Physical Activity Recognition Using Single Sensor

Rapid advancement in the field of Artificial Intelligence, to be more specific in Machine Learning and Nanotechnology, strengthens hopes to better understand human mind. Ubiquitous Computing helped in the creation of intelligent environments pervaded by these visible and invisible devices, which are affecting and improving all aspects of human life. So, as a consequence, smart environments work on the behalf of humans for ease of comfort. The aim of this work was to develop part of a ubiquitous care system to monitor elderly basic daily life activities; stand, sit, walk, lay and transitional activities. This book investigates the use of a wearable sensor to develop and evaluate the activity classification scheme with reliable accuracy in the real-world situations. A semi-supervised clustering model is presented which, unlike traditional clustering algorithms, require less labelled data to train the classifier. The core model for the clustering approach is a physical activity transition model that imitates different states of postures and transitions of human activity.