Date of Award

Spring 2015

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical Engineering

First Advisor

Afghah, Fatemeh Dr.

Abstract

The Smart home has gained widespread attentions due to its flexible integration into everyday life. This next generation of green home system transparently unifies various home appliances, smart sensors and wireless communication technologies. It can integrate diversified physical sensed information and control various consumer home devices, with the support of active sensor networks having both sensor and actuator components. Although smart homes are gaining popularity due to their energy saving and better living benefits, there is no standardized design for smart homes. In this thesis, a smart home design is put forward that can classify and predict the state of the home utilizing historical data of the home. A wireless sensor network was setup in a home to gather and send data to a sink node. The collected data was utilized to train and test a classification model achieving high accuracy with Support Vector Machine (SVM). SVM was further utilized as a predictor of future home states. Based on the data collection, classification and prediction models, a system was designed that can learn, run with minimal human supervision and detect anomalies in a home. The aforementioned attributes make the system an asset for senior care scenarios.

Share

COinS