Time-Frequency analysis of Different types of signals
Mohamed Nabih Ali Mohamed Nawar;
Abstract
Cardiovascular disorders (CVD’s) or Heart disease, which is called coronary artery disease, is a broad term that can refer to a human heart condition. CVD’s are the first cause of death internationally. Taking in consideration that heart auscultation still the primary tool for heart diagnosis in the small health care centers of the rustic areas. It was found that it is highly dependent on the experience of the clinicians.
Phonocardiogram (PCG) is one of the best graphical representations of heart sounds and murmurs (abnormal heart sounds). It documents the timing of heart sounds, annotates their different relative intensities, analyzing the heart sound signals. PCG provide an early warning for heart diseases and provides valuable information concerning the heart valves. Though, with intelligent algorithms and methods we can analyze heart signals easily and classifying heart diseases.
This thesis presents an intelligent decision system for detecting abnormalities in heart sound signals "PCG" based on Discrete Wavelet Transform (DWT) and Artificial Neural Network (ANN) techniques to enhance the heart diseases classification accuracy.
The Large heart sound signals database PASCAL was used training and testing the developed system. DWT was used to denoised "PCG" signals and to extract the main features of the signals.
The "ANN" classifier based on backpropagation algorithm was used to detect the abnormalities of the "PCG" signals using the extracted wavelet coefficients. Performance of the proposed system have been evaluated and ANN classifier gave an overall accuracy 97.97 %. The proposed system showed high performance in comparison with other classification techniques for the same "PCG".
Heart signal abnormality detection circuit was built and programmed to be capable of detecting abnormalities in heart signals. The circuit was constructed using Arduino Uno board in corporation with "Atmega328" microcontroller manufactured with Atmel Company.
Achieved results revealed that the proposed system has ability for "PCG" signals classification, and to give assistance to the clinicians for making an accurate diagnosis of heart diseases.
Keywords:
Biomedical Engineering – Digital Electronics – Theoretical Physics – Biophysics
Phonocardiogram (PCG) is one of the best graphical representations of heart sounds and murmurs (abnormal heart sounds). It documents the timing of heart sounds, annotates their different relative intensities, analyzing the heart sound signals. PCG provide an early warning for heart diseases and provides valuable information concerning the heart valves. Though, with intelligent algorithms and methods we can analyze heart signals easily and classifying heart diseases.
This thesis presents an intelligent decision system for detecting abnormalities in heart sound signals "PCG" based on Discrete Wavelet Transform (DWT) and Artificial Neural Network (ANN) techniques to enhance the heart diseases classification accuracy.
The Large heart sound signals database PASCAL was used training and testing the developed system. DWT was used to denoised "PCG" signals and to extract the main features of the signals.
The "ANN" classifier based on backpropagation algorithm was used to detect the abnormalities of the "PCG" signals using the extracted wavelet coefficients. Performance of the proposed system have been evaluated and ANN classifier gave an overall accuracy 97.97 %. The proposed system showed high performance in comparison with other classification techniques for the same "PCG".
Heart signal abnormality detection circuit was built and programmed to be capable of detecting abnormalities in heart signals. The circuit was constructed using Arduino Uno board in corporation with "Atmega328" microcontroller manufactured with Atmel Company.
Achieved results revealed that the proposed system has ability for "PCG" signals classification, and to give assistance to the clinicians for making an accurate diagnosis of heart diseases.
Keywords:
Biomedical Engineering – Digital Electronics – Theoretical Physics – Biophysics
Other data
| Title | Time-Frequency analysis of Different types of signals | Other Titles | التحليل الترددى-الزمنى لأنواع مختلفة من الإشارات | Authors | Mohamed Nabih Ali Mohamed Nawar | Issue Date | 2016 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.