Wyniki wyszukiwania - BazTech

1

The ADHD effect on the actions obtained from the EEG signals

Yaghoobi Karimui R., Azadi S., Keshavarzi P.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

425--437

EN

Attention-deficit/hyperactivity disorder (ADHD) is an important challenge in studies of children's ethology that unbalances the opposite behaviors for creating inattention along with or without hyperactivity. Nevertheless, most studies on the ADHD children, which employed the EEG signals for analyzing the ADHD influence on the brain activities, consid- ered the EEG signals as a random or chaotic process without considering the role of these opposites in the brain activities. In this study, we considered the EEG signals as a biotic process according to these opposites and examined the ADHD effect on the brain activity by defining the dual sets of transitions between states in the complement plots of quantized EEG segments. The results of this study generally indicated that the complement plots of quantized EEG signal have a surprising regularity similar to the Mandala patterns compared to the chaotic processes. These results also indicated that the probability of occurrence of dual sets in the complement plots of ADHD children was averagely different ( p < 0.01) from that of healthy children, so that the SVM classifier developed by these probabilities could significantly separate the ADHD from healthy children (99.37% and 98.25% for training and testing sets, respectively). Therefore, the complement plots of quantized EEG signals rele-vant to the ADHD children not only can quantify informational opposition caused by inattention, hyperactivity and impulsivity, but also these plots can provide remarkable information for developing new diagnostic and therapeutic techniques.

2

Cardiac arrhythmia classification using the phase space sorted by Poincare sections

Yaghoobi Karimui R., Azadi S.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 4

690--700

EN

Many methods for automatic heartbeat classification have been applied and reported in literature, but methods, which used the basin geometry of quasi-periodic oscillations of electrocardiogram (ECG) signal in the phase space for classifying cardiac arrhythmias, frequently extracted a limited amount of information of this geometry. Therefore, in this study, we proposed a novel technique based on Poincare section to quantify the basin of quasi-periodic oscillations, which can fill the mentioned gap to some extent. For this purpose, we first reconstructed the two-dimensional phase space of ECG signal. Then, we sorted this space using the Poincare sections in different angles. Finally, we evaluated the geometric features extracted from the sorted spaces of five heartbeat groups recommend by the association for the advancement of medical instrumentation (AAMI) by using the sequential forward selection (SFS) algorithm. The results of this algorithm indicated that a combination of nine features extracted from the sorted phase space along with per and post instantaneous heart rate could significantly separate the five heartbeat groups (99.23% and 96.07% for training and testing sets, respectively). Comparing these results with the results of earlier work also indicated that our proposed method had a figure of merit (FOM) about 32.12%. Therefore, this new technique not only can quantify the basin geometry of quasi-periodic oscillations of ECG signal in the phase space, but also its output can improve the performance of detection systems developed for the cardiac arrhythmias, especially in the five heartbeat groups recommend by the AAMI.

3

Real-Time Object Tracking using Gradient Vector Flow

Azadi S., Pourjam E., Nikkerdar A., Sharifi M.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 1a

280--283

EN

In this paper an object tracking system with utilizing optical flow technique, and Gradient Vector Flow (GVF) active contours is presented. Optical flow technique is less sensitive to background structure and does not need to build a model for the background of image so it would need less time to process the image. GVF active snakes have good precision for image segmentation. However, due to the high computational cost, they are not usually applicable. Since precision is one of the important factors in the image segmentation, several methods have been developed to overcome the computational speed. In this paper, we, first, recognize the moving object. Then, the object fame with some pixels surrounding to it, was created. Then, this new frame is sent to the GVF filed calculation procedure. Contour initialization is obtained based on the selected pixels. This approach increases the calculation speed, and therefore makes it possible to use the contour for the tracking. The system was built, and tested with a microcomputer. The results show a speed of 10 to 12 frames per second which is considerably suitable for object tracking approaches.

PL

W artykule przedstawiono system śledzenia obiektu z wykorzystaniem techniki Optic Flow oraz Gradiend Vector Flow. Wykrywanie ruchomego obiektu stanowi pierwszy etap działania, następnie ramka zawierająca obiekt przesyłana jest do algorytmu GVF, gdzie określany jest zarys obiektu. Dzięki temu podejściu możliwe jest wykorzystanie, wymagającego obliczeniowo GVF w śledzeniu obiektów. Przedstawiono wyniki eksperymentalne.