Wireless sensor network based smart home: Sensor selection, deployment and monitoring

Abstract

The ubiquitous nature of miniature wireless sensors and rapid developments in the wireless network technology have revolutionized home monitoring and surveillance systems. The new means and methods of collecting data efficiently and have led to novel applications for indoor wireless sensor networks. The applications are not limited to solely monitoring but can be extended to behavioral recognition. This can be of great value with the elderly as it can allow anomalous behavior to be detected and corrective actions taken accordingly. This paper details the installation and configuration of unobtrusive sensors in an elderly person's house - a smart home in the making - in a small city in New Zealand. The overall system is envisaged to use machine learning to analyze the data generated by the sensor nodes. The novelty of this project is that instead of setting up an artificial test bed of sensors within the University premises, the sensors have been installed in a subject's home so that data can be collected in a real, not artificial, environment.