Classification of respiratory sounds by using an artificial neural network

Zümray Dokur; Tamer Ölmez

doi:10.1142/S0218001403002526

Classification of respiratory sounds by using an artificial neural network

Zümray Dokur^*
, Tamer Ölmez

^*Bu çalışma için yazışmadan sorumlu yazar

Elektronik ve Hab.Müh.Bölümü

Araştırma çıktısı: Dergi yayını › Mektup › Hakem

20 Atıf (Scopus)

Özet

In this paper, a classification method for respiratory sounds (RSs) in patients with asthma and in healthy subjects is presented. Wavelet transform is applied to a window containing 256 samples. Elements of the feature vectors are obtained from the wavelet coefficients. The best feature elements are selected by using dynamic programming. Grow and Learn (GAL) neural network, Kohonen network and multi-layer perceptron (MLP) are used for the classification. It is observed that RSs of patients (with asthma) and healthy subjects are successfully classified by the GAL network.

Orijinal dil	İngilizce
Sayfa (başlangıç-bitiş)	567-580
Sayfa sayısı	14
Dergi	International Journal of Pattern Recognition and Artificial Intelligence
Hacim	17
Basın numarası	4
DOI'lar	https://doi.org/10.1142/S0218001403002526
Yayın durumu	Yayınlandı - Haz 2003

BM SKH

Bu sonuç, aşağıdaki Sürdürülebilir Kalkınma Hedefine/Hedeflerine katkıda bulunur

SKH 3 Sağlık ve Kaliteli Yaşam

Belgeye Erişim

10.1142/S0218001403002526

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

@article{45fc73c3ef1b4d7ca700d205cf378b44,

title = "Classification of respiratory sounds by using an artificial neural network",

abstract = "In this paper, a classification method for respiratory sounds (RSs) in patients with asthma and in healthy subjects is presented. Wavelet transform is applied to a window containing 256 samples. Elements of the feature vectors are obtained from the wavelet coefficients. The best feature elements are selected by using dynamic programming. Grow and Learn (GAL) neural network, Kohonen network and multi-layer perceptron (MLP) are used for the classification. It is observed that RSs of patients (with asthma) and healthy subjects are successfully classified by the GAL network.",

keywords = "Artificial neural network, Classification of biomedical signals, Pattern recognition, Respiratory sounds, Wavelet transform",

author = "Z{\"u}mray Dokur and Tamer {\"O}lmez",

year = "2003",

month = jun,

doi = "10.1142/S0218001403002526",

language = "English",

volume = "17",

pages = "567--580",

journal = "International Journal of Pattern Recognition and Artificial Intelligence",

issn = "0218-0014",

publisher = "World Scientific Publishing Co. Pte Ltd",

number = "4",

}

TY - JOUR

T1 - Classification of respiratory sounds by using an artificial neural network

AU - Dokur, Zümray

AU - Ölmez, Tamer

PY - 2003/6

Y1 - 2003/6

N2 - In this paper, a classification method for respiratory sounds (RSs) in patients with asthma and in healthy subjects is presented. Wavelet transform is applied to a window containing 256 samples. Elements of the feature vectors are obtained from the wavelet coefficients. The best feature elements are selected by using dynamic programming. Grow and Learn (GAL) neural network, Kohonen network and multi-layer perceptron (MLP) are used for the classification. It is observed that RSs of patients (with asthma) and healthy subjects are successfully classified by the GAL network.

AB - In this paper, a classification method for respiratory sounds (RSs) in patients with asthma and in healthy subjects is presented. Wavelet transform is applied to a window containing 256 samples. Elements of the feature vectors are obtained from the wavelet coefficients. The best feature elements are selected by using dynamic programming. Grow and Learn (GAL) neural network, Kohonen network and multi-layer perceptron (MLP) are used for the classification. It is observed that RSs of patients (with asthma) and healthy subjects are successfully classified by the GAL network.

KW - Artificial neural network

KW - Classification of biomedical signals

KW - Pattern recognition

KW - Respiratory sounds

KW - Wavelet transform

UR - https://www.scopus.com/pages/publications/0041341957

U2 - 10.1142/S0218001403002526

DO - 10.1142/S0218001403002526

M3 - Letter

AN - SCOPUS:0041341957

SN - 0218-0014

VL - 17

SP - 567

EP - 580

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

IS - 4

ER -

Classification of respiratory sounds by using an artificial neural network

Özet

BM SKH

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap