A Support Vector Machine over a Decision Tree for Enhanced Human Activity Recognition

Abstract

Aim: The main aim of the research is to enhance Human Activity Recognition using Novel SVM (SVM) over Decision Tree. Materials and Methods: SVM and Decision Tree are implemented in this research work. Sample size is calculated using G power software and determined as 10 per group with pretest power 80%, threshold 0.05% and CI 95%. Result:NovelSVM provides a higher of 93.55% compared to Decision Tree algorithm with 92.36% in predicting  lack of accuracy in Human Activity Recognition. Support vector machine has a significance value of 0.07(p>0.05) which is statistically insignificant. Conclusion: SVM algorithm predicts Human Activity Recognition better than Decision Tree algorithm.