Vocal Acoustic Analysis

2022 ◽  
pp. 612-628
Author(s):  
João Paulo Teixeira ◽  
Nuno Alves ◽  
Paula Odete Fernandes
Keyword(s):  
Acoustic Analysis ◽  
Low Cost ◽  
Principal Component ◽  
Female Group ◽  
Multilinear Regression ◽  
Non Invasive ◽  
Reduction Techniques ◽  
Multilinear Regression Analysis ◽  
And Control ◽  
Dimension Reduction Techniques

Vocal acoustic analysis is becoming a useful tool for the classification and recognition of laryngological pathologies. This technique enables a non-invasive and low-cost assessment of voice disorders, allowing a more efficient, fast, and objective diagnosis. In this work, ANN and SVM were experimented on to classify between dysphonic/control and vocal cord paralysis/control. A vector was made up of 4 jitter parameters, 4 shimmer parameters, and a harmonic to noise ratio (HNR), determined from 3 different vowels at 3 different tones, with a total of 81 features. Variable selection and dimension reduction techniques such as hierarchical clustering, multilinear regression analysis and principal component analysis (PCA) was applied. The classification between dysphonic and control was made with an accuracy of 100% for female and male groups with ANN and SVM. For the classification between vocal cords paralysis and control an accuracy of 78,9% was achieved for female group with SVM, and 81,8% for the male group with ANN.

scholarly journals Vocal Acoustic Analysis

2020 ◽  
Vol 11 (1) ◽  
pp. 37-51
Author(s):  
João Paulo Teixeira ◽  
Nuno Alves ◽  
Paula Odete Fernandes
Keyword(s):  
Acoustic Analysis ◽  
Low Cost ◽  
Principal Component ◽  
Female Group ◽  
Multilinear Regression ◽  
Non Invasive ◽  
Reduction Techniques ◽  
Multilinear Regression Analysis ◽  
And Control ◽  
Dimension Reduction Techniques

Vocal acoustic analysis is becoming a useful tool for the classification and recognition of laryngological pathologies. This technique enables a non-invasive and low-cost assessment of voice disorders, allowing a more efficient, fast, and objective diagnosis. In this work, ANN and SVM were experimented on to classify between dysphonic/control and vocal cord paralysis/control. A vector was made up of 4 jitter parameters, 4 shimmer parameters, and a harmonic to noise ratio (HNR), determined from 3 different vowels at 3 different tones, with a total of 81 features. Variable selection and dimension reduction techniques such as hierarchical clustering, multilinear regression analysis and principal component analysis (PCA) was applied. The classification between dysphonic and control was made with an accuracy of 100% for female and male groups with ANN and SVM. For the classification between vocal cords paralysis and control an accuracy of 78,9% was achieved for female group with SVM, and 81,8% for the male group with ANN.

scholarly journals The prototype device for non-invasive diagnosis of arteriovenous fistula condition using machine learning methods

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Marcin Grochowina ◽  
Lucyna Leniowska ◽  
Agnieszka Gala-Błądzińska
Keyword(s):  
Machine Learning ◽  
Arteriovenous Fistula ◽  
Low Cost ◽  
Principal Component ◽  
Special Kind ◽  
Classification Model ◽  
Supervised Machine Learning ◽  
Signal Acquisition ◽  
Non Invasive ◽  
Prototype Device

Abstract Pattern recognition and automatic decision support methods provide significant advantages in the area of health protection. The aim of this work is to develop a low-cost tool for monitoring arteriovenous fistula (AVF) with the use of phono-angiography method. This article presents a developed and diagnostic device that implements classification algorithms to identify 38 patients with end stage renal disease, chronically hemodialysed using an AVF, at risk of vascular access stenosis. We report on the design, fabrication, and preliminary testing of a prototype device for non-invasive diagnosis which is very important for hemodialysed patients. The system includes three sub-modules: AVF signal acquisition, information processing and classification and a unit for presenting results. This is a non-invasive and inexpensive procedure for evaluating the sound pattern of bruit produced by AVF. With a special kind of head which has a greater sensitivity than conventional stethoscope, a sound signal from fistula was recorded. The proces of signal acquisition was performed by a dedicated software, written specifically for the purpose of our study. From the obtained phono-angiogram, 23 features were isolated for vectors used in a decision-making algorithm, including 6 features based on the waveform of time domain, and 17 features based on the frequency spectrum. Final definition of the feature vector composition was obtained by using several selection methods: the feature-class correlation, forward search, Principal Component Analysis and Joined-Pairs method. The supervised machine learning technique was then applied to develop the best classification model.

