Activity Learning and Recognition Using Margin Setting Algorithm in Smart Homes

Intelligent environments is receiving lots of attention in the research community. With lots of algorithms developed over the years to model activity and pattern recognition, most algorithms are still not suitable for activity learning. Early research was focused on home automation but recent research is moving towards an intelligent environment that is capable of identifying trends and patterns and make effective decisions. Making this feat a possibility requires extensive research in the fields of artificial intelligence, machine learning and statistical learning. These tools enable an intelligent environment to analyze, control and make intelligent decision according to the condition set by the user. In this paper, we introduce a novel supervised learning algorithm called margin setting (MSA) and apply it to ARAS (Activity Recognition with Ambient Sensing) dataset to help recognize patterns in the activities of daily living (ADL) of two residents in a smart home intelligent environment. Our goal is to introduce an accurate pattern recognition and activity learning method. The experimental results show the accuracy and efficiency of the proposed method using the dataset, which contains 20 different binary sensors with 27 different activities.