Classification of Lung Sounds using Higher-Order Statistics: A divide-and-conquer approach

Highlights • A pattern recognition system to classify five lung sounds is proposed. • The system is based on HOS and on a divide-and-conquer approach. • The proposed approach uses Genetic Algorithms to dimensionality reduction, and k-Nearest Neighbor and Naive Bayes to recognize the signals. • The s...

Full description

Saved in:
Bibliographic Details
Published in:Computer methods and programs in biomedicine 2016-06, Vol.129, p.12-20
Main Authors: Naves, Raphael, Barbosa, Bruno H.G, Ferreiradanton@deg.ufla.br, Danton D
Format: Article
Language:English
Subjects:
Acoustics
Algorithms
Bayes Theorem
Classification
Classifiers
Feature extraction
Genetic Algorithm
Genetic algorithms
Higher-order statistics
Humans
Internal Medicine
Lung sounds
Lungs
Models, Statistical
Other
Pattern recognition
Respiratory Sounds - classification
Statistics
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • A pattern recognition system to classify five lung sounds is proposed. • The system is based on HOS and on a divide-and-conquer approach. • The proposed approach uses Genetic Algorithms to dimensionality reduction, and k-Nearest Neighbor and Naive Bayes to recognize the signals. • The system achieved a high classification accuracy and can be implemented in an embedded system.
ISSN:0169-2607
1872-7565
DOI:10.1016/j.cmpb.2016.02.013