Acoustic HMMs to Detect Abnormal Respiration with Limited Training Data

Masaru YAMASHITA

doi:10.1587/transinf.2022EDP7068

Acoustic HMMs to Detect Abnormal Respiration with Limited Training Data

Masaru YAMASHITA

Full Text Views

0

Cite this

Summary :

In many situations, abnormal sounds, called adventitious sounds, are included with the lung sounds of a subject suffering from pulmonary diseases. Thus, a method to automatically detect abnormal sounds in auscultation was proposed. The acoustic features of normal lung sounds for control subjects and abnormal lung sounds for patients are expressed using hidden markov models (HMMs) to distinguish between normal and abnormal lung sounds. Furthermore, abnormal sounds were detected in a noisy environment, including heart sounds, using a heart-sound model. However, the F1-score obtained in detecting abnormal respiration was low (0.8493). Moreover, the duration and acoustic properties of segments of respiratory, heart, and adventitious sounds varied. In our previous method, the appropriate HMMs for the heart and adventitious sound segments were constructed. Although the properties of the types of adventitious sounds varied, an appropriate topology for each type was not considered. In this study, appropriate HMMs for the segments of each type of adventitious sound and other segments were constructed. The F1-score was increased (0.8726) by selecting a suitable topology for each segment. The results demonstrate the effectiveness of the proposed method.

Publication: IEICE TRANSACTIONS on Information Vol.E106-D No.3 pp.374-380

Publication Date: 2023/03/01

Publicized: 2022/12/19

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2022EDP7068

Type of Manuscript: PAPER

Category: Pattern Recognition

Authors

Masaru YAMASHITA
Nagasaki University

Keyword

hidden markov model, lung sound, patient detection, abnormal respiration

Cite this

Copy

Masaru YAMASHITA, "Acoustic HMMs to Detect Abnormal Respiration with Limited Training Data" in IEICE TRANSACTIONS on Information, vol. E106-D, no. 3, pp. 374-380, March 2023, doi: 10.1587/transinf.2022EDP7068.
Abstract: In many situations, abnormal sounds, called adventitious sounds, are included with the lung sounds of a subject suffering from pulmonary diseases. Thus, a method to automatically detect abnormal sounds in auscultation was proposed. The acoustic features of normal lung sounds for control subjects and abnormal lung sounds for patients are expressed using hidden markov models (HMMs) to distinguish between normal and abnormal lung sounds. Furthermore, abnormal sounds were detected in a noisy environment, including heart sounds, using a heart-sound model. However, the F1-score obtained in detecting abnormal respiration was low (0.8493). Moreover, the duration and acoustic properties of segments of respiratory, heart, and adventitious sounds varied. In our previous method, the appropriate HMMs for the heart and adventitious sound segments were constructed. Although the properties of the types of adventitious sounds varied, an appropriate topology for each type was not considered. In this study, appropriate HMMs for the segments of each type of adventitious sound and other segments were constructed. The F1-score was increased (0.8726) by selecting a suitable topology for each segment. The results demonstrate the effectiveness of the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7068/_p

Copy

@ARTICLE{e106-d_3_374,
author={Masaru YAMASHITA, },
journal={IEICE TRANSACTIONS on Information},
title={Acoustic HMMs to Detect Abnormal Respiration with Limited Training Data},
year={2023},
volume={E106-D},
number={3},
pages={374-380},
abstract={In many situations, abnormal sounds, called adventitious sounds, are included with the lung sounds of a subject suffering from pulmonary diseases. Thus, a method to automatically detect abnormal sounds in auscultation was proposed. The acoustic features of normal lung sounds for control subjects and abnormal lung sounds for patients are expressed using hidden markov models (HMMs) to distinguish between normal and abnormal lung sounds. Furthermore, abnormal sounds were detected in a noisy environment, including heart sounds, using a heart-sound model. However, the F1-score obtained in detecting abnormal respiration was low (0.8493). Moreover, the duration and acoustic properties of segments of respiratory, heart, and adventitious sounds varied. In our previous method, the appropriate HMMs for the heart and adventitious sound segments were constructed. Although the properties of the types of adventitious sounds varied, an appropriate topology for each type was not considered. In this study, appropriate HMMs for the segments of each type of adventitious sound and other segments were constructed. The F1-score was increased (0.8726) by selecting a suitable topology for each segment. The results demonstrate the effectiveness of the proposed method.},
keywords={},
doi={10.1587/transinf.2022EDP7068},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Acoustic HMMs to Detect Abnormal Respiration with Limited Training Data
T2 - IEICE TRANSACTIONS on Information
SP - 374
EP - 380
AU - Masaru YAMASHITA
PY - 2023
DO - 10.1587/transinf.2022EDP7068
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2023
AB - In many situations, abnormal sounds, called adventitious sounds, are included with the lung sounds of a subject suffering from pulmonary diseases. Thus, a method to automatically detect abnormal sounds in auscultation was proposed. The acoustic features of normal lung sounds for control subjects and abnormal lung sounds for patients are expressed using hidden markov models (HMMs) to distinguish between normal and abnormal lung sounds. Furthermore, abnormal sounds were detected in a noisy environment, including heart sounds, using a heart-sound model. However, the F1-score obtained in detecting abnormal respiration was low (0.8493). Moreover, the duration and acoustic properties of segments of respiratory, heart, and adventitious sounds varied. In our previous method, the appropriate HMMs for the heart and adventitious sound segments were constructed. Although the properties of the types of adventitious sounds varied, an appropriate topology for each type was not considered. In this study, appropriate HMMs for the segments of each type of adventitious sound and other segments were constructed. The F1-score was increased (0.8726) by selecting a suitable topology for each segment. The results demonstrate the effectiveness of the proposed method.
ER -