Improved Human Activity Recognition Using Machine Learning: Support Vector Machine over Logistic Regression

Abstract

Aim: The main aim of the research is to enhance Human Activity Recognition using Support Vector Machine (Novel SVM) over K-Nearest neighbor (Logistic Regression) Materials and Methods: Novel SVM and Logistic Regression 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: Novel SVM provides a higher of 93.50% compared to Logistic Regression algorithm with 92.12% in predicting lack of accuracy in Human Activity Recognition. There is a significant difference between two groups with a significance value of p=0.06 (p>0.05), which is statistically insignificant.. Conclusion: Novel SVM algorithm predicts Human Activity Recognition better than K-Nearest Neighbor Algorithm.