https://scholars.lib.ntu.edu.tw/handle/123456789/560722
Title: | Automatic wheezing detection based on signal processing of spectrogram and back-propagation neural network | Authors: | Lin B.-S. HUEY-DONG WU Chen S.-J. |
Keywords: | Asthma; Backpropagation neural network; Bilateral filtering; Order truncate average; Wheezing detection | Issue Date: | 2015 | Journal Volume: | 6 | Journal Issue: | 4 | Start page/Pages: | 649-672 | Source: | Journal of Healthcare Engineering | Abstract: | Wheezing is a common clinical symptom in patients with obstructive pulmonary diseases such as asthma. Automatic wheezing detection offers an objective and accurate means for identifying wheezing lung sounds, helping physicians in the diagnosis, long-term auscultation, and analysis of a patient with obstructive pulmonary disease. This paper describes the design of a fast and high-performance wheeze recognition system. A wheezing detection algorithm based on the order truncate average method and a back-propagation neural network (BPNN) is proposed. Some features are extracted from processed spectra to train a BPNN, and subsequently, test samples are analyzed by the trained BPNN to determine whether they are wheezing sounds. The respiratory sounds of 58 volunteers (32 asthmatic and 26 healthy adults) were recorded for training and testing. Experimental results of a qualitative analysis of wheeze recognition showed a high sensitivity of 0.946 and a high specificity of 1.0. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/560722 | ISSN: | 2040-2295 | DOI: | 10.1260/2040-2295.6.4.649 | SDG/Keyword: | Backpropagation; Backpropagation algorithms; Diagnosis; Diseases; Neural networks; Pulmonary diseases; Torsional stress; Asthma; Back propagation neural networks; Bilateral filtering; Detection algorithm; Order truncate average; Qualitative analysis; Recognition systems; Training and testing; Signal processing; abnormal respiratory sound; adult; airflow; Article; artificial neural network; back propagation; back propagation neural network; clinical article; controlled study; Fourier transformation; human; signal detection; signal processing; sound intensity; wheezing; algorithm; asthma; case control study; classification; computer assisted diagnosis; middle aged; pathophysiology; procedures; Respiratory Sounds; sound detection; Adult; Algorithms; Asthma; Case-Control Studies; Diagnosis, Computer-Assisted; Humans; Middle Aged; Neural Networks (Computer); Respiratory Sounds; Signal Processing, Computer-Assisted; Sound Spectrography |
Appears in Collections: | 醫學院附設醫院 (臺大醫院) |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.