scholarly journals Establishment of Prediction Equations of Lean Body Mass Suitable for Chinese Adults

2019 ◽  
Vol 2019 ◽  
pp. 1-9
Author(s):  
Jinhua Li ◽  
Jingjie Shang ◽  
Bin Guo ◽  
Jian Gong ◽  
Hao Xu
Keyword(s):  
Lean Body Mass ◽  
Body Mass ◽  
Predictive Ability ◽  
Female Group ◽  
Chinese Adults ◽  
Multilinear Regression ◽  
Predictive Equations ◽  
Large Sample ◽  
Multilinear Regression Analysis ◽  
Southern Chinese

Aim. To develop predictive equations of lean body mass (LBM) suitable for healthy southern Chinese adults with a large sample. LBM measured by dual-energy X-ray absorptiometry (DXA) are considered as the standard ones. Methods. Retrospective analysis was conducted on the consecutive people who did total body measurement with DXA from July 2005 to October 2015. People with diseases that might affect LBM were excluded and overall 12,194 subjects were included in this study. Information about the 10,683 subjects (2,987 males and 7,696 females) from July 2005 to November 2014 was used to establish equations. These subjects were grouped by sex and then subdivided according to their body mass index (BMI). The female group was divided into another two subgroups: the premenopausal and postmenopausal subgroups. Equations were developed through stepwise multilinear regression analysis of height, weight, age, and BMI. Information about the 1,511 subjects (395 males and 1116 females) from December 2014 to October 2015 was used to verify the established equations. Results. BMI, height, weight, and age were introduced into the equations as independent variables in the male group, while age was proved to have no influence on LBM in the female group. Regrouping according to BMI or menopause did not increase the predictive ability of equations. Good agreement between LBM evaluated by equation (LBM_PE) and LBM measured by DXA (LBM_DXA) was observed in both the male and female groups. Conclusion. Predictive equations of LBM suitable for healthy southern Chinese adults are established with a large sample. BMI was related to LBM content; however, there is no need for further group based on BMI or menopause while developing LBM questions.

Avoiding Optimal Mean ℓ2,1-Norm Maximization-Based Robust PCA for Reconstruction

2017 ◽  
Vol 29 (4) ◽  
pp. 1124-1150 ◽  
Author(s):  
Minnan Luo ◽  
Feiping Nie ◽  
Xiaojun Chang ◽  
Yi Yang ◽  
Alexander G. Hauptmann ◽  
...  
Keyword(s):  
Principal Component ◽  
Reconstruction Error ◽  
Data Sets ◽  
Robust Pca ◽  
Robust Principal Component Analysis ◽  
Reduction Techniques ◽  
Optimal Projection ◽  
Nonsmooth Problem ◽  
The Mean ◽  
Dimension Reduction Techniques

Robust principal component analysis (PCA) is one of the most important dimension-reduction techniques for handling high-dimensional data with outliers. However, most of the existing robust PCA presupposes that the mean of the data is zero and incorrectly utilizes the average of data as the optimal mean of robust PCA. In fact, this assumption holds only for the squared [Formula: see text]-norm-based traditional PCA. In this letter, we equivalently reformulate the objective of conventional PCA and learn the optimal projection directions by maximizing the sum of projected difference between each pair of instances based on [Formula: see text]-norm. The proposed method is robust to outliers and also invariant to rotation. More important, the reformulated objective not only automatically avoids the calculation of optimal mean and makes the assumption of centered data unnecessary, but also theoretically connects to the minimization of reconstruction error. To solve the proposed nonsmooth problem, we exploit an efficient optimization algorithm to soften the contributions from outliers by reweighting each data point iteratively. We theoretically analyze the convergence and computational complexity of the proposed algorithm. Extensive experimental results on several benchmark data sets illustrate the effectiveness and superiority of the proposed method.

