André Augusto Spadotto

Feature selection through gravitational search algorithm

In this paper we deal with the problem of feature selection by introducing a new approach based on Gravitational Search Algorithm (GSA). The proposed algorithm combines the optimization behavior of GSA together with the speed of Optimum-Path Forest (OPF) classifier in order to provide a fast and accurate framework for feature selection. Experiments on datasets obtained from a wide range of applications, such as vowel recognition, image classification and fraud detection in power distribution systems are conducted in order to asses the robustness of the proposed technique against Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and a Particle Swarm Optimization (PSO)-based algorithm for feature selection.

Software para análise quantitativa da deglutição

OBJECTIVE: The present paper is aimed at introducing a software to allow a detailed analysis of the swallowing dynamics. MATERIALS AND METHODS: The sample included ten (six male and four female) stroke patients, with mean age of 57.6 years. Swallowing videofluoroscopy was performed and images were digitized for posterior analysis of the pharyngeal transit time with the aid of a chronometer and the software. RESULTS: Differences were observed in the average pharyngeal swallowing transit time as a result of measurements with chronometer and software. CONCLUSION: This software is a useful tool for the analysis of parameters such as swallowing time and speed, allowing a better understanding of the swallowing dynamics, both in the clinical approach of patients with oropharyngeal dysphagia and for scientific research purposes.

Protocolo para controle de eficácia terapêutica em disfagia orofaríngea neurogênica (PROCEDON)

PURPOSE: to submit a proposal for efficacy control in neurogenic oropharyngeal dysphagia. METHODS: the protocol was proposed in accordance with other researches and applied in one post-stroke individual, with right-hemispheric lesion confirmed by computed tomography, with oropharyngeal dysphagia, male gender, 66-year old, with laringotraqueal aspiration and using nasogastric feeding tube before swallowing therapy. In order to control the therapy effectiveness in pre- and post-swallowing therapy, the following procedures were applied: classification of severity degree for oropharyngeal dysphagia, functional oral intake scale (FOIS), videofluoroscopic evaluation of swallowing with additional swallowing pharyngeal transit time evaluation using a specific software and individual perception. RESULTS: before swallowing therapy, severe oropharyngeal dysphagia, FOIS level 1, presence of laryngotracheal aspiration, and 13 seconds of pharyngeal transit time were found. After swallowing therapy, moderate oropharyngeal dysphagia, FOIS level 5, absence of laryngotracheal aspiration, and 4 seconds of pharyngeal transit time were found. CONCLUSION: the proposed protocol could measure changes, both for pathophysiology of swallowing as well as for oral ingestion of the individual. We believe that it is still necessary to include nutritional and lung status of the individual in efficacy control of oropharyngeal dysphagia.

Taste and Temperature in Swallowing Transit Time after Stroke

Background: Oropharyngeal dysphagia is common in individuals after stroke. Taste and temperature are used in dysphagia rehabilitation. The influence of stimuli, such as taste and temperature, on swallowing biomechanics has been investigated in both healthy individuals and in individuals with neurological disease. However, some questions still remain unanswered, such as how the sequence of offered stimuli influences the pharyngeal response. The goal of the present study was to determine the influence of the sequence of stimuli, sour taste and cold temperature, on pharyngeal transit time during deglutition in individuals after stroke. Methods: The study included 60 individuals with unilateral ischemic stroke, 29 males and 31 females, aged 41–88 years (mean age: 66.2 years) examined 0–50 days after ictus (median: 6 days), with mild to moderate oropharyngeal dysphagia. Exclusion criteria were hemorrhagic stroke patients, patients with decreased level of consciousness, and clinically unstable patients, as confirmed by medical evaluation. The individuals were divided into two groups of 30 individuals each. Group 1 received a nonrandomized sequence of stimuli (i.e. natural, cold, sour, and sour-cold) and group 2 received a randomized sequence of stimuli. A videofluoroscopic swallowing study was performed to analyze the pharyngeal transit time. Four different stimuli (natural, cold, sour, and sour-cold) were offered. The images were digitalized and specific software was used to measure the pharyngeal transit time. Since the values did not present regular distribution and uniform variances, nonparametric tests were performed. Results: Individuals in group 1 presented a significantly shorter pharyngeal transit time with the sour-cold stimulus than with the other stimuli. Individuals in group 2 did not show a significant difference in pharyngeal transit time between stimuli. Conclusions: The results showed that the sequence of offered stimuli influences the pharyngeal transit time in a different way in individuals after stroke and suggest that, when the sour-cold stimulus is offered in a randomized sequence, it can influence the response to the other stimuli in stroke patients. Hence, the sour-cold stimulus could be used as a therapeutic aid in dysphagic stroke patients.

