Predictive modeling and cognition to cardio-vascular reactivity through machine learning in Indian adults with sedentary and physically active lifestyle

Physical inactivity in youth is one of the major concerns in today’s world because the technological developments in various areas have made them lethargic, since just clicking a button fulfills most of their daily requirements. Sedentary behavior that is prolonged sitting with no physical activity is the reason behind numerous physiological diseases in human beings such as obesity, diabetes, cardio-vascular disorders, anxiety, colon cancer etc. around the world. Therefore, for a healthy living, it is suggested to do a minimum amount of health enhancing physical activity daily. In this research, we generated a dataset with information regarding sedentary behavior and physical activity and its impact on the overall health of the young subjects. International physical activity questionnaire and a basic body examination based on the metabolic equivalent’s min/week scores are used to collect this information. Several machine-learning techniques namely k-nearest neighbor, linear discriminant analysis, decision tree, support vector machine and Random forest are implemented for identifying and classifying the subjects in terms of sedentary and physically active groups. Healthiness in terms of cardio-vascular activities of the subjects based on their sedentary and physically active behaviors are determined in this paper, the evaluation criteria used for monitoring heart health is heart rate variability.