Germán Castellanos-Domínguez

Automatic Detection of Pathological Voices Using Complexity Measures, Noise Parameters, and Mel-Cepstral Coefficients

This paper proposes a new approach to improve the amount of information extracted from the speech aiming to increase the accuracy of a system developed for the automatic detection of pathological voices. The paper addresses the discrimination capabilities of 11 features extracted using nonlinear analysis of time series. Two of these features are based on conventional nonlinear statistics (largest Lyapunov exponent and correlation dimension), two are based on recurrence and fractal-scaling analysis, and the remaining are based on different estimations of the entropy. Moreover, this paper uses a strategy based on combining classifiers for fusing the nonlinear analysis with the information provided by classic parameterization approaches found in the literature (noise parameters and mel-frequency cepstral coefficients). The classification was carried out in two steps using, first, a generative and, later, a discriminative approach. Combining both classifiers, the best accuracy obtained is 98.23% ± 0.001.

Digital Auscultation Analysis for Heart Murmur Detection

This work presents a comparison of different approaches for the detection of murmurs from phonocardiographic signals. Taking into account the variability of the phonocardiographic signals induced by valve disorders, three families of features were analyzed: (a) time-varying & time–frequency features; (b) perceptual; and (c) fractal features. With the aim of improving the performance of the system, the accuracy of the system was tested using several combinations of the aforementioned families of parameters. In the second stage, the main components extracted from each family were combined together with the goal of improving the accuracy of the system. The contribution of each family of features extracted was evaluated by means of a simple k-nearest neighbors classifier, showing that fractal features provide the best accuracy (97.17%), followed by time-varying & time–frequency (95.28%), and perceptual features (88.7%). However, an accuracy around 94% can be reached just by using the two main features of the fractal family; therefore, considering the difficulties related to the automatic intrabeat segmentation needed for spectral and perceptual features, this scheme becomes an interesting alternative. The conclusion is that fractal type features were the most robust family of parameters (in the sense of accuracy vs. computational load) for the automatic detection of murmurs. This work was carried out using a database that contains 164 phonocardiographic recordings (81 normal and 83 records with murmurs). The database was segmented to extract 360 representative individual beats (180 per class).

An improved method for voice pathology detection by means of a HMM-based feature space transformation

This paper presents new a feature transformation technique applied to improve the screening accuracy for the automatic detection of pathological voices. The statistical transformation is based on Hidden Markov Models, obtaining a transformation and classification stage simultaneously and adjusting the parameters of the model with a criterion that minimizes the classification error. The original feature vectors are built up using classic short-term noise parameters and mel-frequency cepstral coefficients. With respect to conventional approaches found in the literature of automatic detection of pathological voices, the proposed feature space transformation technique demonstrates a significant improvement of the performance with no addition of new features to the original input space. In view of the results, it is expected that this technique could provide good results in other areas such as speaker verification and/or identification.

Detection of obstructive sleep apnea in ECG recordings using time-frequency distributions and dynamic features

Detection of obstructive sleep apnea can be performed through heart rate variability analysis, since fluctuations of oxygen saturation in blood cause variations in the heart rate. Such variations in heart rate can be assessed by means of time-frequency analysis implemented with time-frequency distributions belonging to Cohen’s class. In this work, dynamic features are extracted from time frequency distributions in order to detect obstructive sleep apnea from ECG signals recorded during sleep. Furthermore, it is applied a methodology to measure the relevance of each dynamic feature, before the implementation of k-nn classifier used to recognize the normal and pathologic signals. As a result, the proposed method can be applied as a simple diagnostic tool for OSA with a high accuracy (up to 92.67%) in one-minute intervals.

Selection of Dynamic Features Based on Time–Frequency Representations for Heart Murmur Detection from Phonocardiographic Signals

This work discusses a method for the selection of dynamic features, based on the calculation of the spectral power through time applied to the detection of systolic murmurs from phonocardiographic recordings. To investigate the dynamic properties of the spectral power during murmurs, several quadratic energy distributions have been studied, namely Wigner-Ville, Choi-Williams, smoothed pseudo Wigner-Ville, exponential, and hyperbolic T-distribution. The classification performance has been compared with that using a Short Time Fourier Transform and Continuous Wavelet Transform representations. Furthermore, this work discusses a variety of nonparametric techniques to estimate the spectral power contours as dynamic features that characterize the heart sounds (HS): instantaneous energy, eigenvectors, instantaneous frequency, equivalent bandwidth, subband spectral centroids, and Mel cepstral coefficients. In this way, the aforementioned time–frequency representations and their dynamic features were evaluated by means of their ability to detect the presence of murmurs using a simple k-Nearest Neighbors classifier. Moreover, the relevancies of the proposed dynamic features have been evaluated using a time-varying principal component analysis. The work presented is carried out using a database containing 22 phonocardiographic recordings (16 normal and 6 records with murmurs), segmented to extract 402 representative individual beats (201 per class). The results suggest that the smoothing given by the quadratic energy distribution significantly improves the classification performance for the detection of murmurs in HS. Moreover, it is shown that the power dynamic features which give the best overall classification performance are the MFCC contours. As a result, the proposed method can be implemented as a simple diagnostic tool for primary health-care purposes with high accuracy (up to 98%) discriminating between normal and pathologic beats.

