A Novel Framework for Smart Home Human Activity Identification using Binary Cuckoo Search Metaheuristic

Abstract

Human activity recognition has been a topic of attraction among researchers and developers because of its enormous usage in widespread region of human life. The varied human activities and the way they are executed at individual level are the main challenges to be recognized in human behavior modeling. In this thesis a novel methodology is proposed that recognizes human activities from the behavior of individuals in a smart home environment. The dataset considered in the work is captured using Bluetooth Low Energy (BLE), a popular technology for indoor localization. The proposed framework is a binary cuckoo search based stacking model that collectively exploits multiple base learners for human activities recognition from the gathered accelerometer sensors data mounted on wearable and mobile devices. The work is tested on the newly developed SPHERE dataset to recognize user activities in smart home environment. The experimental results showcase the effectiveness of the proposed approach, outperforming other recent existing techniques on the dataset, giving high predictive accuracy value of 93.77 % via 10-fold cross validation.