Intelligent electrocardiogram pattern classification and recognition using low-cost cardio-care system
Electrocardiogram (ECG) contains detailed data relating to incidental abnormality of an issue. Manual analysis of a long time ECG record could be a lengthy process. Computerised ECG analysis supports clinicians in decision making. Whereas planning an occasional-price diagnostic support system, constraints on the system resources limit the processing speed, eventually affecting the reliability. To resolve these issues, 3 key factors are addressed during this study: the feature extraction technique, total range of options and therefore the database used. For feature extraction, `polar Teager energy' algorithm has been developed, yielding nearly 70percent saving in processing time as compared to other well-known methods. Using features with linear relationship results in reduction in feature vector dimension, while not compromising its classification performance. Therefore the linear relationship between two ECG features, particularly `informational entropy'(S) and `mean Teager energy' has been revealed. These features are utilised for ECG beat classification using `fuzzy C-means clustering' algorithm. The algorithm is evaluated using the MIT-BIH database and then tested by ECG measured with the cardio-care unit. The QRS detection performance of the proposed methodology is very smart, with 0.twenty sevenp.c detection error rate. For classification of ECG beats, average sensitivity and positive prediction rate achieved are 98.93p.c each.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here