Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 43186 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Shamsollahi, Mohammad Bagher
- Abstract:
- About 42 percent of annual mortality in all around the world is originated from cardiovascular arrhythmias and diseases. One of these arrhythmias is atrial fibrillation whose onset and persistence can produce clot and consequently cause stroke. The basis of our research are upon this idea that dangerous heart arrhythmias do not happen abruptly and there always are some background signs before occurrence of them. In our approach to predict the onset of atrial fibrillation, by analyzing ECG signal in order to extract distinguishing features, we want to classify signals which will terminate Paroxysmal Atrial Fibrillation (PAF) from signals which won’t end with PAF. In this thesis, we propose an algorithm in order to predict PAF which depends on the number of premature beats before onset of PAF, changes of heart rate variability and information of atrial components. In order to calculate the number of premature beats, we use Heart Hate Variability (HRV) signal and to access information of atrial components, we calculate the variance and area under the curve of absolute value of Intrinsic Mode Functions (IMF) extracted by applying Empirical Mode Decomposition (EMD) methos. By using these three features accompanied by variance of HRV signal we manage to predict the onset of PAF on the “paroxyxmal atrial fibrillation challenge” database (AFPDB) and achieve prediction accuracy of 88 percent and 89 percent on training and test database, respectively. After that, in order to have better approximation of concept of prediction, we associate prediction accuracy with time. So, we use not the whole time of the data but we use the time slots far from the end of data, consequently we manage to achieve the curve which describe the prediction accuracy against time. For aforementioned database, prediction accuracy in the last 50 seceonds of data has increasing trend which starts from 65 percent and almost reaches to 90 percent
- Keywords:
- Empirical Modes Decomposition (EMD)Method ; Premature Beats ; Heart Rate Variability ; Paroxysmal Atrial Fibrillation (PAF) ; Intrinsic Mode Function
Digital Object List-
محتواي پايان نامه - view
Bookmark