Abstract
This paper explores a sequential decision making methodology of when to update statistical learning models in Intelligent Edge Computing devices given underlying changes in the contextual data distribution. The proposed model update scheduling takes into consideration the optimal decision time for minimizing the network overhead while preserving the prediction accuracy of the models. The paper reports on a comparison between the proposed approach with four other update delaying policies found in the literature, an evaluation of the performances using linear and support vector regression models over real contextual data streams and a discussion on the strengths and weaknesses of the proposed policy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adu-Manu, K.S., Tapparello, C., Heinzelman, W., Katsriku, F.A., Abdulai, J.D.: Water quality monitoring using wireless sensor networks: current trends and future research directions. ACM Trans. Sen. Netw. 13(1), 4:1–4:41 (2017). https://doi.org/10.1145/3005719
Akkaş, M.A.: Using wireless underground sensor networks for mine and miner safety. Wireless Netw. 24(1), 17–26 (2018). https://doi.org/10.1007/s11276-016-1313-0
Anagnostopoulos, C.: Time-optimized contextual information forwarding in mobile sensor networks. J. Parallel Distrib. Comput. 74(5), 2317–2332 (2014). https://doi.org/10.1016/j.jpdc.2014.01.008
Anagnostopoulos, C.: Quality-optimized predictive analytics. Appl. Intell. 45, (2016). https://doi.org/10.1007/s10489-016-0807-x
Anagnostopoulos, C., Kolomvatsos, K.: A delay-resilient and quality-aware mechanism over incomplete contextual data streams. Inf. Sci. 355–356, 90–109 (2016). https://doi.org/10.1016/j.ins.2016.03.020. http://www.sciencedirect.com/science/article/pii/S0020025516301670
Ferguson, T.S.: Optimal stopping and applications. http://www.math.ucla.edu/~tom/Stopping/sr1.pdf
Granjon, P.: The cusum algorithm: a small review (2013)
Harth, N., Anagnostopoulos, C.: Edge-centric efficient regression analytics (2018). http://eprints.gla.ac.uk/160937/
Huerta, R., Mosqueiro, T., Fonollosa, J., Rulkov, N.F., Rodriguez-Lujan, I.: Online decorrelation of humidity and temperature in chemical sensors for continuous monitoring. Chemom. Intell. Lab. Syst. 157, 169–176 (2016). https://doi.org/10.1016/j.chemolab.2016.07.004. http://www.sciencedirect.com/science/article/pii/S0169743916301666
Liu, Y., Yang, C., Jiang, L., Xie, S., Zhang, Y.: Intelligent edge computing for iot-based energy management in smart cities. IEEE Netw. 33(2), 111–117 (2019). https://doi.org/10.1109/MNET.2019.1800254
Lorden, G.: Procedures for reacting to a change in distribution. Ann. Math. Stat. 42, (1971). https://doi.org/10.1214/aoms/1177693055
Markakis, E.K., Karras, K., Zotos, N., Sideris, A., Moysiadis, T., Corsaro, A., Alexiou, G., Skianis, C., Mastorakis, G., Mavromoustakis, C.X., Pallis, E.: Exegesis: extreme edge resource harvesting for a virtualized fog environment. IEEE Commun. Mag. 55(7), 173–179 (2017). https://doi.org/10.1109/MCOM.2017.1600730
Mavromoustakis, C., Batalla, J., Mastorakis, G., Markakis, E., Pallis, E.: Socially oriented edge computing for energy awareness in iot architectures. IEEE Commun. Mag. 56(7), 139–145 (2018). https://doi.org/10.1109/MCOM.2018.1700600
Moustakides, G.: Optimal stopping times for detecting changes in distributions. Ann. Stat. 14, (1986). https://doi.org/10.1214/aos/1176350164
Page, E.S.: Continuous inspection schemes. Biometrika 41(1–2), 100–115 (1954). https://doi.org/10.1093/biomet/41.1-2.100
Shi, W., Cao, J., Zhang, Q., Li, Y., Xu, L.: Edge computing: vision and challenges. IEEE Internet Things J. 3, 1–1 (2016). https://doi.org/10.1109/JIOT.2016.2579198
Shiryaev, A.: On optimum methods in quickest detection problems. Theory Probab. Appl. 8(1), 22–46 (1963). https://doi.org/10.1137/1108002
Siang Lau, T., Tay, W.P.: Quickest change detection under a nuisance change, pp. 6643–6647 (2018). https://doi.org/10.1109/ICASSP.2018.8462436
Tan, Z., Liu, Y., Zhang, Z.: Performance requirements on energy efficiency in WSNS. 3, (2011). https://doi.org/10.1109/ICCRD.2011.5764269
Tian, H., Yu, M., Wang, W.: Continuum: a platform for cost-aware, low-latency continual learning. In: Proceedings of the ACM Symposium on Cloud Computing—SoCC 18 (2018). https://doi.org/10.1145/3267809.3267817
Wark, T., Hu, W., Corke, P., Hodge, J., Keto, A., Mackey, B., Foley, G., Sikka, P., Bruenig, M.: Springbrook: challenges in developing a long-term, rainforest wireless sensor network. pp. 599 – 604 (2009). https://doi.org/10.1109/ISSNIP.2008.4762055
Acknowledgements
This research is funded by the EU H2020 GNFUV Project RAWFIE–OC2–EXP–SCI (Grant No. 645220), under the EC FIRE+ initiative.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Aleksandrova, E., Anagnotopoulos, C. (2020). Optimised Statistical Model Updates in Distributed Intelligence Environments. In: Mastorakis, G., Mavromoustakis, C., Batalla, J., Pallis, E. (eds) Convergence of Artificial Intelligence and the Internet of Things. Internet of Things. Springer, Cham. https://doi.org/10.1007/978-3-030-44907-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-44907-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44906-3
Online ISBN: 978-3-030-44907-0
eBook Packages: EngineeringEngineering (R0)