Contemporary Human Activity Recognition Based Predictions by Sensors Using Random Forest Classifier

Abstract

The task of recognizing human activities directs extensive divergence of various functions and applications. Despite analysing the intricate activity it endures demanding requirements in contemporary field of research. A subject performs a definite task at a particular time by determining the activity by using sensor data. In this research task we appraise a unique way by using data with supervised learning techniques by placing sensors on the human body by contingent upon classification process at different stages. The State-of-art machine learning approach random forests are widely discussed in terms of covering practical and theoretical aspects of body sensing. The eventual target is the superior rate of accurate predictions effecting Human Activity Recognition further effective for behavioural monitoring, medical and healthcare sectors. Classification processes are deployed for pairs of activities that are distracted often and this work attempts to analyse the essential sensors for the improved prediction. The results shows the best accuracy scores and the remaining of our findings we expose the outline, exhibiting the degree of distraction between features of ranking and human activities which renders back to sensor ranking.