

Other20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society
CountryAustralia
CitySydney, NSW
Period8/23/108/27/10

Fingerprint

acoustics
education
occurrences

All Science Journal Classification (ASJC) codes

  • Acoustics and Ultrasonics

Cite this

Yamamoto, H., Matsunaga, S., Yamashita, M., Yamauchi, K., & Miyahara, S. (2010). Classification between normal and abnormal respiratory sounds based on stochastic approach. In 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society (Vol. 5, pp. 4144-4148)

Classification between normal and abnormal respiratory sounds based on stochastic approach. / Yamamoto, Hitoshi; Matsunaga, Shoichi; Yamashita, Masaru; Yamauchi, Katsuya; Miyahara, Sueharu.

20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society. Vol. 5 2010. p. 4144-4148.

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

Yamamoto, H, Matsunaga, S, Yamashita, M, Yamauchi, K & Miyahara, S 2010, Classification between normal and abnormal respiratory sounds based on stochastic approach. in 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society. vol. 5, pp. 4144-4148, 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating the 2010 Annual Conference of the Australian Acoustical Society, Sydney, NSW, Australia, 8/23/10.
Yamamoto H, Matsunaga S, Yamashita M, Yamauchi K, Miyahara S. Classification between normal and abnormal respiratory sounds based on stochastic approach. In 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society. Vol. 5. 2010. p. 4144-4148
Yamamoto, Hitoshi ; Matsunaga, Shoichi ; Yamashita, Masaru ; Yamauchi, Katsuya ; Miyahara, Sueharu. / Classification between normal and abnormal respiratory sounds based on stochastic approach. 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society. Vol. 5 2010. pp. 4144-4148
@inproceedings{a1494776c33045a68bec1d897152486d,
title = "Classification between normal and abnormal respiratory sounds based on stochastic approach",
abstract = "In this paper, we propose a novel classification procedure for distinguishing between normal and abnormal respiratory sounds on the basis of stochastic approach. The main characteristic of our procedure is that two stochastic models are used to detect abnormal respiratory sounds precisely: (1) hidden Markov models (HMMs) for acoustic spectral features and (2) bigram models for the occurrence of acoustic segments in each inspiratory/expiratory period. The classification procedure comprises a training process and a test process. In the training process, acoustic models for normal and abnormal respiratory sounds are trained using a transcribed database. In the test process, the classification procedure detects the segment sequence with the highest total likelihood and yields the classification results. Our procedure achieved a classification rate of 84.2{\%} between normal and abnormal respiratory sounds. Experimental results revealed that for the classification, use of the segment bigram led to a 4.8{\%} reduction of error rate in comparison with the classification rate of a conventional method that uses deterministic rules to describe segment sequences instead of the segment bigram.",
author = "Hitoshi Yamamoto and Shoichi Matsunaga and Masaru Yamashita and Katsuya Yamauchi and Sueharu Miyahara",
year = "2010",
language = "English",
isbn = "9781617827457",
volume = "5",
pages = "4144--4148",
booktitle = "20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society",

}

TY - GEN

T1 - Classification between normal and abnormal respiratory sounds based on stochastic approach

AU - Yamamoto, Hitoshi

AU - Matsunaga, Shoichi

AU - Yamashita, Masaru

AU - Yamauchi, Katsuya

AU - Miyahara, Sueharu

PY - 2010

Y1 - 2010

N2 - In this paper, we propose a novel classification procedure for distinguishing between normal and abnormal respiratory sounds on the basis of stochastic approach. The main characteristic of our procedure is that two stochastic models are used to detect abnormal respiratory sounds precisely: (1) hidden Markov models (HMMs) for acoustic spectral features and (2) bigram models for the occurrence of acoustic segments in each inspiratory/expiratory period. The classification procedure comprises a training process and a test process. In the training process, acoustic models for normal and abnormal respiratory sounds are trained using a transcribed database. In the test process, the classification procedure detects the segment sequence with the highest total likelihood and yields the classification results. Our procedure achieved a classification rate of 84.2% between normal and abnormal respiratory sounds. Experimental results revealed that for the classification, use of the segment bigram led to a 4.8% reduction of error rate in comparison with the classification rate of a conventional method that uses deterministic rules to describe segment sequences instead of the segment bigram.

AB - In this paper, we propose a novel classification procedure for distinguishing between normal and abnormal respiratory sounds on the basis of stochastic approach. The main characteristic of our procedure is that two stochastic models are used to detect abnormal respiratory sounds precisely: (1) hidden Markov models (HMMs) for acoustic spectral features and (2) bigram models for the occurrence of acoustic segments in each inspiratory/expiratory period. The classification procedure comprises a training process and a test process. In the training process, acoustic models for normal and abnormal respiratory sounds are trained using a transcribed database. In the test process, the classification procedure detects the segment sequence with the highest total likelihood and yields the classification results. Our procedure achieved a classification rate of 84.2% between normal and abnormal respiratory sounds. Experimental results revealed that for the classification, use of the segment bigram led to a 4.8% reduction of error rate in comparison with the classification rate of a conventional method that uses deterministic rules to describe segment sequences instead of the segment bigram.

UR - http://www.scopus.com/inward/record.url?scp=84869100330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869100330&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781617827457

VL - 5

SP - 4144

EP - 4148

BT - 20th International Congress on Acoustics 2010, ICA 2010 - Incorporating Proceedings of the 2010 Annual Conference of the Australian Acoustical Society

ER -