Abstract
Context recognition (CR) systems infer the user’s context, such as their physical activity, from sensor data obtained, for example, with smartphone sensors. Designing an energy-efficient CR system, however, is a complex optimization problem involving conflicting objectives and several constraints arising from real-world limitations and designers’ preferences. To address this task, we propose a constrained multiobjective formulation of the CR design problem. Unlike most studies in this domain, we use a true multiobjective approach in solving it. Specifically, we apply a multiobjective evolutionary algorithm equipped with two different constraint handling techniques. Their performance is demonstrated in optimizing six CR systems of various complexity. The proposed problem formulation and the optimization results make it possible to better understand the CR systems operation and provide valuable information to the designers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cvetković, B., Janko, V., Romero, A.E., Kafalı, Ö., Stathis, K., Luštrek, M.: Activity recognition for diabetic patients using a smartphone. J. Med. Syst. 40(12), 1–8 (2016). https://doi.org/10.1007/s10916-016-0598-y
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002). https://doi.org/10.1109/4235.996017
Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. NCS. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-44874-8
Garcia, R.d.P., de Lima, B.S.L.P., Lemonge, A.C.d.C., Jacob, B.P.: A rank-based constraint handling technique for engineering design optimization problems solved by genetic algorithms. Comput. Struct. 187, 77–87 (2017). https://doi.org/10.1016/j.compstruc.2017.03.023
Gjoreski, M., et al.: Classical and deep learning methods for recognizing human activities and modes of transportation with smartphone sensors. Inf. Fusion 62, 47–62 (2020). https://doi.org/10.1016/j.inffus.2020.04.004
Janko, V.: Adapting sensor settings for energy-efficient context recognition. Ph.D. thesis, Jožef Stefan International Postgraduate School (2020). https://www.researchgate.net/publication/343230379
Janko, V., Luštrek, M.: Choosing duty-cycle parameters for context recognition. In: 14th International Conference on Intelligent Environments, pp. 83–86. IEEE (2018). https://doi.org/10.1109/IE.2018.00020
Janko, V., Luštrek, M.: Using Markov chains and multi-objective optimization for energy-efficient context recognition. Sensors 18(1), 80 (2018). https://doi.org/10.3390/s18010080
Roggen, D., et al.: Collecting complex activity datasets in highly rich networked sensor environments. In: Seventh International Conference on Networked Sensing Systems (INSS), pp. 233–240. IEEE (2010). https://doi.org/10.1109/INSS.2010.5573462
Sagha, H., et al.: Benchmarking classification techniques using the Opportunity human activity dataset. In: IEEE International Conference on Systems, Man, and Cybernetics, pp. 36–40. IEEE (2011). https://doi.org/10.1109/ICSMC.2011.6083628
Tanabe, R., Oyama, A.: A note on constrained multi-objective optimization benchmark problems. In: IEEE Congress on Evolutionary Computation (CEC), pp. 1127–1134. IEEE (2017). https://doi.org/10.1109/CEC.2017.7969433
Vodopija, A., Oyama, A., Filipič, B.: Ensemble-based constraint handling in multiobjective optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO 2019), pp. 2072–2075. ACM (2019). https://doi.org/10.1145/3319619.3326909
Yürür, Ö., Liu, C.H., Sheng, Z., Leung, V.C., Moreno, W., Leung, K.K.: Context-awareness for mobile sensing: a survey and future directions. IEEE Commun. Surv. Tutor. 18(1), 68–93 (2016). https://doi.org/10.1109/COMST.2014.2381246
Acknowledgment
This work is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation program under Grant Agreement no. 692286. We also acknowledge financial support from the Slovenian Research Agency (young researcher program and research core funding no. P2-0209).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Vodopija, A., Janko, V., Luštrek, M., Filipič, B. (2020). Constrained Multiobjective Optimization for the Design of Energy-Efficient Context Recognition Systems. In: Filipič, B., Minisci, E., Vasile, M. (eds) Bioinspired Optimization Methods and Their Applications. BIOMA 2020. Lecture Notes in Computer Science(), vol 12438. Springer, Cham. https://doi.org/10.1007/978-3-030-63710-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-63710-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63709-5
Online ISBN: 978-3-030-63710-1
eBook Packages: Computer ScienceComputer Science (R0)