Recently it has been noted that user behaviour can have a large impact on the final energy consumption in buildings. Through the combination of mathematical modelling and data from wireless ambient sensors, we can model human behaviour patterns and use the information to regulate building management systems (BMS) in order to achieve the best trade-off between user comfort and energy efficiency. In this work, we have modelled user occupancy and activity patterns using Machine Learning approaches. We have applied non-linear multiclass Support Vector Machines (SVMs) to deal with the complex nature of the data collected from various sensors to accurately identify user occupancy and activities of daily living (ADL) patterns. To validate our results, we also used other methodologies (i.e. Hidden-Markov Model and k-Nearest Neighbours). The experimental results show that our proposed approach outperforms the other methods for the scenarios evaluated.

Recently, it has been noted that user behaviour can have a large impact on the final energy consumption in buildings. Through the combination of mathematical modelling and data from wireless ambient sensors, we can model human behaviour patterns and use the information to regulate building management systems (BMS) in order to achieve the best trade-off between user comfort and energy efficiency. Furthermore, streaming sensor data can be used to perform real-time classification. In this work, we have modelled user activity patterns using both offline and online learning approaches based on non-linear multi-class Support Vector Machines. We have conducted a comparison study with other machine learning approaches (i.e. Linear SVM, Hidden-Markov and K-nearest models). Experimental results show that our proposed approach outperforms the other methods for the scenarios evaluated in terms of accuracy and processing speed.

No abstract

No abstract