Human Activity Recognition Based on Evolution of Features Selection and Random Forest
Christine Dewi, Rung-Ching Chen · 2019
Human Activity Recognition is a promising area having potential to benefit the human society by developing assistive technologies in order to aid elderly, chronically ill and for people with special needs. Accurate activity recognition is challenging because human activity is complex and highly diverse. A comparative study on Human Activity Recognition (HAR) dataset based on four methods, Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA) with different features for selecting the best classifier among the models to test the dataset, has been carry out in this paper. The best classifier is choosing by accuracy of the model. We compare the result of dataset with and without important features selection by RF methods varImp(), Boruta, and Recursive Feature Elimination (RFE) to get the best accuracy. From the four methods, we found that the method RF have high accuracy from every group (98.16%, 98.09%, 93.6%), which is considered as a best classifier.