Digital Twins in Human Activity Prediction on Gait Using Extreme Gradient Boosting Local Binary Pattern

Abstract

In recent years, there has been a growing interest in the development of digital twins. Digital twins have become a valuable tool in various fields, including healthcare, for predicting and analyzing human activity patterns. By utilizing the extension extreme gradient (XG) boosting local binary pattern (LBP) algorithm, digital twins can accurately predict human gait and provide valuable insights for healthcare professionals. In this chapter, the authors propose an innovative approach to predict human activities based on gait patterns using an extended XG boost model, enhanced with local binary patterns for feature extraction. The integration of extended XG boost, a highly efficient and interpretable machine learning algorithm, with local binary patterns, a robust technique for texture analysis, enables the extraction of discriminative features from gait data. The utilization of digital twins, specifically with the extension XG BOOST LBP algorithm, has proven to be a valuable tool in predicting and analyzing human gait.