slugAn Approach To Automatically Detect Cardiac Arrhythmia
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2014, Vol 2, Issue 4
Abstract
Electrocardiogram (ECG), a non-invasive technique is used as a primary diagnostic tool for cardiovascular diseases. The main objective is to make the analysis of normal and abnormal beats easy so that the patient could be diagnosed for the heart problems in less time as well more accurately so that medical practitioners have primary information about the ailment and could start a treatment early.. However, it is very difficult to identify the minute changes in ECG signals which indicate a particular type of cardiac abnormality, hence imposing the need for a computer assisted diagnosis tool. A computer based intelligent system for analysis of cardiac states is very useful in diagnostics and disease management. In this work, we propose a methodology for the automatic detection of normal and abnormal cardiac conditions using ECG signals. ECG signals from MIT BIH arrhythmia database were used for analysis and classification. The ECG signals were first denoised using wavelet based denoising technique. After the denoising, it was subjected to QRS complex detection. The QRS complex is physiologically an important peak in the ECG signal. After detection of QRS complex, the ECG was segmented to obtain 200 samples segment as a beat for subsequent analysis. The segmented ECG signal was used for its dimensionality reduction using Principal component analysis(PCA).PCA implementation decreases the training error and the sum of the training and test times. In total 12 components were used for the pattern classification using feed forward neural network. The proposed system is clinically ready to deploy for mass screening programs. Overall, compared to previous techniques, this system is more suitable for diagnosis of cardiac arrhythmia with highest accuracy.
Authors and Affiliations
Priyanka Urban, E. Smily Jeya Jothi
Keywords
Related Articles
- EP ID EP17971
- DOI -
- Views 354
- Downloads 12
Applying Genetic Algorithm on Dynamic Programming Problems
GA is one of the mostly used heuristic search methodology in the present time. Without evolutionary programming and evolutionary algorithms the whole search process is wasted. GA is applied in various fields of search a...
An Opinion Mining By Manhattan Clustering Using Decision Tree Feature Selection
In present era Opinion mining plays a major character in text mining applications, and people are more depend on the web for many actions like purchasing, investment, business markings, etc. These applications led to a...
Congestion Management in a Deregulated Power System Using Fuzzy Logic with IPFC
Congestion management is a major problem that the independent system operator would face in scheduling and rescheduling process in a deregulated electricity market era. One of the most practiced, an obvious method is co...
Comparative Analysis on Environmental and Economic Parameters of Biomass and Coal Fired Thermal Power Plant
This paper is trying to focus our attention to fulfil our current energy demands in sustainable way rather than the conventional methodology that was prevalent before independence in our country. One of the finest ways...
Development of Low Power Micro Inverter for Use In House Hold Applications
The paper presents the design of a single phase low power solar micro inverter that can be used in homes for low power applications. The basic idea behind this research is to make most use of solar energy in operating s...