Classification of normal swallowing and oropharyngeal dysphagia using wavelet

Oropharyngeal dysphagia is characterized by any alteration in swallowing dynamics which may lead to malnutrition and aspiration pneumonia. Early diagnosis is crucial for the prognosis of patients with dysphagia, and the best method for swallowing dynamics assessment is swallowing videofluoroscopy, an exam performed with X-rays. Because it exposes patients to radiation, videofluoroscopy should not be performed frequently nor should it be prolonged. This study presents a non-invasive method for the pre-diagnosis of dysphagia based on the analysis of the swallowing acoustics, where the discrete wavelet transform plays an important role to increase sensitivity and specificity in the identification of dysphagic patients.

Optimum path forest classifier applied to laryngeal pathology detection

Optimum path forest-based classifiers are a novel approach for supervised pattern recognition. The OPF classifier differs from traditional approaches by not estimating probability density functions of the classes neither assuming samples linearity, and creates a discrete optimal partition of the feature space, in which the decision boundary is obtained by the influence zones of the most representative samples of the training set. Due to the large number of applications in biomedical signal processing involving pattern recognition techniques, specially voice disorders identification, we propose here the laryngeal pathology detection by means of OPF. Experiments were performed in three public datasets against SVM, and a comparison in terms of accuracy rates and execution times was also regarded.

Oropharyngeal dysphagia identification using wavelets and optimum path forest

The swallowing disturbers are defined as oropharyngeal dysphagia when present specifies signals and symptoms that are characterized for alterations in any phases of swallowing. Early diagnosis is crucial for the prognosis of patients with dysphagia and the potential to diagnose dysphagia in a noninvasive manner by assessing the sounds of swallowing is a highly attractive option for the dysphagia clinician. This study proposes a new framework for oropharyngeal dysphagia identification, having two main contributions: a new set of features extract from swallowing signal by discrete wavelet transform and the dysphagia classification by a novel pattern classifier called OPF. We also employed the well known SVM algorithm in the dysphagia identification task, for comparison purposes. We performed the experiments in two sub-signals: the first was the moment of the maximal peak (MP) of the signal and the second is the swallowing apnea period (SAP). The OPF final accuracy obtained were 85.2% and 80.2% for the analyzed signals MP and SAP, respectively, outperforming the SVM results.

Componentes do sinal acústico da deglutição: estudo preliminar

PURPOSE To analyze the components of the acoustic signal of swallowing using a specific software. METHODS Fourteen healthy subjects ranging in age from 20 to 50 years (mean age 31 ± 10 years), were evaluated. Data collection consisted on the simultaneous capture of the swallowing audio with a microphone and of the swallowing videofluoroscopic image. The bursts of the swallowing acoustic signal were identified and their duration and the interval between them were later analyzed using a specific software, which allowed the simultaneous analyses between the acoustic wave and the videofluoroscopic image. RESULTS Three burst components were identified in most of the swallows evaluated. The first burst presented mean time of 87.3 milliseconds (ms) for water and 78.2 for the substance. The second burst presented mean time of 112.9 ms for water and 85.5 for the pasty substance. The mean interval between first and second burst was 82.1 ms for water and 95.3 ms for the pasty consistency, and between second and third burst was 339.8 ms for water and 322.0 ms for the pasty consistency. CONCLUSION The software allowed the visualization of three bursts during the swallowing of healthy individuals, and showed that the swallowing signal in normal subjects is highly variable.

Residual signal auto-correlation to evaluate speech in Parkinson's disease patients

OBJECTIVE To evaluate the maximum residual signal auto-correlation also known as pitch amplitude (PA) values in patients with Parkinsons disease (PD) patients. METHOD The signals of 21 Parkinsons patients were compared with 15 healthy individuals, divided according age and gender. RESULTS Statistical difference was seen between groups for PA, 0.39 for controls and 0.25 for PD. Normal value threshold was set as 0.3; (p<0.001). In the Parkinsons group 80.77%, and in the control group only 12.28%, had a PA<0.3 demonstrating an association between these variables. The dispersion diagram for age and PA for PD individuals showed p=0.01 and r=0.54. There was no significant difference in relation to gender and PA between groups. CONCLUSION The significant differences in pitchs amplitude between PD patients and healthy individuals demonstrate the methods specificity. The results showed the need of prospective controlled studies to improve the use and indications of residual signal auto-correlation to evaluate speech in PD patients.

Robust and fast Vowel Recognition Using Optimum-Path Forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy.