Application of Naive Bayes Algorithm for Physical Fitness Level Classification

Abstract

The implementation of physical fitness tests requires adequate facilities, so technology is needed to make it easier without having to provide facilities. The purpose of this study is to make it easier to get the results of a person's physical fitness level using age, gender, height and weight data through an intelligent system using the naïve Bayes algorithm without having to do a physical fitness test. This research is included in the Experimental research. The method used in this study used machine learning and classification with the naïve Bayes algorithm. Data analysis techniques use probability by using data tests and evaluations. The evaluation used uses accuracy. The population in this study was 100 college students. Training model scheme 98 and test 2 get an accuracy value when training is 100%, on testing an accuracy value of 50%. The best model is used as a reference in predicting new data, using 5 new data where 3 data already know the VO2Max value with the same prediction value and actual value, then 2 new data are not yet known VO2Max value, the 4th data gets a value of 44.2 and the 5th data gets a value of 33.2. The results of VO2Max testing using the naïve Bayes algorithm are declared accountable. Contribution to future research is to multiply research datasets to improve accuracy and improve user interface quality through development research.