The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Em muitas situações, sons anormais, chamados sons adventícios, são incluídos nos sons pulmonares de um indivíduo que sofre de doenças pulmonares. Assim, foi proposto um método para detectar automaticamente sons anormais na ausculta. As características acústicas dos sons pulmonares normais para indivíduos controle e sons pulmonares anormais para pacientes são expressas usando modelos de Markov ocultos (HMMs) para distinguir entre sons pulmonares normais e anormais. Além disso, foram detectados sons anormais num ambiente ruidoso, incluindo sons cardíacos, utilizando um modelo de sons cardíacos. No entanto, o escore F1 obtido na detecção de respiração anormal foi baixo (0.8493). Além disso, a duração e as propriedades acústicas dos segmentos dos sons respiratórios, cardíacos e adventícios variaram. Em nosso método anterior, foram construídos os HMMs apropriados para os segmentos cardíaco e sonoro adventício. Embora as propriedades dos tipos de sons adventícios variassem, não foi considerada uma topologia adequada para cada tipo. Neste estudo foram construídos HMMs apropriados para os segmentos de cada tipo de som adventício e demais segmentos. A pontuação F1 foi aumentada (0.8726) selecionando uma topologia adequada para cada segmento. Os resultados demonstram a eficácia do método proposto.
Masaru YAMASHITA
Nagasaki University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
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
Copiar
@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},}
Copiar
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 -