scholarly journals Use of Paper Microdevices in the Identification and Quantification of Cocaine in Seized Street Samples

2021 ◽  
Author(s):  
Jadson dos Reis ◽  
Wanderson Romão
Keyword(s):  
Response Time ◽  
Illicit Drugs ◽  
Low Cost ◽  
Principal Component ◽  
Spot Size ◽  
Experimental Planning ◽  
Non Invasive ◽  
Factorial Model ◽  
Cocaine Hydrochloride ◽  
Analyte Detection

The growing consumption of illicit drugs in Brazil is becoming increasingly problematic for society. It is therefore critical to develop technologies to combat drug trafficking that allow for rapid, non-invasive evaluation of drug samples. Microfluidics is a technology that manipulates and studies small amounts of fluids, using structures with dimensions from ten to hundreds of micrometers (microdevices). The main advantages of microfluidic approaches are its low cost, speed, and ability to provide results in loco. Here, paper microfluidics were developed to perform the modified Scott test to calculate the cocaine hydrochloride content in seized samples of cocaine (n = 30) and crack (n = 30). A smartphone with the Photometrix® app was used to construct a model for quantifying the samples. A factorial model was developed to optimize microfluidic analytical parameters such as spot size (6, 8 and 10 mm), reagent content (50, 75, and 100% cobalt thiocyanate II), cocaine hydrochloride concentration (4, 6 and 8 mg mL-1) and response time (or analyte detection; t = 0, 0.5 1, 12 and 24 h). After experimental planning, a diameter of ΜPADs = 8 mm - [Co(SCN)2] = 100% and a 1 h response time were identified as the best conditions. We observed that the cocaine hydrochloride concentration did not influence the model. A sample concentration of 15 mg mL-1 was used to quantify cocaine hydrochloride in street samples apprehended by the Forensic Police of Espírito Santo state (with n = 60). The quantification curve constructed to determine the cocaine hydrochloride concentration showed a determination coefficient, R2, of 0.98246 and RMSEC (root mean squares error calibration - mean square error of the calibration) of 0.39480, with a LOD and LOQ of 0.09 and 0.30 mg mL-1, respectively. For the crack samples, the cocaine hydrochloride concentrations ranged from 2.5 to 60.8 wt% with an average purity content of 21.3 ± 13.3 wt%. For the seized cocaine samples, variation in hydrochloride content from 1.2 to 22.6 wt% was observed with a mean percentage of 14.19 ± 6.92 wt%. Finally, chemometric tools such as principal component analysis were used to assess the similarity among the samples.

scholarly journals Classification of Hass avocado (persea americana mill) in terms of its ripening via hyperspectral images

TecnoLógicas ◽  
2019 ◽  
Vol 22 (45) ◽  
pp. 109-128 ◽  
Author(s):  
Jhon Pinto ◽  
Hoover Rueda-Chacón ◽  
Henry Arguello
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Agricultural Sector ◽  
Low Cost ◽  
Color Space ◽  
Principal Component ◽  
Persea Americana ◽  
Hyperspectral Images ◽  
Non Invasive ◽  
Hass Avocado

The use of non-invasive and low-cost methodologies allows the monitoring of fruit ripening and quality control, without affecting the product under study. In particular, the Hass avocado is of high importance for the agricultural sector in Colombia because the country is strongly promoting its export, which has generated an expansion in the number of acres cultivated with this fruit. Therefore, this paper aims to study and analyze the ripening state of Hass avocados through non-invasive hyperspectral images, using principal component analysis (PCA) along with spectral vegetation indices, such as the normalized difference vegetation index (NDVI), ratio vegetation index (RVI), photochemical reflectance index (PRI), colorimetry analysis in the CIE L*a*b* color space, and color index triangular greenness index (TGI). In particular, this work conducts a quantitative analysis of the ripening process of a population of 7 Hass avocados over 10 days. The avocados under study were classified into three categories: unripe, close-to-ripe, and ripe. The obtained results show that it is possible to characterize the ripening state of avocados through hyperspectral images using a non-invasive acquisition system. Further, it is possible to know the post-harvest ripening state of the avocado at any given day.

scholarly journals Application of t-SNE to human genetic data

2017 ◽  
Vol 15 (04) ◽  
pp. 1750017 ◽  
Author(s):  
Wentian Li ◽  
Jane E. Cerise ◽  
Yaning Yang ◽  
Henry Han
Keyword(s):  
Dimension Reduction ◽  
Population Stratification ◽  
Association Studies ◽  
Genetic Association Studies ◽  
Principal Component ◽  
Genetic Data ◽  
Visualization Technique ◽  
Data Intensive ◽  
Reduction Techniques ◽  
Dimension Reduction Techniques

The t-distributed stochastic neighbor embedding t-SNE is a new dimension reduction and visualization technique for high-dimensional data. t-SNE is rarely applied to human genetic data, even though it is commonly used in other data-intensive biological fields, such as single-cell genomics. We explore the applicability of t-SNE to human genetic data and make these observations: (i) similar to previously used dimension reduction techniques such as principal component analysis (PCA), t-SNE is able to separate samples from different continents; (ii) unlike PCA, t-SNE is more robust with respect to the presence of outliers; (iii) t-SNE is able to display both continental and sub-continental patterns in a single plot. We conclude that the ability for t-SNE to reveal population stratification at different scales could be useful for human genetic association studies.

scholarly journals Reduction of Ultrasound Imaging Artifacts

2017 ◽  
Author(s):  
Sumesh EP ◽  
Kauther Saleh Mohammed Al-Saqri
Keyword(s):  
Medical Imaging ◽  
Medical Image ◽  
Low Cost ◽  
Non Invasive ◽  
Reduction Techniques ◽  
Different Types ◽  
Diagnosis Accuracy ◽  
Artifacts Reduction ◽  
Imaging Artifacts

Nowadays, with the development of medicine and medical equipment, medical imaging has become an important part in health care sector. Doctors can diagnose diseases using medical imaging without making cut/wound in the human’s body; ultrasound is efficiently used because of its low cost and non-invasive nature and produces good quality images. However, artifacts are a common occurrence in an ultrasound display such as degraded, ambiguity, resolution etc. These artifacts affect the diagnosis accuracy. Thus, artifacts reduction in medical image is essential. In this paper, we describe and study medical image’s artifacts reduction techniques. Different image enhancement techniques for removing different types of artifacts without losing the fine details are studied to produce enhanced images. These reduction techniques are implemented using Matlab. The main objective of this project is to improve the quality of the medical images in order to help doctors to make better diagnosis decisions. This proposed work is expected to be very useful and efficient to use.

scholarly journals Mouth Self-Examination for Prevention and Control of Oral Cavity Cancer

2020 ◽  
Vol 58 (225) ◽  
Author(s):  
Gambhir Shrestha ◽  
Leison Maharjan
Keyword(s):  
Early Detection ◽  
Oral Cavity ◽  
Oral Cavity Cancer ◽  
Low Cost ◽  
Oral Lesions ◽  
Non Invasive ◽  
Prevention And Early Detection ◽  
Self Examination ◽  
And Control ◽  
Public Health Strategies

Oral cavity cancer is one of the most common preventable cancers in the world. The burden of thedisease is high in South Asia. Therefore, public health strategies such as creating awareness anddisease screening should be advocated for its prevention and early detection. Mouth self-examinationserves both the purposes. It is easy to perform, non-invasive, and low-cost methods. It not only helpsin the early detection of suspicious oral lesions but also helps people to quit their high-risk behaviorssuch as consumption of tobacco and alcohol.

Sign in / Sign up

Export Citation Format

Share Document