Building an Intelligent and Efficient Smart Space to Detect Human Behavior in Common Areas

Abstract

Smart spaces have become an integral part of our daily routines to improve quality of life for many different groups of people. The use of embedded systems to build these smart spaces, in combination with data analytics, can provide real-time information about the environment and how it interacts with the people in it. In this paper, we demonstrate how one embedded system that acquires data based on a 2-dimensional positional-grid, movement, temperature and vibration is used to build a smart and pervasive space. Data collected from these sensors is used for real time localization in conjunction with machine learning mechanisms to analyze human activities. We evaluate five machine learning algorithms, namely Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes and Artificial Neural Network applied on a dataset collected in our lab. Results show high classification performance for all methods giving up-to 99.95% classification accuracy. These patterns provide useful information about occupancy patterns, movement patterns, etc., which will be later used to allocate computational resources in the smart space accordingly. Furthermore, our implementation does not use any camera or microphone deployment, hence addressing potential privacy issues.