Automatic Speech Analysis in Patients with Parkinson's Disease using Feature Dimension Reduction

2017 ◽  
Author(s):  
Ismail El Moudden ◽  
Mounir Ouzir ◽  
Souad ElBernoussi
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dimension Reduction ◽  
Speech Analysis ◽  
Feature Dimension ◽  
Feature Dimension Reduction

scholarly journals Effective Dysphonia Detection Using Feature Dimension Reduction and Kernel Density Estimation for Patients with Parkinson’s Disease

2021 ◽  
Author(s):  
Sridhar Krishnan ◽  
Shanshan Yang ◽  
Fang Zheng ◽  
Xin Luo ◽  
Suxian Cai ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dimension Reduction ◽  
Density Estimation ◽  
Kernel Density Estimation ◽  
Kernel Density ◽  
Support Vector ◽  
Linear Discriminant ◽  
Feature Dimension ◽  
Feature Dimension Reduction

Detection of dysphonia is useful for monitoring the progression of phonatory impairment for patients with Parkinson’s disease (PD), and also helps assess the disease severity. This paper describes the statistical pattern analysis methods to study different vocal measurements of sustained phonations. The feature dimension reduction procedure was implemented by using the sequential forward selection (SFS) and kernel principal component analysis (KPCA) methods. Four selected vocal measures were projected by the KPCA onto the bivariate feature space, in which the class-conditional feature densities can be approximated with the nonparametric kernel density estimation technique. In the vocal pattern classification experiments, Fisher’s linear discriminant analysis (FLDA) was applied to perform the linear classification of voice records for healthy control subjects and PD patients, and the maximum a posteriori (MAP) decision rule and support vector machine (SVM) with radial basis function kernels were employed for the nonlinear classification tasks. Based on the KPCA-mapped feature densities, the MAP classifier successfully distinguished 91.8% voice records, with a sensitivity rate of 0.986, a specificity rate of 0.708, and an area value of 0.94 under the receiver operating characteristic (ROC) curve. The diagnostic performance provided by the MAP classifier was superior to those of the FLDA and SVM classifiers. In addition, the classification results indicated that gender is insensitive to dysphonia detection, and the sustained phonations of PD patients with minimal functional disability are more difficult to be correctly identified.

scholarly journals Effective Dysphonia Detection Using Feature Dimension Reduction and Kernel Density Estimation for Patients with Parkinson’s Disease

2021 ◽  
Author(s):  
Sridhar Krishnan ◽  
Shanshan Yang ◽  
Fang Zheng ◽  
Xin Luo ◽  
Suxian Cai ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dimension Reduction ◽  
Density Estimation ◽  
Kernel Density Estimation ◽  
Kernel Density ◽  
Support Vector ◽  
Linear Discriminant ◽  
Feature Dimension ◽  
Feature Dimension Reduction

Detection of dysphonia is useful for monitoring the progression of phonatory impairment for patients with Parkinson’s disease (PD), and also helps assess the disease severity. This paper describes the statistical pattern analysis methods to study different vocal measurements of sustained phonations. The feature dimension reduction procedure was implemented by using the sequential forward selection (SFS) and kernel principal component analysis (KPCA) methods. Four selected vocal measures were projected by the KPCA onto the bivariate feature space, in which the class-conditional feature densities can be approximated with the nonparametric kernel density estimation technique. In the vocal pattern classification experiments, Fisher’s linear discriminant analysis (FLDA) was applied to perform the linear classification of voice records for healthy control subjects and PD patients, and the maximum a posteriori (MAP) decision rule and support vector machine (SVM) with radial basis function kernels were employed for the nonlinear classification tasks. Based on the KPCA-mapped feature densities, the MAP classifier successfully distinguished 91.8% voice records, with a sensitivity rate of 0.986, a specificity rate of 0.708, and an area value of 0.94 under the receiver operating characteristic (ROC) curve. The diagnostic performance provided by the MAP classifier was superior to those of the FLDA and SVM classifiers. In addition, the classification results indicated that gender is insensitive to dysphonia detection, and the sustained phonations of PD patients with minimal functional disability are more difficult to be correctly identified.

