Occupancy detection in intelligent environments based on low-cost wireless sensor networks and machine learning techniques

Abstract

The smart cities, ideally, can use computer systems who perceive the intention of users, decreasing the need for human intervention to configure the environments. For this, it is necessary to create computational applications that are increasingly adaptable and flexible, improving the services of intelligent environments in a continuous and transparent. In this work, we present a wireless sensor network that detects the occupation in the environment and acts in the lighting and cooling system in an intelligent. Also, some outliers were added to the data in order to validate the results of the classification techniques and check their performance on noise data.