Abstract
With the popularity and affordability of ZigBee wireless sensor technology, IoT-based smart controlling system for home appliances becomes prevalent for smart home applications. From the data analytics point of view, one important objective from analyzing such IoT data is to gain insights from the energy consumption patterns, thereby trying to fine-tune the energy efficiency of the appliance usage. The data analytics usually functions at the back-end crunching over a large archive of big data accumulated over time for learning the overall pattern from the sensor data feeds. The other objective of the analytics, which may often be more crucial, is to predict and identify whether an abnormal consumption event is about to happen. For example, a sudden draw of energy that leads to hot spot in the power grid in a city, or black-out at home. This dynamic prediction is usually done at the operational level, with moving data stream, by data stream mining methods . In this paper, an improved version of very fast decision tree (VFDT) is proposed, which learns from misclassified results for the sake of filtering the noisy data from learning and maintaining sharp classification accuracy of the induced prediction model. Specifically, a new technique called misclassified recall (MR), which is a pre-processing step for self-rectifying misclassified instances, is formulated. In energy data prediction, most misclassified instances are due to data transmission errors or faulty devices. The former case happens intermittently, and the errors from the latter cause may persist for a long time. By caching up the data at the MR pre-processor, the one-pass online model learning can be effectively shielded in case of intermitting problems at the wireless sensor network; likewise the stored data could be investigated afterwards should the problem persist for long. Simulation experiments over a dataset about predicting exceptional appliances energy use in a low energy building are conducted. The reported results validate the efficacy of the new methodology VFDT + MR, in comparison to a collection of popular data stream mining algorithms from the literature.
This is a preview of subscription content, log in via an institution to check access.
Image courtesy by https://github.com/LuisM78/Appliances-energy-prediction-data
Similar content being viewed by others
References
Bottou L, Bousquet O (2008) The tradeoffs of large scale learning. Adv Neural Inf Process Syst 20:161–168
Candanedo LM, Feldheim V, Deramaix D (2017) Data driven prediction models of energy use of appliances in a low-energy house, energy and buildings, vol 140. Springer, New York, pp 81–97
Ceci M, Cassavia N, Corizzo R, Dicosta P, Malerba D, Maria G, Masciari E, Pastura C (2015) Big data techniques for renewable energy market, semanticscholar.org, 2015. https://pdfs.semanticscholar.org/014b/2592b1aec6243d230c689207a47264e730fc.pdf
Ceci M, Corizzo R, Fumarola F, Ianni M, Malerba D, Maria G, Masciari E, Oliverio M, Rashkovska A (2015) Big data techniques for supporting accurate predictions of energy production from renewable sources. In: IDEAS ‘15 proceedings of the 19th international database engineering & applications symposium, pp. 62–71
Cerquitelli T (2017) Predicting large scale fine grain energy consumption. In: 8th international conference on sustainability in energy and buildings, SEB-16, energy procedia 111 (2017), pp. 1079–1088
Choi JH, Shin HS, Nasridinov A (2016) A comparative study on data mining classification techniques for military applications. J Converg 7. https://www.manuscriptlink.com/journals/joc/digitalLibrary/2016/7/0
Darrell S, Indyk (eds). (2005) Nearest-neighbor methods in learning and vision. MIT Press, Cambridge, 0-262-19547-X
Domingos P, Hulten G (2000) Mining high-speed data streams. In: Proceedings KDD 2000, ACM Press, New York, NY, USA, pp. 71–80
Egarter D, Monacchi A, Khatib T, Elmenreich W (2016) Integration of legacy appliances into home energy management systems. J Ambient Intell Hum Comput 7(2):171–185
Finogeev AG, Parygin DS, Finogeev AA (2017) The convergence computing model for big sensor data mining and knowledge discovery. Human Centri Comput Inf Sci 7(11):1–16
Fong S, Hu S, Wei S, Cho K, Wong RK, Mohammed S (2017) On recognizing abnormal human behaviors by data stream mining with misclassified recalls. In: WWW ‘17 proceedings of the 26th international conference on World Wide Web companion, pp. 1129–1135
Ikonomovska E, Gama J, Džeroski S (2010) Learning model trees from evolving data streams. Data Min Knowl Discov 23(1):128–168
Ikonomovska E, Gama J, Zenko B Džeroski S (2011) Speeding-up hoeffding-based regression trees with options. ICML 2011:537–544
Kang WM, Moon SY, Park JH (2017) An enhanced security framework for home appliances in smart home. Hum Centric Comput Inf Sci 7(6):1–12
Lachut D, Banerjee N, Rollins S, (2014) Predictability of energy use in homes. In: 2014 international green computing conference (IGCC), 3–5 Nov. 2014, pp. 1–10
Maity S, Park JH (2016) Powering IoT devices: a novel design and analysis technique. J Converg 7:1–18 (Article ID 16071001)
Martin EG, Lavesson N, Grahn H (2015) Energy efficiency in data stream mining. In: 2015 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM), 25–28 Aug. 2015, Paris, France, pp. 1125–1132
Mocanu E, Nguyen PH, Gibescu M, Kling WL (2014) Comparison of machine learning methods for estimating energy consumption in buildings. In: 2014 international conference on probabilistic methods applied to power systems (PMAPS), 7–10 July 2014, pp. 1–6
Pughat A, Sharma V (2015) A review on stochastic approach for dynamic power management in wireless sensor networks. Human Centric Comput Inf Sci 4:1–14
Parra J Jr, Kiekintveld C (2013) Initial exploration of machine learning to predict customer demand in an energy market simulation, trading agent design and analysis: papers from the AAAI 2013 workshop, pp 29–32
Perera KS, Aung Z, Woon WL (2014) Machine learning techniques for supporting renewable energy generation and integration: a survey. In: DARE'14 Proceedings of the second international conference on data analytics for renewable energy integration, Nancy, France. Springer, Switzerland, pp 81–96. https://doi.org/10.1007/978-3-319-13290-7_7
Quinlan R (1993) C4.5: programs for machine learning. Morgan Kaufmann Publishers, San Mateo
Russell S, Norvig P (2003) [1995] Artificial intelligence: a modern approach (2nd edn). Prentice Hall, New Jersey, 978-0137903955
Settles B (2010) Active learning literature survey, computer sciences technical report 1648. University of Wisconsin–Madison, retrieved 2014-11-18
Shcherbakov MV, Brebels A, Shcherbakova NL, Kamaev VA, Gerget OM, Devyatykh D (2016) Outlier detection and classification in sensor data streams for proactive decision support systems. J Phys Conf Ser 803(Number 1):1–10
Song T-W, Yang C-S (2008) A connectivity improving mechanism for zigbee wireless sensor networks. In: IEEE/IFIP international conference on embedded and ubiquitous computing, 2008. EUC ‘08. 17–20 Dec. 2008, pp. 495–500
Verma P, Sood SK, Kalra S (2017) Cloud-centric IoT based student healthcare monitoring framework, J Ambient Intell Hum Comput. https://doi.org/10.1007/s12652-017-0520-6 (Springer)
Wang D, Fong S, Wong RK, Mohammed S, Fiaidhi F, Wong KKL (2017) Robust high-dimensional bioinformatics data streams mining by ODR-ioVFDT. Sci Rep 7:43167. https://doi.org/10.1038/srep43167
Yang H, Fong S (2013) Countering the concept-drift problem in big data using iOVFDT. In: Proceedings of the 2013 IEEE international congress BIGDATACONGRESS’13, June 27–July 02, 2013, pp. 126–132
Author information
Authors and Affiliations
Corresponding author
Appendix
Rights and permissions
About this article
Cite this article
Fong, S., Li, J., Song, W. et al. Predicting unusual energy consumption events from smart home sensor network by data stream mining with misclassified recall. J Ambient Intell Human Comput 9, 1197–1221 (2018). https://doi.org/10.1007/s12652-018-0685-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-018-0685-7