Acoustic and Device Feature Fusion for Load Recognition

Zoha, A. , Gluhak, A., Nati, M., Imran, M. A. and Rajasegarar, S. (2012) Acoustic and Device Feature Fusion for Load Recognition. In: 2012 6th IEEE International Conference Intelligent Systems, Sofia, Bulgaria, 06-08 Sep 2012, ISBN 9781467322782 (doi: 10.1109/IS.2012.6335166)

Abstract

Appliance-specific Load Monitoring (LM) provides a possible solution to the problem of energy conservation which is becoming increasingly challenging, due to growing energy demands within offices and residential spaces. It is essential to perform automatic appliance recognition and monitoring for optimal resource utilization. In this paper, we study the use of non-intrusive LM methods that rely on steady-state appliance signatures for classifying most commonly used office appliances, while demonstrating their limitation in terms of accurately discerning the low-power devices due to overlapping load signatures. We propose a multilayer decision architecture that makes use of audio features derived from device sounds and fuse it with load signatures acquired from energy meter. For the recognition of device sounds, we perform feature set selection by evaluating the combination of time-domain and FFT-based audio features on the state of the art machine learning algorithms. The highest recognition performance however is shown by support vector machines, for the device and audio recognition experiments. Further, we demonstrate that our proposed feature set which is a concatenation of device audio feature and load signature significantly improves the device recognition accuracy in comparison to the use of steady-state load signatures only.

• Item Type: Conference Proceedings
• Additional Information: The authors acknowledge the support from the REDUCE project grant (no:EP/I000232/1) under the Digital Economy Programme run by Research Councils UK - a cross council initiative led by EPSRC and contributed to by AHRC, ESRC, and MRC.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zoha, Dr Ahmed and Imran, Professor Muhammad
• Authors: Zoha, A., Gluhak, A., Nati, M., Imran, M. A., and Rajasegarar, S.
• College/School: College of Science and Engineering > School of Engineering > Systems Power and Energy
• ISSN: 1541-1672
• ISBN: 9781467322782
• Published Online: 22 October 2012
• Copyright Holders: Copyright © 2012 IEEE
• First Published: First published in 2012 6th IEEE International Conference Intelligent Systems
• Publisher Policy: Reproduced in accordance with the publisher copyright policy