Nonlinear dynamic analysis of pathological voices

Authors:
Fang Chunying;Li Haifeng;Ma Lin;Zhang Xiaopeng
Affiliations:
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China,School of Computer and Information Engineering, Heilongjiang Institute of Science and Technology, Harbin, C ...;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
Venue:
ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories and Technology
Year:
2013

Citing 8
Cited 0

Feature Subset Selection Using a Genetic Algorithm

IEEE Intelligent Systems
Interactions between speech coders and disordered speech

Speech Communication
Hybrid Genetic Algorithms for Feature Selection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy

IEEE Transactions on Pattern Analysis and Machine Intelligence
Wavelet time-frequency analysis and least squares support vector machines for the identification of voice disorders

Computers in Biology and Medicine
Genetic Algorithm Based Semi-feature Selection Method

IJCBS '09 Proceedings of the 2009 International Joint Conference on Bioinformatics, Systems Biology and Intelligent Computing
Forward semi-supervised feature selection

PAKDD'08 Proceedings of the 12th Pacific-Asia conference on Advances in knowledge discovery and data mining
Opensmile: the munich versatile and fast open-source audio feature extractor

Proceedings of the international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Research on the human health evaluation through sound analysis is now attracting more and more researchers in the world. Acoustic analysis could be a useful tool to diagnose the disease. Therefore, pathological voices can be used to evaluate the health status as a complementary technique, such as bronchitis. In this article, we proposed a nonlinear dynamic method to analysis pathological voices. Firstly, pathological voices were preprocessed and numerous features were extracted. Secondly, a binary coded chromosome genetic algorithm (GA) was applied as feature selection method to optimize feature descriptor set. The experimental results show that GA, PCA along with support vector machine (SVM) has the best performance in the pathology voices diagnosis.