Classification of Arrhythmias from ECG Using Fractal Dimensions and Wavelet Theory

Author(s):  
Ben Ali Sabrine ◽  
Aguili Taoufik
2007 ◽  
Vol 17 (06) ◽  
pp. 1801-1910 ◽  
Author(s):  
ELEONORA BILOTTA ◽  
GIANPIERO DI BLASI ◽  
FAUSTO STRANGES ◽  
PIETRO PANTANO

In this article, we conclude our series of papers on the analysis and visualization of Chua attractors and their generalizations. We present a gallery of 144 n-scroll, 15 hyperchaotic and 37 synchronized systems. Along with time series and FFT we provide 3D visualizations; for some attractors we also supply Lyapunov coefficients and fractal dimensions. The goal in constructing our Gallery has been to make the general public aware of the enormous variety of chaotic phenomena and to change the widespread impression that they are isolated rarities. The Gallery provides a valuable collection of images and technical data which can be used to analyze these phenomena and to reproduce them in future studies. From a scientific point of view, we have tried to identify new methodological approaches to the study of chaos, opening nontraditional perspectives on the complexity of this domain. In our papers, we have discussed a broad range of topics, ranging from techniques for visualizing Chua attractors to computational methods allowing us to make a statistical classification of attractors' positions in phase space and to describe the evolutionary processes through which their shapes change over time. We see these processes as analogous to population dynamics in artificial environments. Within these environments, we use experimental methods to identify the models which guide morphogenetic change and which organize genetic landscapes in parameter space. This paper is organized as follows. First, we provide formal descriptions of the attractors generated by n-scroll, hyperchaotic and synchronized systems. The next section describes a Gallery of Chua attractors, generated by gradually varying the parameters and analyzing the resulting bifurcation maps. We then describe software tools allowing us to perform statistical analyses on selected sets of attractors, to visualize them, to explore their organization in phase space, and to conduct experimental investigations of the morphogenetic processes through which a small set of base attractors can generate a broad range of different forms. In the last section, we describe the creation of a Virtual 3D Gallery displaying some of the attractors we have presented in our six papers. The attractors are organized by theme, as they might be in a museum. The environment allows users to explore the attractors, interact with shapes, listen to music and sounds generated by the attractors, change their spatial organization, and create new shapes. To complete the paper — and the series — we propose a number of general conclusions.


2013 ◽  
Vol 404 ◽  
pp. 485-489 ◽  
Author(s):  
Qiang Huang ◽  
Xiao Zhuo Ouyang ◽  
Qiu Ping Huang

A new state recognition method for rotary machines based on the fractal theory and neural network is proposed, and it is analyzed with the example of bushing abrasion of the connecting rod in diesel engine. Firstly, the wavelet theory is used to reduce noises in the vibration signals and then pick up the generalized fractal dimensions with different iterative steps. They will be the input parameters of the RBF neural network, and the output ones are the four working states. After being trained, the model of neural network can identify the states by the vibration signals. According to the experiment and simulation, the wavelet noise reduction can reproduce the vibration signals clearly and optimize the state recognition. The method based on the fractal theory and neural network is demonstrated to be efficient and feasible, and it can identify the states correctly. It has preferable engineering applicability and the referenced value to other vibration diagnosis of rotary machines.


2012 ◽  
Vol 11 (04) ◽  
pp. 1250034 ◽  
Author(s):  
R. UTHAYAKUMAR ◽  
D. EASWARAMOORTHY

Identification of abnormality in Electroencephalogram (EEG) signals is the vast area of research in the neuroscience. Especially, the classification of healthy and epileptic subjects through EEG signals is the crucial problem in the biomedical sciences. Denoising of EEG signals is another important task in signal processing. The noises must be corrected or reduced before the subsequent decision analysis. This paper presents a wavelet-based denoising method for the recovery of EEG signal contaminated by nonstationary noises and investigates the recognition of healthy and epileptic EEG signals by using multifractal measures such as Generalized Fractal Dimensions. The multifractal measures show the significant differences among normal, interictal and epileptic ictal EEGs with denoising by wavelet transform as the pre-processing step. The denoised artifact-free EEG presents a very good improvement in the identification rate of epileptic seizure. The proposed scheme illustrates with high accuracy through the suitable graphical and statistical tools and performs an important role in the epileptic seizure detection.


Symmetry ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 964
Author(s):  
Olga Cheremisina ◽  
Vladimir Kulagin ◽  
Suad El-Saleem ◽  
Evgeny Nikulchev

The paper describes the substance image formation based on the measurements by multisensor systems and the possibility of the development of a gas analysis device like an electronic nose. Classification of gas sensors and the need for their application for the recognition of difficult images of multicomponent air environments are considered. The image is formed based on stochastic transformations, calculations of correlation, and fractal dimensions of reconstruction attractors. The paper shows images created for substances with various structures that were received with the help of a multisensor system under fixed measurement conditions.


2012 ◽  
Vol 152-154 ◽  
pp. 526-530
Author(s):  
Ke Xu ◽  
Peng Zhou ◽  
Chao Lin Yang

Because steel strips are covered with scales and water during hot-rolling, it is difficult to recognize the defects from images of hot-rolled strips through conventional methods. Principles and characteristics of fractal dimensions were studied, and computation of the fractal dimensions of the defect images with Peleg Covered Carpet is presented. Fractal dimensions of piecewise linearly transformed and smoothed images were used as features for classification of defects. These features were inputted to train the AdaBoost classifier. Experiments with samples of pimples, shells and scales from a real surface inspection system of hot-rolled strips showed that it is effective to recognized scales from other defects, and the total classification rate of this method is higher than 90%.


2018 ◽  
Author(s):  
Yuri A Karetin ◽  
Aleksandra A Kalitnik ◽  
Alina E Safonova ◽  
Eduardas Cicinskas

The fractal formalism in combination with linear image analysis enables statistically significant description and classification of “irregular” (in terms of Euclidean geometry) shapes, such as, outlines of in vitro flattened cells. We developed an optimal model for classifying bivalve Spisula sachalinensis and Callista brevisiphonata immune cells, based on evaluating their linear and non-linear morphological features: dimensional characteristics (area, perimeter), various parameters of cell bounding circle, convex hull, cell symmetry, roundness, and a number of fractal dimensions and lacunarities evaluating the spatial complexity of cells. Proposed classification model is based on Ward’s clustering method, loaded with highest multimodality index factors. This classification scheme groups cells into three morphological types, which can be distinguished both visually and by several linear and quasi-fractal parameters.


Sign in / Sign up

Export Citation Format

Share Document