XGBoost-Based Human Activity Recognition Algorithm using Wearable Smart Devices

Abstract

With the popularity of wearable smart devices, human activity recognition (HAR) based on smart sensors has been widely applied in daily life and medical health fields. In order to balance the accuracy of HAR and the complexity of the algorithm, this paper proposes an HAR algorithm based on the extreme gradient boosting (XGBoost) method. The original data collected by sensors contains noise, thus denoising process is firstly performed. Then multi-dimensional features are extracted from the data because of the limited dimensional features, which cannot be directly utilized in the training process. After that, principal component analysis (PCA) is used to reduce the dimensionality of the data in order to alleviate the input complexity of the training model. Finally, the human activity is recognized using the XGBoost method, and the ultimate goal is to obtain the tradeoff between speed and accuracy of the HAR algorithm.