Global and local choice of the number of nearest neighbors in locally linear embedding

Highlights? We propose a new method for automatically computing the number of neighbors in LLE. ? We analyze the global and local properties of the embedding results. ? We study manifolds where the density and the intrinsic dimensionality of the neighborhoods are variable. ? Artificial and real-world datasets were tested. The crux in the locally linear embedding algorithm is the selection of the number of nearest neighbors k. Some previous techniques have been developed for finding this parameter based on embedding quality measures. Nevertheless, they do not achieve suitable results when they are tested on several kind of manifolds. In this work is presented a new method for automatically computing the number of neighbors by means of analyzing global and local properties of the embedding results. Besides, it is also proposed a second strategy for choosing the parameter k, on manifolds where the density and the intrinsic dimensionality of the neighborhoods are changeful. The first proposed technique, called preservation neighborhood error, calculates a unique value of k for the whole manifold. Moreover, the second method, named local neighborhood selection, computes a suitable number of neighbors for each sample point in the manifold. The methodologies were tested on artificial and real-world datasets which allow us to visually confirm the quality of the embedding. According to the results our methods aim to find suitable values of k and appropriated embeddings.

Dynamic Feature Extraction: an Application to Voice Pathology Detection

Abstract In pattern recognition, observations are often represented by the so called static features, that is, numeric values that represent some kind of attribute from observations, which are assumed constant with respect to an associated dimension or dimensions (e.g. time, space, and so on). Nevertheless, we can represent the objects to be classified by means of another kind of measurements that do change over some associated dimension: these are called dynamic features. A dynamic feature can be represented by either a vector or a matrix for each observation. The advantage of using such an extended form is the inclusion of new information that gives abetter representation of the object. The main goal in this work is to extend traditional Principal Component Analysis (normally applied on static features) to a classification task using a dynamic representation. The method was applied to detect the presence of pathology in the speech using two different voice disorders databases, obtaining high classificat...

Regularization parameter choice in locally linear embedding

Locally linear embedding (LLE) is a recent unsupervised learning algorithm for non-linear dimensionality reduction of high dimensional data. One advantage of this algorithm is that just two parameters are needed to be set by user: the number of nearest neighbors and a regularization parameter. The choice of the regularization parameter plays an important role in the embedding results. In this paper, an automated method for choosing this parameter is proposed. Besides, in order to objectively qualify the performance of the embedding results, a new measure of embedding quality is suggested. Our approach is experimentally verified on 9 artificial data sets and 2 real world data sets. Numerical results are compared against two methods previously found in the state of art.

Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering

The computer-assisted analysis of biomedical records has become an essential tool in clinical settings. However, current devices provide a growing amount of data that often exceeds the processing capacity of normal computers. As this amount of information rises, new demands for more efficient data extracting methods appear. This paper addresses the task of data mining in physiological records using a feature selection scheme. An unsupervised method based on relevance analysis is described. This scheme uses a least-squares optimization of the input feature matrix in a single iteration. The output of the algorithm is a feature weighting vector. The performance of the method was assessed using a heartbeat clustering test on real ECG records. The quantitative cluster validity measures yielded a correctly classified heartbeat rate of 98.69% (specificity), 85.88% (sensitivity) and 95.04% (general clustering performance), which is even higher than the performance achieved by other similar ECG clustering studies. The number of features was reduced on average from 100 to 18, and the temporal cost was a 43% lower than in previous ECG clustering schemes.

Improvement of an extended Kalman filter power line interference suppressor for ECG signals

The powerline interference reduction in ECG records is a challenging problem which is still open for research. The powerline signal, measured directly from the transmission line may have amplitude, phase and frequency variations. These reasons make the classical filtering methods sub-optimal in the powerline interference reduction. We propose a tracking method based on Kalman filtering which uses an state space model for the noisy signal and allows adequate discrimination between the ECG signal and the perturbation, even during non-stationarities. The parameters of this algorithm are optimized via genetic algorithms, obtaining a set of values that give it a mean correlation index on the QT database over 0,99.