Abstract
This chapter addresses the problem of collaborative Predictive Modelling via in-network processing of contextual information captured in Internet of Things (IoT) environments. In-network predictive modelling allows the computing and sensing devices to disseminate only their local predictive Machine Learning (ML) models instead of their local contextual data. The data center, which can be an Edge Gate- way or the Cloud, aggregates these local ML predictive models to predict future outcomes. Given that communication between devices in IoT environments and a centralised data center is energy consuming and communication bandwidth demanding, the local ML predictive models in our proposed in-network processing are trained using Swarm Intelligence for disseminating only their parameters within the network. We further investigate whether dissemination overhead of local ML predictive models can be reduced by sending only relevant ML models to the data center. This is achieved since each IoT node adopts the Particle Swarm Optimisation algorithm to locally train ML models and then collaboratively with their network neighbours one representative IoT node fuses the local ML models. We provide comprehensive experiments over Random and Small World network models using linear and non-linear regression ML models to demonstrate the impact on the predictive accuracy and the benefit of communication-aware in-network predictive modelling in IoT environments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Cyclic Redundancy Check.
- 2.
Wireless Sensor Network.
References
Anagnostopoulos, C., Hadjiefthymiades, S.: Advanced principal component-based compression schemes for wireless sensor networks. ACM Trans. Sen. Netw. 11(1), 7:1–7:34 (2014). ISSN 1550-4859
Candanedo, L.M., Feldheim, V., Deramaix, D.: Data driven prediction models of energy use of appliances in a low-energy house. Energy Build. 140, 81–97 (2017)
Aric Hagberg, P.S., Dan Schult. Networkx. https://networkx.github.io/ (2014). Cited 29 Oct 2018
Barabási, A.-L.: Network science acknowledgements random networks. Creative Commons (2014)
Beers, B.: What regression measures. Investopedia (2019). Cited 2 Feb 2019
Bhatia, R.: Why do data scientists prefer python over java? Analytics India Magazine (2018). Cited 27 Feb 2019
Candanedo, L.M., Feldheim, V., Deramaix, D.: Data driven prediction models of energy use of appliances in a low-energy house. Energy Build. 140, 81–97 (2017). ISSN 0378-7788. doi:https://doi.org/10.1016/j.enbuild.2017.01.083
Newman, M.E.J., Watts, D., Strogatz, S.H.: Random graph models of social networks. Proc. Natl. Acad. Sci. USA 99(1), 2566–2572 (2002). https://doi.org/10.1073/pnas.012582999
Engelbrecht, A.P.: Particle Swarm Optimization. Wiley (2007)
Harth, N., Anagnostopoulos, C.: Edge-centric efficient regression analytics. http://eprints.gla.ac.uk/160937/. April 2018
M. Incorporated.: Predictive modeling: The only guide you need. https://www.microstrategy.com/us/resources/introductory-guides/predictive-modeling-the-only-guide-you-need (2018). Cited 23 March 2019
Indu, S.D.: Wireless sensor networks: Issues and challenges. Int. J. Comput. Sci. Mob. Comput., 681–685 (20140
Jj and Jj. MAE and RMSE—which metric is better?—human in a machine world—medium. https://medium.com/human-in-a-machine-world/mae-and-rmse-which-metric-is-better-e60ac3bde13d (2016). Cited 1 Oct 2018
Jones, E., Oliphant, T., Peterson, P. et al.: SciPy: Open source scientific tools for Python. http://www.scipy.org/ (2001)
A. Kaveh. Particle Swarm Optimisation, chapter 2. Springer International Publishing, 2014
Keith: The history of social media: Social networking evolution! https://historycooperative.org/the-history-of-social-media/journal=HistoryCooperative (2019). Cited 21 March 2019
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of ICNN’95—International Conference on Neural Networks, vol. 4, pp. 1942–1948 (1995). https://doi.org/10.1109/icnn.1995.488968
Lueth, K.L.: State of the IOT 2018: Number of IOT devices now at 7b—market accelerating. IoT Analytics (2018). Cited 28 Feb 2019
Lv, Y., Tian, Y.: Design and application of sink node for wireless sensor network. In: 2010 2nd International Conference on Industrial and Information Systems, vol. 1, pp. 487–490 (2010)
Math.com: Graphing equations and inequalities—slope and y-intercept—in depth. http://www.math.com/school/subject2/lessons/S2U4L2DP.html (2000–2005). Cited 24 March 2019
Mehl, B.: 6 IOT communication protocols for web connected devices. Kisi. https://www.getkisi.com/blog/internet-of-things-communication-protocols (2018). Cited 1 March 2019
Oliphant, T.: Numpy: A guide to numpy. USA: Trelgol Publishing (2006). Cited 24 March 2019
Özsoy, V.S., Örkcü, H.: Estimating the parameters of nonlinear regression models through particle swarm optimization. Gazi Univ. J. Sci. 29, 187–199 (2016)
Pascual: Understanding regression error metrics. https://www.dataquest.io/blog/understanding-regression-error-metrics/ (2018). Cited 20 Feb 2019
Python, R.: Python plotting with matplotlib (guide)—real python. https://realpython.com/python-matplotlib-guide/ (2018). Cited 11 Oct 2018
Riordan, O., Wormald, N.: The diameter of sparse random graphs. Combinat. Prob. Comput. 19(5–6), 835–926 (2010)
Srivastava, T.: 7 important model evaluation error metrics everyone should know. https://www.analyticsvidhya.com/blog/2016/02/7-important-model-evaluation-error-metrics/ (2017). Cited 24 Nov 2018
Swaminathan, S.: Linear regression—detailed view. https://towardsdatascience.com/linear-regression-detailed-view-ea73175f6e86 (2018). Cited 21 Oct 2018
V. S. Technology: What are mean squared error and root mean squared error? https://www.vernier.com/til/1014/ (2001). Cited 1 Oct 2018
Montoya, S.: How to calculate the Root Mean Square Error (RMSE) of an interpolated pH raster? https://www.hatarilabs.com/ih-en/how-to-calculate-the-root-mean-square-error-rmse-of-an-interpolated-ph-raster (2018). Cited 20 March 2019
T. P. S. University: 15.5—nonlinear regression. https://newonlinecourses.science.psu.edu/stat501/node/370/ (2018). Cited 13 Jan 2019
Wikipedia: Watts-strogatz model https://en.wikipedia.org/wiki/Watts-Strogatz_model (2018). Cited 3 Nov 2018
Wikipedia: Particle swarm optimization https://en.wikipedia.org/wiki/Particle_swarm_optimization (2018). Cited 30 Oct 2018
Wikipedia: Linear regression https://en.wikipedia.org/wiki/Linear_regression (2019). Cited 8 Oct 2018
Wikipedia: Random graph https://en.wikipedia.org/wiki/Random_graph (2019). Cited 19 Jan 2019
Acknowledgements
This research is funded by the EU-H2020 GNFUV Project (#Grant 645220) and the EU-H2020 MSCA INNOVATE Project (#Grant 745829).
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
Ivanov, H., Anagnostopoulos, C., Kolomvatsos, K. (2020). In-Network Machine Learning Predictive Analytics: A Swarm Intelligence Approach. 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_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-44907-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44906-3
Online ISBN: 978-3-030-44907-0
eBook Packages: EngineeringEngineering (R0)