IoT Resource Classification: Fuzzy Rules Automation in Client Preference Selection
Abstract
In the Internet of Things, there is a large number of interconnected sensing and/or actuating resources, and each of these resources can offer different services. Specifying client preferences as to the relevance of QoS attributes associated with resources is often accompanied by uncertainty. In this sense, Fuzzy Logic is opportune to deal with uncertain data. As part of the Fuzzy approach, it is necessary to use rules, whose specification can gain complexity when the number of attributes to be considered increases. From this motivation comes the objective of this work, which is the conception of a proposal for automation of Fuzzy rules, called IoT-DFR3. Among its main features, we highlight: (i) dynamic generation of Fuzzy rules; (ii) selection of client preferences; (iii) resource classification using Interval Type-2 Fuzzy Logic. The results obtained with the classification of resources applying client preferences and the automatic generation of fuzzy rules are presented.
References
Cabrera, N. (2014). Aplicação da Extensão de Zadeh para Conjuntos Fuzzy Tipo 2 Intervalar. PhD thesis, Universidade Federal de Uberlândia.
Dilli, R., Argou, A., Pernas, A., Reiser, R., and Yamin, A. (2018). EXEHDA-RR: Uma proposta para tratar incertezas e otimizar o processo de classificação de recursos na IoT. Simpósio Brasileiro de Computação Ubíqua - CSBC.
Ezenwoke, A. (2018). Fuzzy Hybrid Approach for Ranking and Selecting Services in Cloud-based Marketplaces. Journal of Artificial Intelligence, 11(1):9–17.
Khutade, P. A. and Phalnikar, R. (2014). QoS Aware Web Service Selection and Ranking Framework Based on Ontology. International Journal of Soft Computing and Engineering (IJSCE), 4(3):77–81.
Kumar, R. R., Mishra, S., and Kumar, C. (2017). Prioritizing the solution of cloud service selection using integrated MCDM methods under Fuzzy environment. Journal of Supercomputing, 73(11):4652–4682.
Mutlu, B., Sezer, E. A., and Akcayol, M. A. (2018). Automatic rule generation of fuzzy systems: A comparative assessment on software defect prediction. In 2018 3rd International Conference on Computer Science and Engineering (UBMK), pages 209–214. IEEE.
Santos, M. and Mendoza, B. (2018). Identificación borrosa de un cultivo experimental. In XXXIX Jornadas de Automática, pages 888–893. Área de Ingeniería de Sistemas y Automática, Universidad de Extremadura.
Schenfeld, M. C., Amaral, L., de Matos, E., and Hessel, F. (2016). Arquitetura para fog computing em sistemas de middleware para internet das coisas. In Anais do XLIII Seminário Integrado de Software e Hardware, pages 199–209, Porto Alegre, RS, Brasil. SBC.
Sclafani, P. (2021). Top 10 IoT Trends for 2022.
Tripathy, A. K. and Tripathy, P. K. (2018). Fuzzy QoS requirement-aware dynamic service discovery and adaptation. Applied Soft Computing Journal, 68(November):136–146.
Wang, L. X. and Mendel, J. M. (1992). Generating Fuzzy Rules by Learning from Examples. IEEE Transactions on Systems, Man and Cybernetics.
Xu, Z. and Yager, R. R. (2006). Some geometric aggregation operators based on intuitionistic fuzzy sets. International Journal of General Systems, 35(4):417–433.
