Non-Linear Analysis of Heart Rate Variability and ECG Signal Features of Swimmers from NIT-Rourkela: A Case Study

Non-Linear Analysis of Heart Rate Variability and ECG Signal Features of Swimmers from NIT-Rourkela: A Case Study

Anupama Ray (Indian Institute of Technology Delhi, India), Suraj Kumar Nayak (National Institute of Technology Rourkela, India), Biswajeet Champaty (National Institute of Technology Rourkela, India), D. N. Tibarewala (School of BioScience and Engineering, Jadavpur University, India) and Kunal Pal (National Institute of Technology Rourkela, India)
DOI: 10.4018/978-1-5225-0660-7.ch003


The current study deals with the investigation of the effect of long-term endurance training on the autonomic nervous system of healthy adults. ECG was recorded for 5 min under resting condition in a sitting position using an ECG acquisition device for 25 swimmers and 25 age-matched sedentary controls. Heart Rate Variability (HRV) parameters of the volunteers were used for statistical analysis and classification using binary classification trees and artificial neural networks. The LF/HF ratio for swimmers and sedentary controls was found to be 0.89 ± 0.32 and 0.94 ± 0.46, respectively. This may be attributed to the vagal dominance due to endurance training in the swimmers. Statistical ECG signal processing and db06 wavelet based processing were performed to understand the effect of swimming on the cardiac health. The signal classification results indicated that both the HRV and the processed ECG signal features may be used for the classification of the swimmers and the sedentary controls using CART, Boosted tree, Random Forest and neural network algorithms.
Chapter Preview


Recent advances in the biosignal processing techniques allow relating the activity of the autonomic nervous system (ANS) with the cardiovascular mortality, diabetic neuropathy, myocardial infarction and congestive heart failure (Maestri, et al., 2007). Though the efficiency of the ANS may be predicted by performing various biochemical (Richards, et al., 1999), cardiovascular reflex and scintigraphic tests, analysis of ANS activity from the electrocardiogram (ECG)-based non-invasive tests, viz. heart rate variability (HRV), baro-reflex sensitivity, QT interval and heart rate turbulence, are being studied extensively (Katona, McLean, Dighton, & Guz, 1982). Amongst the ECG-based non-invasive tests, the analysis of the HRV is the simplest method to study the sympathovagal balance (Sztajzel, 2004). Continuous HRV monitoring and analysis of the patients may allow the early detection of the above-mentioned diseases, which in turn, help in preventing significant pathophysiological alterations in the patients (Aliberti, et al., 2013).

Athletes have been found to have sinus bradycardia, which may be attributed to the increase in the efficiency of their heart to pump more blood (Ho, Brotherton, Lewis, & Uzunyan, 2014). This helps the sports-persons (e.g. athletes and swimmers) to adapt their body to lack of oxygen during physical strains (Brosnan, et al., 2014). This adaptability of the body have been related to the vagal predominance of the ANS and better synchronization amongst the functioning of the circulatory and the respiratory organs (Aubert, et al., 1996; Baselli, et al.). In the present study, an attempt was made to study the suitability of the parameters obtained from HRV analysis for classifying swimmers from that of sedentary persons. Few studies have been conducted on the effect of the intensive swimming training in prepubertal swimmers (Vinet, Beck, Nottin, & Obert, 2005), training performance enhancement (Atlaoui, et al., 2007) and variation in performance at different altitudes (Schmitt, et al., 2006). The conclusions derived from these studies could not be generalized because the number of subjects in these studies was less. The present study, therefore, aims to compare the effect of swimming on the HRV and its relationship with ANS in long-term trained swimmers with age-matched sedentary controls.

Complete Chapter List

Search this Book: