Thomson Multitaper MFCC and PLP voice features for early detection of Parkinson disease

Upadhya, Savitha S.; Cheeran, Alice N.; Nirmal, Jagannath

doi:10.1016/j.bspc.2018.07.019

Cited by 34 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…e classification accuracy reported through proposed method was in the range from 94.00%-98.00%. In another study, Upadhya et al [34] adopted Single Taper Smooth (STS) window and omson Multitaper (TMT) windowing techniques for MFCC and PLP voice feature extraction. For classification, neural network classifier was deployed for the classification of the subjects at the early stage of PD.…”

Section: Related Workmentioning

confidence: 99%

Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier

Rahman

Rizvi

Khan

et al. 2021

Mobile Information Systems

View full text Add to dashboard Cite

Parkinson’s disease (PD) is one of the most common and serious neurological diseases. Impairments in voice have been reported to be the early biomarkers of the disease. Hence, development of PD diagnostic tool will help early diagnosis of the disease. Additionally, intelligent system developed for binary classification of PD and healthy controls can also be exploited in future as an instrument for prodromal diagnosis. Notably, patients with rapid eye movement (REM) sleep behaviour disorder (RBD) represent a good model as they develop PD with a high probability. It has been shown that slight speech and voice impairment may be a sensitive marker of preclinical PD. In this study, we propose PD detection by extracting cepstral features from the voice signals collected from people with PD and healthy subjects. To classify the extracted features, we propose to use dimensionality reduction through linear discriminant analysis and classification through support vector machine. In order to validate the effectiveness of the proposed method, we also developed ten different machine learning models. It was observed that the proposed method yield area under the curve (AUC) of 88%, sensitivity of 73.33%, and specificity of 84%. Moreover, the proposed intelligent system was simulated using publicly available multiple types of voice database. Additionally, the data were collected from patients under on-state. The obtained results on the public database are promising compared to the previously published work.

show abstract

Section: Related Workmentioning

confidence: 99%

Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier

Rahman

Rizvi

Khan

et al. 2021

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Estes tapers são ortogonais um do outro, por tanto, são gerados k amostras de dados chamadas de subespectro. Essas estimativas espectrais ortogonais são então ponderadas, geralmente, usando pesos uniformes para obter o espectro médio denominado espectro multifuncional [Upadhya et al 2018…”

Section: A Base De Dadosunclassified

Uma abordagem baseada em redes neurais artificiais sobre o espectro de potência de eletroencefalogramas para o auxílio médico na classificação de crises epiléticas

Vargas¹,

Oliva²,

Teixeira³

2021

Anais Do XXI Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2021)

View full text Add to dashboard Cite

A epilepsia é a quarta enfermidade neurológica mais comum e atinge aproximadamente 1% da população mundial. O diagnóstico é, em geral, amparado por um eletroencefalograma (EEG), cuja análise depende da interpretação médica, o que por vezes gera incongruência de diagnóstico, além de ser um trabalho tedioso, impreciso e propenso a erros. Este trabalho propõe um método de reconhecimento automático de padrões baseado em aprendizado de máquina e engenharia de características aplicadas ao espectros de potência de segmentos de EEGs. Resultados sugerem a possibilidade de detectar crises epilépticas com uma precisão superior a 80% em bases de dados já utilizadas na literatura.

show abstract

“…Here, the estimation of Spectrum sxðf Þ from N data is given in equation (1). Equation ( 2) is a windowed periodogram obtained by using the data window (Akinci et al, 2013;Babadi and Brown, 2014;Di Matteo et al, 2020;Rooney and Buck, 2015;Upadhya et al, 2018).…”

Section: Multitape Power Spectrum Density (Mpsd)mentioning

confidence: 99%

Determination of isolator damages in electric power transmission lines with continuous wavelet transform and multitape power spectrum density

Akıncı

Chung²

2021

WJSTSD

View full text Add to dashboard Cite

PurposeDetection of deformation of devices in high voltage electricity transmission line systems is an important issue in terms of economy and reuse. This study is aimed to detect devices that are deformed or thought to have suffered due to environmental and electrical reasons.Design/methodology/approachIn this experimental study, it was ensured that the sound and deformed insulators used in energy transmission lines were determined by the analysis of the sounds obtained by using the impact method. Equal intensity impact was applied to the isolator using the pendulum and the resulting sound noise signal analyses were made using power spectral density (PSD), magnitude scalogram (MS), multitape power spectrum density (MPSD) and continuous wavelet transform (CWT) methods in the study. In the analysis results, the isolators that are not visible to the eye and have certain damage were successfully separated from the intact insulators. Especially, MPSD and CWT analysis results are quite satisfactory.FindingsDamage analysis of insulators used in electricity transmission lines has been made. A total of 40 insulators were examined in two categories in their group, both damaged and not damaged. Data collection system was established. The data obtained from the data collection system were analysed and compared using four analysis methods. PSD, MS, MPSD and CWT analyses were made in the study. All the analyses carried out generally contain features that distinguish damaged and undamaged insulators from each other, the most successful results are MS and CWT results. CWT results are very successful in terms of time and amplitude, and it has been proposed as a method that can be used to separate damaged and undamaged insulators.Originality/valueIt can be suggested as a result of experimental tests that the results of CWT analysis can be used in the pulse noise method in isolators to be tested for reuse in electrical power transmission lines.

show abstract

Thomson Multitaper MFCC and PLP voice features for early detection of Parkinson disease

Cited by 34 publications

References 19 publications

Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier

Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier

Uma abordagem baseada em redes neurais artificiais sobre o espectro de potência de eletroencefalogramas para o auxílio médico na classificação de crises epiléticas

Determination of isolator damages in electric power transmission lines with continuous wavelet transform and multitape power spectrum density

Contact Info

Product

Resources

About