Bulanık Mantığın Akıllı Etmenlere Bütünleştirilmesi: Bir SFS Üzerinde Deneyler

Öz

Siber-fiziksel Sistemler (SFS), anlık dış değişikliklerin olduğu fiziksel dünya ile etkileşime giren karmaşık yapıdaki sistemlerdir. Literatürde, yazılım etmenleri bu karmaşık yapıdaki sistemlerin programlanması için bir seçenek olarak kabul edilir ve sahip oldukları özellikleri geliştirmek için bulanık mantık ile birlikte kullanılabilir. Etmen odaklı yaklaşımlar, özellikle Kanı-İstek-Hedef (KİH) mimarisi, çeşitli uygulamalarda kullanılmaktadır. Siber-fiziksel Sistemler alanında özerklik, önalma ve insan benzeri akıl yürütme, bir sistemin zekasını geliştirmek için gereken temel unsurlardır. KİH etmenleri tarafından bu özellikler, sistemlerin karmaşık olduğu SFS de uygulanabilir ve bulanık mantık ile kapasiteleri genişletilebilir. Bu çalışma, SFS'deki kusurlu olabilecek hesaplamaları azaltmak amacıyla bulanık mantığı baz alarak KİH mimarisine bağlı akıllı etmenleri uygular. Önerilen bulanık KİH yaklaşımını değerlendirmek için bir MİB fan sistemi kullanılmıştır. İlk olarak, sıcaklık duyargasının herhangi bir örnekleme gürültüsü olmadan ideal olduğu varsayılarak sistem test edilmiştir. Normal KİH ve bulanık mantık tabanlı KİH ayrı ayrı uygulanarak sonuçlar test edilmiştir. Daha sonra -+ beş hata oranı dikkate alınarak veri örnekleme süreci test edilmiştir. Hem ideal hem de gürültülü veriler için bulanık KİH yaklaşımının önemli bir gelişme gösterdiği sonucuna varılmıştır. Ayrıca, somut bir vaka çalışması da kullanarak Jason KİH için akıl yürütme döngüsü kısıtlamaları denenmiştir.

Anahtar Kelimeler

• Bulanık BDI Etmen
• Ajan-tabanlı CPS
• Fan Kontrol Sistemi
• Akıllı Ajanlar
• Jason Etmen Program Dili

Integrating Fuzzy Logic into Intelligent Agents: Experiments on a CPS

Öz

Cyber-physical Systems (CPS) are complex systems that interact with the physical world where instant external changes exist. In the literature, software agents are considered as an option, and their enhancement with fuzzy logic can also be employed to enhance their abilities. Agent-oriented approaches, particularly Belief-Desire-Intention (BDI) architecture, are used in various applications. In all these domains, autonomy, proactivity, and human-like reasoning are essential aspects to enhance the intelligence of a system. These features can also be applied in CPS, where the systems are complex. This study aims to enhance a CPS using fuzzy logic for intelligent agents so that intelligent decision making can be applied to eliminate inaccurate calculations in the CPS. To evaluate the proposed fuzzy-BDI approach, we used a MİB fan control system. First, the system is tested assuming that the temperature sensor is ideal without any sampling noise. We applied traditional BDI and fuzzy-BDI separately. Then, we tested the data sampling process considering the -+five error rate. We concluded that the fuzzy-BDI approach for both ideal and noisy data showed considerable improvement. Moreover, we experimented the Jason’s reasoning cycle constraints using a concrete case study.

Anahtar Kelimeler

• Fuzzy BDI Agent
• Agent-based CPS
• Fan Control System
• Intelligent Agents
• Jason Agent Program Language

Kaynakça

1. Khan A. R. ve Asghar M. Z., “An intelligent agent for a vacuum cleaner,” International Journal of Digital Content Technology and its Applications, vol. 3, no. 2, pp. 143–146, 2009.
2. Bratman M., “Intention, plans, and practical reason,” Cambridge: Cambridge, MA: Harvard University Press. 1987.
3. Bratman M. E., Israel D. J. ve Pollack M. E., “Plans and resource bounded practical reasoning,” Computational intelligence, vol. 4, no. 3,pp. 349–355, 1988.
4. Rao A. S., Georgeff M. P. ve ark., “Bdi agents: From theory to practice.” in ICMAS, vol. 95, 1995, pp. 312–319.
5. Rao A. S. ve Georgeff M. P., “In Proceedings of the 2nd International Conference on Principles of Knowledge Representation and Reasoning (KR’91)“. Cambridge, MA, USA, April 22-25, 1991. Morgan Kaufmann, 473-484.
6. Lee S., Son Y.-J., ve Jin J., “An integrated human decision making model for evacuation scenarios under a bdi framework,” ACM Transactions on Modeling and Computer Simulation (TOMACS), vol. 20, no. 4, pp. 1–24, 2010.
7. Kacprzak M. ve Kosi´nski W., “Modelling fuzzy beliefs of agents,” Zeszyty Naukowe Politechniki Białostockiej. Informatyka, no. 9, pp. 45–60, 2012.
8. Wu X. ve Zhang J.-L., “Rough set models based on random fuzzy sets and belief function of fuzzy sets,” International Journal of General Systems, vol. 41, no. 2, pp. 123–141, 2012.