Dimension Reduction Using Image Transform for Content-Based Feature Extraction

2018 ◽  
pp. 26-40
Author(s):  
Sourav De ◽  
Madhumita Singha ◽  
Komal Kumari ◽  
Ritika Selot ◽  
Akshat Gupta
Keyword(s):  
Feature Extraction ◽  
Dimension Reduction ◽  
Image Feature ◽  
Extraction Technique ◽  
Image Transform ◽  
Improved Performance ◽  
Different Color ◽  
Feature Dimension ◽  
Feature Extraction Technique ◽  
Feature Dimension Reduction

Technological advancements in the field of machine learning have attempted classification of the images of gigantic datasets. Classification with content-based image feature extraction categorizes the images based on the image content in contrast to conventional text-based annotation. The chapter has presented a feature extraction technique based on application of image transform. The method has extracted meaningful features and facilitated feature dimension reduction. A technique, known as fractional coefficient of transforms, is adopted to facilitate feature dimension reduction. Two different color spaces, namely RGB and YUV, are considered to compare the classification metrics to figure out the best possible reduced feature dimension. Further, the results are compared to state-of-the-art techniques which have revealed improved performance for the proposed feature extraction technique.

Soft Computing-Based Early Detection of Parkinson's Disease Using Non-Invasive Method Based on Speech Analysis

2021 ◽  
pp. 329-340
Author(s):  
Chandrasekar Ravi
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Speech Analysis ◽  
Machine Learning Techniques ◽  
Speech Signals ◽  
Fuzzy Classifier ◽  
Non Invasive ◽  
Specificity And Sensitivity ◽  
Learning Techniques ◽  
Invasive Method

This chapter aims to use the speech signals that are a behavioral bio-marker for Parkinson's disease. The victim's vocabulary is mostly lost, or big gaps are observed when they are talking or the conversation is abruptly stopped. Therefore, speech analysis could help to identify the complications in conversation from the inception of the symptoms of Parkinson's disease in initial phases itself. Speech can be regularly logged in an unobstructed approach and machine learning techniques can be applied and analyzed. Fuzzy logic-based classifier is proposed for learning from the training speech signals and classifying the test speech signals. Brainstorm optimization algorithm is proposed for extracting the fuzzy rules from the speech data, which is used by fuzzy classifier for learning and classification. The performance of the proposed classifier is evaluated using metrics like accuracy, specificity, and sensitivity, and compared with benchmark classifiers like SVM, naïve Bayes, k-means, and decision tree. It is observed that the proposed classifier outperforms the benchmark classifiers.

scholarly journals Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

2020 ◽  
Vol 12 (2) ◽  
pp. 321
Author(s):  
Jiao Guo ◽  
Henghui Li ◽  
Jifeng Ning ◽  
Wenting Han ◽  
Weitao Zhang ◽  
...  
Keyword(s):  
Dimension Reduction ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
European Space Agency ◽  
Agricultural Crop ◽  
Temporal Data ◽  
Multi Temporal ◽  
Crop Classification ◽  
Feature Dimension ◽  
Feature Dimension Reduction

Crop classification in agriculture is one of important applications for polarimetric synthetic aperture radar (PolSAR) data. For agricultural crop discrimination, compared with single-temporal data, multi-temporal data can dramatically increase crop classification accuracies since the same crop shows different external phenomena as it grows up. In practice, the utilization of multi-temporal data encounters a serious problem known as a “dimension disaster”. Aiming to solve this problem and raise the classification accuracy, this study developed a feature dimension reduction method using stacked sparse auto-encoders (S-SAEs) for crop classification. First, various incoherent scattering decomposition algorithms were employed to extract a variety of detailed and quantitative parameters from multi-temporal PolSAR data. Second, based on analyzing the configuration and main parameters for constructing an S-SAE, a three-hidden-layer S-SAE network was built to reduce the dimensionality and extract effective features to manage the “dimension disaster” caused by excessive scattering parameters, especially for multi-temporal, quad-pol SAR images. Third, a convolutional neural network (CNN) was constructed and employed to further enhance the crop classification performance. Finally, the performances of the proposed strategy were assessed with the simulated multi-temporal Sentinel-1 data for two experimental sites established by the European Space Agency (ESA). The experimental results showed that the overall accuracy with the proposed method was raised by at least 17% compared with the long short-term memory (LSTM) method in the case of a 1% training ratio. Meanwhile, for a CNN classifier, the overall accuracy was almost 4% higher than those of the principle component analysis (PCA) and locally linear embedded (LLE) methods. The comparison studies clearly demonstrated the advantage of the proposed multi-temporal crop classification methodology in terms of classification accuracy, even with small training ratios.

Sign in / Sign up

Export Citation Format

Share Document