The aim of this study presented in this paper is to determine the choice of the appropriate wavelet analyzer with the method of extraction of MFCC coefficients for an assistance in the diagnosis of Parkinson's disease. The analysis used is based on a database of 18 healthy and 20 Parkinsonian patients. The suggested processing is based on the transformation of the speech signal by the wavelet transform through testing several sorts of wavelets, extracting Mel Frequency Cepstral Coefficients (MFCC) from the signals, and we apply the support vector machine (SVM) as classifier. The test results reveal that the best recognition rate, which is 86.84%, is obtained by the wavelets of level 2 at 3 rd scale (Daubechie, Symlet, ReverseBior or BiorSpline) combination-MFCC-SVM.

No abstract

No abstract

We are interested in a right junction of two plates of different materials (aluminum and copper) placed in contact edge to edge. The aim of this study is the interaction of Lamb waves with a defect located at the junction. The reflection and transmission of the fundamental symmetrical S0 wave is analyzed. The theoretical coefficients of reflection and transmission are obtained by a multi-modal approach based on the orthogonality relations involving different modes. Using the Finite Element Method (FEM), we estimate the limit value of the ratio between the dimension of the defect and the thickness of the structure, for which the multi-modal approach is applicable. In experimental and numerical studies, it is also brought to light the effects of diffraction by the defect.

No abstract

In this study we are interested in a welded junction of two plates. Plates have the same thickness and are joined along their edges. Some previous theoretical studies have shown that guided Lamb waves are suitable for the characterisation of the interface between two plates [C. Scandrett and N. Vasudevan & M.V Predoi and M. Rousseau]. In a first time a junction perpendicular to the plates is experimentally investigated. Aluminium, copper and steel plates are used. Incident S0 Lamb wave is excited by a contact piezocomposite transducer and the surface displacements of the plate are detected by use of a laser vibrometer on both side of the junction. Converted waves are observed. From the measured normal surface displacements, reflection and transmission energy coefficients of the incident S0 wave through the junction are calculated. These coefficients are in a good agreement with the theoretically predicted ones. In a second time, the studied junction is not perpendicular to the plate. Experimental results are presented and compare to numerical ones obtained with the Comsol R Finite Element code.

Parkinson's disease is a recognizable clinical syndrome with a variety of causes and clinical presentations; it represents a rapidly growing neurodegenerative disorder. Since about 90 percent of Parkinson's disease sufferers have some form of early speech impairment, recent studies on tele diagnosis of Parkinson's disease have focused on the recognition of voice impairments from vowel phonations or the subjects' discourse. In this paper, we present a new approach for Parkinson's disease detection from speech sounds that are based on CNN and LSTM and uses two categories of characteristics Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) obtained from noise-removed speech signals with comparative EMD-DWT and DWT-EMD analysis. The proposed model is divided into three stages. In the first step, noise is removed from the signals using the EMD-DWT and DWT-EMD methods. In the second step, the GTCC and MFCC are extracted from the enhanced audio signals. The classification process is carried out in the third step by feeding these features into the LSTM and CNN models, which are designed to define sequential information from the extracted features. The experiments are performed using PC-GITA and Sakar datasets and 10-fold cross validation method, the highest classification accuracy for the Sakar dataset reached 100% for both EMD-DWT-GTCC-CNN and DWT-EMD-GTCC-CNN, and for the PC-GITA dataset, the accuracy is reached 100% for EMD-DWT-GTCC-CNN and 96.55% for DWT-EMD-GTCC-CNN. The results of this study indicate that the characteristics of GTCC are more appropriate and accurate for the assessment of PD than MFCC.

The diagnosis techniques of diseases which are based on biomedical signals processing are constantly evolving, cardiovascular diseases are no exception to the other biomedical signals. Thanks to the development of signal processing techniques, it has been possible to extract several kinds of information from the ECG signals who told us about the heart's health. The goal of this study is to attempt to create a model based on two methods of signal processing: wavelet analysis and the determination of Mel frequency cepstral coefficients. With the help of this model, it is possible to extract statistical features and MFCC coefficients from approximation coefficients obtained when the discrete wavelet transform (DWT) is applied to analyze an ECG signal. As a result, the various features derived for each approximation coefficient will be classified using a support vector machine classifier (SVM classifier). The classifier's performance has been measured after the use a k fold cross validation technique to avoid the overfitting and the underfitting problems and making the results more reliable and credible.