Improvised methods for tackling big data stream mining challenges: case study of human activity recognition
- 699 Downloads
Big data stream is a new hype but a practical computational challenge founded on data streams that are prevalent in applications nowadays. It is quite well known that data streams that are originated and collected from monitoring sensors accumulate continuously to a very huge amount making traditional batch-based model induction algorithms infeasible for real-time data mining or just-in-time data analytics. In this position paper, following a new data stream mining methodology, namely stream-based holistic analytics and reasoning in parallel (SHARP), a list of data analytic challenges as well as improvised methods are looked into. In particular, two types of decision tree algorithms, batch-mode and incremental-mode, are put under test at sensor data that represents a typical big data stream. We investigate whether and to what extent of two improvised methods—outlier removal and balancing imbalanced class distributions—affect the prediction performance in big data stream mining. SHARP is founded on incremental learning which does not require all the training to be loaded into the memory. This important fundamental concept needs to be supported not only by the decision tree algorithms, but by the other improvised methods usually at the preprocessing stage as well. This paper sheds some light into this area which is often overlooked by data analysts when it comes to big data stream mining.
KeywordsData stream mining Big data Very fast decision tree Resampling Sensor data
The authors are thankful for the financial support from the research grant “Temporal Data Stream Mining by Using Incrementally Optimized Very Fast Decision Forest (iOVFDF)”, Grant No. MYRG2015-00128-FST, offered by the University of Macau, FST, and RDAO.
- 1.Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
- 5.Murdopo A (2013) Distributed decision tree learning for mining big data streams. Master of Science Thesis. European Master in Distributed ComputingGoogle Scholar
- 6.Fong S, Zhuang Y, Wong R, Mohammed S (2014) A Scalable data stream mining methodology: stream-based holistic analytics and reasoning in parallel. In: Proceedings of the 2nd International symposium on computational and business intelligence, New Delhi, 7–8 Dec 2014, pp 110–115Google Scholar
- 7.Bifet A, Holmes G, Kirkby R, Pfahringer B (2010) MOA: massive online analysis. J Mach Learn Res 99:1601–1604Google Scholar
- 10.Katakis I, Tsoumakas G, Vlahavas I (2005) On the utility of incremental feature selection for the classification of textual data streams. In: PCI 2005, LNCS 3746. Springer, pp 338–348Google Scholar
- 11.Fong S, Liang J, Wong R, Ghanavati M (2014) A novel feature selection by clustering coefficients of variations. In: Proceedings of the 9th International conference on digital information management (ICDIM), Phitsanulok, 29 Sept–1 Oct 2014, pp 205–213Google Scholar
- 13.Brest J, Boskovic B, Zamuda A, Fister I, Mezura-Montes E (2013) Real parameter single objective optimization using self-adaptive differential evolution algorithm with more strategies. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC), Cancun, 20–23 June 2013, pp 377–383Google Scholar
- 14.Ryoo MS, Aggarwal JK (2011) Stochastic representation and recognition of high-level group activities. Int J Comput Vis (IJCV) 93(2):183–200Google Scholar
- 18.Li J, Fong S, Mohammed S, Fiaidhi J (2015) Improving the classification performance of biological imbalanced datasets by swarm optimization algorithms. J Supercomput, Springer, pp 1–21Google Scholar
- 19.Fong S, Wong R, Vasilakos A (2015) Accelerated PSO swarm search feature selection for data stream mining big data. IEEE Trans Serv Comput 99:1–12. doi: 10.1109/TSC.2015.2439695
- 20.Fong S, Zhuang Y, Tang R, Yang X-S, Deb S (2013) Selecting optimal feature set in high-dimensional data by swarm search. J Appl Math 2013:18. doi: 10.1155/2013/590614 (Article ID 590614)