Naslov
Classification Accuracy Comparison of Asthmatic Wheezing Sounds Recorded under Ideal and Real- world Conditions

Autori
Miličević, Mario ; Mazić, Igor ; Bonković, Mirjana

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 15th International Conference on Artificial Intelligence, Knowledge Engineering and Databases (AIKED '16) / Valeri Mladenov - Venecija : WSEAS Press, 2016, 101-106

ISBN
978-1-61804-362-7

Skup
15th International Conference on Artificial Intelligence, Knowledge Engineering and Databases (AIKED '16)

Mjesto i datum
Venecija, Italija, 29.01.2016. - 31.01.2016

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
machine learning; classification; asthma; phonopneumogram; MFCC; SVM; k-NN

Sažetak
Asthma is the most common chronic disease among children. Diagnosis of asthma is often challenging, so the computerized lung sound analysis is important diagnostic aid. This research compares the efficiency of the classification algorithms applied both on signals available on the internet and signals recorded on children in real-life clinical settings. With an appropriate signal processing technique, resulting in MFCC features, it is possible to achieve high classification accuracy for signals recorded in suboptimal conditions.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA