ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM FOR CLASSIFICATION OF SPEECH SIGNALS IN ALZHEIMER'S DISEASE USING ACOUSTIC FEATURES AND NON-LINEAR CHARACTERISTICS

Full Article - PDF

Published: 2015-04-13

Page: 122-131


MAHDA NASROLAHZADEH *

Department of Biomedical Engineering, Hakim Sabzevari University, Sabzevar, Iran.

ZEINAB MOHAMMADPOORI

Department of Biomedical Engineering, Hakim Sabzevari University, Sabzevar, Iran.

JAVAD HADDADNIA

Department of Biomedical Engineering, Hakim Sabzevari University, Sabzevar, Iran.

*Author to whom correspondence should be addressed.


Abstract

The purpose of this study is to classify spontaneous speech signals directed to pre-clinical test evaluation for earlier diagnosis of Alzheimer's disease using adaptive neuro fuzzy inference system (ANFIS). Acoustic features and nonlinear features such as Lyapunov exponents and Correlation dimension were used for classification. The proposed system uses four feature sets to achieve high detection accuracy. To evaluate the performance of the method, total classification accuracy is estimated. The classification results demonstrate that the dynamical measures are useful parameters which contain comprehensive information about signals and the ANFIS classifier using nonlinear features and the saliency of acoustic features can be useful in analyzing the speech signals in a specific psychological state.

Keywords: Alzheimer's disease, spontaneous speech, emotional speech, lyapunov exponents, correlation dimension, adaptive neuro-fuzzy inference system


How to Cite

NASROLAHZADEH, M., MOHAMMADPOORI, Z., & HADDADNIA, J. (2015). ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM FOR CLASSIFICATION OF SPEECH SIGNALS IN ALZHEIMER’S DISEASE USING ACOUSTIC FEATURES AND NON-LINEAR CHARACTERISTICS. Asian Journal of Mathematics and Computer Research, 3(2), 122–131. Retrieved from https://ikprress.org/index.php/AJOMCOR/article/view/113

Downloads

Download data is not yet available.