Miguel Antonio Sovierzoski

Identifying eye blinks in EEG signal analysis

The electroencephalogram is a noninvasive record of the brain activity using electrodes placed on the scalp. The electroencephalographic signal can be contaminated by other signal sources, called artifacts. Among the several artifact sources, eye blink is one of the main sources of interference in the EEG exam, and can be erroneously interpreted as epileptiform activity. This study analyzed eye blink signals acquired by EEG electrodes. The main objective of this study was to develop a neural network classifier specialized in the identification of eye blinks in EEG signals. The statistical study of the eye blinks in EEG signals, the methodology and the results of the identification of this event are presented.

Pupil and iris detection in dynamic pupillometry using the OpenCV library

The aim of this work is to describe a computer system to detect and measure the pupil and iris size with applications to dynamic pupillometry. The system was written using the OpenCV library to perform the real time video processing. The frames are captured in grayscale and processed using normalization and threshold techniques to enhance the image, and then, the Hough Transformation is used to detect the iris and the Greedy Snakes Algorithm is used to detect the pupil.

Binary Neural Classifier of Raw EEG Data to Separate Spike and Sharp Wave of the Eye Blink Artifact

This work presents the study, the development and the evaluation of a binary neural classifier to separate the epileptiform events (spike and sharp wave) and eye blink artifacts in electroencephalography exams (EEG). The eye blink is the main artifact that affects the performance of the automatic systems for identification of epileptiform events in EEG signals. The methodology for the development of the binary neural classifier through an ANN MLP is approached. The performance evaluation of the classifier is realized through the statistic index, performance index and ROC Curve with performance criterion. With the EER criterion was obtained sensitivity of 85.9%, specificity of 87.1%, positive selectivity of 86.7% and negative selectivity of 86.3%.

Pulmonary crackle characterization: approaches in the use of discrete wavelet transform regarding border effect, mother-wavelet selection, and subband reduction

Introduction Crackles are discontinuous, non-stationary respiratory sounds and can be characterized by their duration and frequency. In the literature, many techniques of filtering, feature extraction, and classification were presented. Although the discrete wavelet transform (DWT) is a well-known tool in this area, issues like signal border extension, mother-wavelet selection, and its subbands were not properly discussed. Methods In this work, 30 different mother-wavelets 8 subbands were assessed, and 9 border extension modes were evaluated. The evaluations were done based on the energy representation of the crackle considering the mother-wavelet and the border extension, allowing a reduction of not representative subbands. Results Tests revealed that the border extension mode considered during the DWT affects crackle characterization, whereas SP1 (Smooth-Padding of order 1) and ASYMW (Antisymmetric-Padding (whole-point)) modes shall not be used. After DWT, only 3 subbands (D3, D4, and D5) were needed to characterize crackles. Finally, from the group of mother-wavelets tested, Daubechies 7 and Symlet 7 were found to be the most adequate for crackle characterization. Discussion DWT can be used to characterize crackles when proper border extension mode, mother-wavelet, and subbands are taken into account.

Evaluation of Benchmark Indexes to Determine the Best Performance of a Binary Neural Classifier

This work approaches the performance evaluation of a binary neural classifier to identify eye blink in EEG signals. The following statistical indexes are presented: sensitivity (Sn), specificity (Sp), positive selectivity (PSl) and negative selectivity (NSl). From these statistical indexes the performance indexes of the binary classifiers are presented: accuracy, Youden index, product Sn and Sp, Matthews Correlation Coeficient (MCC), Approximate Correlation (AC), ROC Curve with AUC index and EER criteria. A method is developed to evaluate a case study with binary neural classifier, determining the performance in each training epoch and through the training. Graphics present the obtained results. As a result for this case study, with a binary neural classifier, some indexes indicated a determined training epoch with the same threshold value as the condition which presented the best performance, while other indexes presented a near training epoch as the one with the best performance.

Integrated Technological Resource in the Construction of the Teaching and Learning of Technical Nursing Course

This paper shows the importance of a high-fidelity human simulator as a methodological tool able to make a significant contribution to the learning process of nursing technician students of the Federal Education, Science and Technology Institute of Roraima (IFRR). From this simulator you can build several scenarios of specific nursing procedures for the Intensive Care Unit (ICU) in order to be efficiently used in the teaching-learning process. The academic literature contributions available regarding the use of simulators in the teaching process of Health Science were evaluated. The use of this methodological resource should be seen as a trend in the clinical reasoning of nursing students, improving their knowledge and developing psychomotor skills.

An mHealth Remote Monitor System Approach Applied to MCC Using ECG Signal in an Android Application

Nowadays some mHealth paradigms are being subject to changes with the emergence and advances in Mobile Cloud Computing (MCC) using low power data exchange systems like Bluetooth for sensors. This paper shows a different approach of MCC applied to mHealth by introducing a new architecture developed to an application for mobile devices, treating ECG signals using Cloud Data storage and a specially developed frame architecture between the sensor and the mobile device to detect and correct as many errors as possible. The proposed approach not only shows the convergence of MCC, but also focuses on the mHealth scenario to show some benefits of its use in the modern world. A secure link algorithm was also developed between mobile devices and the ECG sensor transmitter.

Influences of the signal border extension in the discrete wavelet transform in EEG spike detection

Introduction The discrete wavelet transform is used in many studies as signal preprocessor for EEG spike detection. An inherent process of this mathematical tool is the recursive wavelet convolution over the signal that is decomposed into detail and approximation coefficients. To perform these convolutions, firstly it is necessary to extend signal borders. The selection of an unsuitable border extension algorithm may increase the false positive rate of an EEG spike detector. Methods In this study we analyzed nine different border extensions used for convolution and 19 mother wavelets commonly seen in other EEG spike detectors in the literature. Results The border extension may degrade an EEG spike detector up to 44.11%. Furthermore, results behave differently for distinct number of wavelet coefficients. Conclusion There is not a best border extension to be used with any EEG spike detector based on the discrete wavelet transform, but the selection of the most adequate border extension is related to the number of coefficients of a mother wavelet.

Body dominance during virtual tennis game: preliminary results

The movement recovery and the independence in the activities of daily living in a short period of time are among the aims of the physical therapy. For this the video games are being used in the physiotherapy clinics to increase the body balance, and the strength and tonus of the muscle. Seventy percentage of the patients in treatment have some orthopedic problem or neurological condition. In this work we analyzed eleven healthy individuals, wearing waistcoat with accelerometers, sandals with pressure sensors, and electromyography on the calves, for monitoring the body swing, and electrical signal from legs, playing a Nintendos tennis game. The results showed that the functional differences between right-hander and left-hander during playing video game are useful for physical therapy.

The Relationship of Sleepiness and Dynamic Pupillometry: A 24-Hour Evaluation

This article evaluates the relationship between sleepiness and pupillometry in patients tested for 24 hours. The volunteer was tested every 30 minutes. The parameters for the pupillary reflex were extracted using image processing algorithms and the graphs related to latency, and constriction of the pupil were presented. Considering the results, it is suggested that is not possible to infer a direct relationship between the dynamic pupillometry and sleepiness.