A Heterogeneous Fault-Resilient Architecture for Mining Anomalous Activity Patterns in Smart Homes
We are presenting a massively parallel heterogeneous cloud-based architecture oriented towards anomalous activity detection in smart homes. The architecture has very high resilience to both hardware and software faults, it is capable of collecting activity from various data sources and performing anomaly detection in real-time. We corroborate the approach with an efficient checkpointing mechanism for data processing which allows the implementation of hybrid (CPU/GPU) fault-resilience and anomaly detection through pattern mining techniques, at the same time offering high throughput.
KeywordsAnomaly detection Pattern mining Smart home Fault resiliency Heterogeneous architecture Graphics processing unit
This work was partially supported by the Romanian national grant PN-II-ID-PCE-2011-3-0260 (AMICAS).
- 1.Lee, J.V., Chuah, Y.D., Chai, C.T.: A multilevel home security system (MHSS). Int. J. Smart Home 7(2), p49 (2013)Google Scholar
- 2.Chairmadurai, K., Manikannan, K.: Integrated Health care system on pervasive computing. Int. J. Innovative Res. Sci. Eng. Technol. 3(1) (2014)Google Scholar
- 4.Jung, J., Ha, K., Lee, J., Kim, Y., Kim, D.: Wireless body area network in a ubiquitous healthcare system for physiological signal monitoring and health consulting. Int. J. Signal Process. Image Process. Pattern Recogn. 1(1), 47–54 (2008)Google Scholar
- 6.Lim, S., Oh, T.H., Choi, Y.B., Lakshman, T.: Security issues on wireless body area network for remote healthcare monitoring. In: Proceedings of the 2010 IEEE International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing, pp. 327–332. IEEE Computer Society (2010)Google Scholar
- 7.Pungila, C., Negru, V.: A highly-efficient memory-compression approach for GPU-accelerated virus signature matching. In: Gollmann, D., Freiling, F.C. (eds.) ISC 2012. LNCS, vol. 7483, pp. 354–369. Springer, Heidelberg (2012)Google Scholar
- 8.Ziv, J., Lempel, A.: Compression of individual sequences via variable-rate coding. IEEE Trans. Inform. Theor. 24 (1978)Google Scholar
- 10.Riak. http://basho.com/riak/
- 11.Cook, D.J., Schmitter-Edgecombe, M.: Assessing the quality of activities in a smart environment. Methods Inf. Med. 48(5), 480–485 (2009). doi: 10.3414/ME0592
- 12.Pungila, C., Reja, M., Negru, V.: Efficient parallel automata construction for hybrid resource-impelled data-matching. Future Gener. Comput. Syst. 36, 31–41 (2014) Special Section: Intelligent Big Data Processing 2014. doi: 10.1016/j.future.2013.09.008
- 13.The CASAS project. http://ailab.wsu.edu/casas/datasets/