Heart Rate Analysis
- Petros Arsenos and George Manis, ‘‘Deceleration capacity of heart rate: Two new methods of computation,’’ Biomedical Signal Processing and Control, Elsevier, vol. 14, pp. 158–163, Nov. 2014 [link]
Abstract: Deceleration Capacity (DC) expresses the property of the neural control of the heart extrinsically to decelerate its rate. For the computation of DC a mathematical method has been proposed and used. Although this method was proved of significant prognostic value, it may produce meaningless negative values for DC, something in contradiction with the principle of inter beat deceleration. In this paper we propose two new methods of computation, DCsgn (DC sign) and BBDC (Beat to Beat Deceleration Capacity), which not only give positive values for DC but could also improve the original method. DCsgn modifies the filtering procedure by totally excluding from computation segments that include possible artifacts. It also uses information of four successive beats in order to detect deceleration (acceleration) segments and not only from the anchor points. BBDC bases all computations on two and not on four successive beats, detecting in this way shorter-term relationships. In order to evaluate the proposed methods, a dataset of 20 young and 20 elderly subjects, all healthy, has been used. Experimental results verify our theoretical claims and show that the proposed method can discriminate more efficiently healthy young and elderly subjects than the original method.
- Argyro Kampouraki, George Manis, and Christoforos Nikou, ‘‘Heartbeat timeseries classification with support vector machines,’’ IEEE Transactions on Information Technology in Biomedicine, vol. 13, no. 4, pp. 512–518, Jul. 2009 [link]
Abstract: In this study, heartbeat time series are classified using support vector machines (SVMs). Statistical methods and signal analysis techniques are used to extract features from the signals. The SVM classifier is favorably compared to other neural network-based classification approaches by performing leave-one-out cross validation. The performance of the SVM with respect to other state-of-the-art classifiers is also confirmed by the classification of signals presenting very low signal-to-noise ratio. Finally, the influence of the number of features to the classification rate was also investigated for two real datasets. The first dataset consists of long-term ECG recordings of young and elderly healthy subjects. The second dataset consists of long-term ECG recordings of normal subjects and subjects suffering from coronary artery disease.