Abstract
Recently, smart homes have become the center of Internet of Things (IoT) development. More and more connected devices are now parts of our house. These devices are considered as “smart” devices because they may be able to communicate with each other or with the Internet. However, they are not “smart” enough in a sense of learning. Most of the time, users have to manually interact with the devices to match their living style. This paper proposes a distributed machine learning method to automate the learning process for these devices to avoid making users repeat the manual interaction over and over again. Each device is able to self-learn to detect users’ favorite settings during certain periods and then share this information among other self-learning smart devices to find patterns that may lead to the best combination of their settings that suit the living style of each member of the house. It implements a distributed classifier system that resulted in an algorithm that is small enough to run on lightweight single-board computers.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ricquebourg, V., et al. (2006). The smart home concept: Our immediate future. In 1st IEEE international conference on E-learning in industrial electronics (pp. 23–28).
Harper, R. (2006). Inside the smart home, ISBN 1852338547, 9781852338541. London: Springer.
Rashidi, P., & Cook, D. J. (2009). Keeping the resident in the loop: Adapting the smart home to the user. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, 39(5), 949–959.
Holland, J. H., et al. (2000). What is a learning classifier system? In Learning classifier systems: From foundation to applications, lecture notes in computer science (Vol. 1813, pp. 3–32). Berlin/Heidelberg: Springer.
Tamee, K., Bull, L., & Pinngern, O. (2006). A learning classifier system approach to clustering. In Sixth International Conference on Intelligent Systems Design and Applications (Vol. 1, pp. 621–626). IEEE.
Irvan, M., Yamada, T., & Terano, T. (2013a). Influence of organizational learning for multi-agent simulation based on an adaptive classifier system. IEEJ Transactions on Electronics, Information and Systems, 133(9), 1752–1761.
Irvan, M., Yamada, T., & Terano, T. (2013b). An on-the-fly learning framework for a fluctuating number of agents in a multi-agent system. In Agent-based approaches in economic and social complex systems VII, Agent-based social systems (Vol. 10, pp. 227–242). Tokyo: Springer.
Goldberg, D. E., & Holland, J. H. (1988). Genetic algorithms and machine learning. Machine Learning, 3(2–3), 95–99.
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996). Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4, 237–285.
March, J. G. (1991). Exploration and exploitation in organizational learning. Organization Science, 2(1), 71–87.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Irvan, M., Terano, T. (2017). Distributed Classifier System for Smart Home’s Machine Learning. In: Putro, U., Ichikawa, M., Siallagan, M. (eds) Agent-Based Approaches in Economics and Social Complex Systems IX. Agent-Based Social Systems, vol 15. Springer, Singapore. https://doi.org/10.1007/978-981-10-3662-0_15
Download citation
DOI: https://doi.org/10.1007/978-981-10-3662-0_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3661-3
Online ISBN: 978-981-10-3662-0
eBook Packages: Business and ManagementBusiness and Management (R0)