Human Activity Recognition on Smartphones using Innovative Logistic Regression and Comparing Accuracy of Naive Bayes Algorithm

Abstract

The objective of this study is to compare the Naive Bayes algorithm with Innovative Logistic Regression in order to enhance human activity identification for sitting and walking. To predict human activity, Naive Bayes and Innovative Logistic Regression are used with different training and testing splits. From each group, ten sets of samples are selected, yielding a total of twenty samples. About 80% of the data from an independent sample T test were utilized in the Gpower test (g power setup parameters: α = 0.05 and power = 0.80, β = 0.2). Compared to Naive Bayes (90.7210%), Innovative Logistic Regression (95.5680%) has higher accuracy, with a statistical significance value of P = 0.003 (p < 0.05). When compared to Naive Bayes, Innovative Logistic Regression has higher accuracy.