Abstract
Smart meters are the next generation gas and electricity meters where the meter readings are presented digitally and accurately to the consumer via an In-Home Display unit. Access to the data sets generated by smart meters is becoming increasingly prevalent. As such, this paper presents an approach for detecting age groups from aggregated smart meter data. The benefits of achieving this range from healthcare cluster mapping for smart resource allocation and intelligent forecasting, to anomaly detection within age-range groups. The technique proposed and presented in this paper uses a cloud analytics platform for the data processing. Using this approach, the classification is able to achieve a 75.1% AUC prediction accuracy using a two-class decision forest and a 74.6% AUC with a boosted two-class decision tree. A two-class linear regression model, which is able to achieve a 53.7% accuracy, is applied as a benchmark for comparison with the decision tree approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Song, H., Srinivasan, R., et al.: Health Monitoring Using Smart Systems in Smart Cities: Foundations, Principles, and Applications, pp. 773–792. Wiley, Hoboken (2017)
Chalmers, C., Hurst, W., et al.: Smart monitoring: an intelligent system to facilitate health care across an ageing population. In: International Conference on Emerging Networks and Systems Intelligence (2016)
Kalogridis, G., Dave, S.: Privacy and eHealth-enabled smart meter informatics. In: International Conference on e-Health Networking, Applications and Services, Natal, pp. 116–121 (2014)
Yassine, A., Singh, S., et al.: Mining human activity patterns from smart home big data for health care applications. IEEE Access 5, 13131–13141 (2017)
Wang, Y., Chen, Q., Hong, T., Kang, C.: Review of smart meter data analytics: applications, methodologies, and challenges. IEEE Trans. Smart Grid 10, 3125–3148 (2018)
Yamagata, C., Coppola, J.F., et al.: Mobile app development and usability research to help dementia and Alzheimer patients. In: Long Island Systems, Applications and Technology Conference, pp. 1–6 (2013)
CER Smart Metering Project - Gas Customer Behaviour Trial, 2009–2010 and also ISSDA, in the following way: Accessed via the Irish Social Science Data Archive. www.ucd.ie/issda. Accessed: 11 Sept 2018
Higuera, V., Ellen Ellis, M.: 10 Early Symptoms of Dementia. Healthline Newsletter, April 2017
Yun, W., Kim, D., et al.: Two-dimensional logistic regression. In: International Conference on Tools with Artificial Intelligence, Patras, pp. 349–353 (2007)
Wellmer, F.W.: Standard deviation and variance of the mean. In: Wellmer, F.W. (ed.) Statistical Evaluations in Exploration for Mineral Deposits. Springer, Heidelberg (1998). https://doi.org/10.1007/978-3-642-60262-7_6
McNeese, B.: Are the Skewness and Kurtosis Useful Statistics? SPC for Excel (2016)
Westfall, P.H.: Kurtosis as Peakedness, 1905–2014. R.I.P. Am. Stat. 68(3), 191–195 (2014)
Acknowledgements
This research project is funded by the EPRSC - EP/R020922/1. Owing to the ethical sensitive nature of this research, the data underlying this publication cannot be made openly available. However, it is available for request from Commission for Energy Regulation (CER). (2012). CER Smart Metering Project - Gas Customer Behaviour Trial, 2009-2010. [dataset]. 1st Edition. Irish Social Science Data Archive. SN: 0013-00. www.ucd.ie/issda/CER-gas.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hurst, W., Curbelo Montanez, C.A., Al-Jumeily, D. (2019). Age Group Detection in Stochastic Gas Smart Meter Data Using Decision-Tree Learning. In: Huang, DS., Huang, ZK., Hussain, A. (eds) Intelligent Computing Methodologies. ICIC 2019. Lecture Notes in Computer Science(), vol 11645. Springer, Cham. https://doi.org/10.1007/978-3-030-26766-7_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-26766-7_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26765-0
Online ISBN: 978-3-030-26766-7
eBook Packages: Computer ScienceComputer Science (R0)