This work presents a system achieving classification of respiratory sounds directly related to various diseases of the human respiratory system, such as asthma, COPD, and pneumonia. We designed a feature set based on wavelet packet analysis characterizing data coming from four sound classes, i.e. crack, wheeze, normal, crack+wheeze. Subsequently, the captured temporal patterns are learned by hidden Markov models (HMMs). Finally, classification is achieved via a directed acyclic graph scheme limiting the problem space while based on decisions made by the available HMMs. Thorough experiments following a well-established protocol demonstrate the efficacy of the proposed solution.
Classification of Sounds Indicative of Respiratory Diseases / S. Ntalampiras, I. Potamitis (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: Engineering Applications of Neural Networks / [a cura di] J. Macintyre, L. Iliadis, I. Maglogiannis, C. Jayne. - [s.l] : Springer, 2019. - ISBN 9783642546716. - pp. 93-103 (( Intervento presentato al 20. convegno EANN tenutosi a Crete nel 2019 [10.1007/978-3-030-20257-6_8].
Classification of Sounds Indicative of Respiratory Diseases
S. Ntalampiras
;
2019
Abstract
This work presents a system achieving classification of respiratory sounds directly related to various diseases of the human respiratory system, such as asthma, COPD, and pneumonia. We designed a feature set based on wavelet packet analysis characterizing data coming from four sound classes, i.e. crack, wheeze, normal, crack+wheeze. Subsequently, the captured temporal patterns are learned by hidden Markov models (HMMs). Finally, classification is achieved via a directed acyclic graph scheme limiting the problem space while based on decisions made by the available HMMs. Thorough experiments following a well-established protocol demonstrate the efficacy of the proposed solution.File | Dimensione | Formato | |
---|---|---|---|
08 EANN2019.pdf
accesso riservato
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
300.88 kB
Formato
Adobe PDF
|
300.88 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.