An Improved Naive Bayesian Human Activity Recognition System with Machine Learning via Support Vector Machine

Enhancing Human Activity Recognition with Support Vector Machine (SVM) over Naive Bayes (NB) is the primary goal of the research. SVM and NB are used in this study project. Using the G power software, the sample size is computed as 10 per group with a pre-test power of 80%, a threshold of 0.05%, and a confidence interval of 95%. SVM predicts a lower accuracy of 91.72% in Human Activity Recognition, while NB predicts a better accuracy of 93.32%. A statistically insignificant difference between the two groups is present, with a significance value of 0.09 (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$p&gt;0.05$</tex>). Compared to NB algorithm, SVM algorithm predicts Human Activity Recognition more accurately.