9. Jing X. Ve Luo X., “A fuzzy dynamic belief logic.” İn International Conference on Agents and Artificial Intelligence ICAART, Nguyen N. T., eds. ,Barcelona, Spain, 2013, pp. 289–294.
10. Rosales R., Castañón-Puga M., Lara-Rosano F., Evans R. D., Osuna-Millan N. ve Flores-Ortiz M. V., “Modelling the interruption on hci using bdi agents with the fuzzy perceptions approach: An interactive museum case study in Mexico,” Applied Sciences, vol. 7, no. 8, p. 832, 2017.
11. Broujeny R. S., Madani K., Chebira A., Amarger V., ve Hurtard L., “A heating controller designing based on living space heating dynamic’s model approach in a smart building,” Energies, vol. 14, no. 4, p. 998, 2021.
12. Xiaochao W., Ying C., ve Longfei C., “A cgf behavior decision making model based on fuzzy bdi framework,” in 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). IEEE, 2019, pp. 1487–1490, 24-26 May 2019, Chongqing, China.
13. Mekki A. B., Tounsi J., ve Said L. B., “Fuzzy bdi agents for supply chain monitoring in an uncertain environment,” in Supply Chain Forum: An International Journal, vol. 17, no. 2. Taylor & Francis, 2016, pp. 109–123.
14. Tezel B. T., Kardas G. ¸ve Uğur A., “Bulanık mantık tabanlı bdi etmenleri fuzzy logic based bdi agents,” in 1st International Conference on Computer Science and Engineering (UBMK 16), Tekirdağ, Turkey, 20-23 October 2016.
15. Yalcin M. M., Karaduman B., Kardas G. ve Challenger M., “An agent-based cyber-physical production system using lego technology,” in 2021 16th Conference on Computer Science and Information Systems (FedCSIS). IEEE, Sofia, Bulgaria, 02-05 September, 2021.
16. Schoofs E., Kisaakye J., Karaduman B., ve Challenger M., “Software agent-based multi-robot development: A case study,” in 2021 10th Mediterranean Conference on Embedded Computing (MECO), pp. 1–8, Budva, Montenegro, 07-10 June 2021,
17. Tezel B. T. ve Mert A., “A cooperative system for metaheuristic algorithms,” Expert Systems with Applications, vol. 165, p. 113976, 2021.
18. Arslan S., Challenger M. ve Dagdeviren O.. “Wireless sensor network based fire detection system for libraries”. In 2017 International Conference on Computer Science and Engineering (UBMK) 2017, October (pp. 271-276). IEEE.
19. Cakmaz Y. E., Alaca O. F., Durmaz C., Akdal B., Tezel B., Challenger M., ve Kardas G., "Engineering a bdi agent-based semantic e-barter system". In 2017 International Conference on Computer Science and Engineering (UBMK) 2017, October, IEEE (pp. 1072-1077).
20. Bordini R. H., Hubner J. F., ve Wooldridge M., Programming multiagent systems in AgentSpeak using Jason. John Wiley & Sons, 2007, vol. 8.
21. Rao A. S., “Agentspeak (l): Bdi agents speak out in a logical computable language,” in European workshop on modelling autonomous agents in a multi-agent world. Van de Velde, W., Perram, J.W. (eds), Lecture Notes in Computer Science, vol 1038. Springer, Berlin, Heidelberg, 1996, pp. 42–55.
22. Georgeff M. ve Ingrand F., “Decision-making in an embedded reasoning system,” in International Joint Conference on Artificial Intelligence, 1989, Detroit, United States, pp. 972-978.
23. Rao A. S. ve Georgeff M. P., “Decision procedures for bdi logics,” Journal of logic and computation, vol. 8, no. 3, pp. 293–343, 1998.
24. Zadeh L. A., “Fuzzy sets,” in Fuzzy sets, fuzzy logic, and fuzzy systems: selected papers by Lotfi A Zadeh. World Scientific, USA, ISBN 9810224214Ö 1996, vol.6 pp. 394–432.
25. Alcal´a-Fdez J. ve Alonso J. M., “A survey of fuzzy systems software: Taxonomy, current research trends, and prospects,” IEEE Transactions on Fuzzy Systems, vol. 24, no. 1, pp. 40–56, 2015.
26. Arcaini P., Riccobene E. ve Scandurra P., “Modeling and analyzing mape-k feedback loops for self-adaptation,” in 2015 IEEE/ACM 10th International Symposium on Software Engineering for Adaptive and Self-Managing Systems. IEEE, 2015, Florence, Italy, 18-19 May 2015, pp. 13–23.
27. Petrovska A., Neuss M., Gerostathopoulos I. ve Pretschner A., “Runtime reasoning from uncertain observations with subjective logic in multi-agent self-adaptive cyber-physical systems,” in 16th Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS, Madrid, Spain, 18-24 May, 2021.
28. Knobloch L. K., “Uncertainty reduction theory,” The international encyclopedia of interpersonal communication, pp. 1–9, 2015.
29. [Jsang A., Subjective Logic: A Formalism for Reasoning Under Uncertainty, Springer Publishing Company, Incorporated, 2018.
30. Silva, G. R., Hübner, J. F., & Becker, L. B. (2021, May). Active Perception within BDI Agents Reasoning Cycle. In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems pp. 1218-1225.
31. Karaduman B., Tezel B. T. Ve Challenger M,. ”Towards Applying Fuzzy Systems in Intelligent Agent-based CPS: A Case Study”. In 2021 6th International Conference on Computer Science and Engineering (UBMK), September 2021, IEEE, pp. 735-740.
32. Ricci A., Piunti M., Viroli M. ve Omicini A., Environment programming in CArtAgO. In Multi-agent programming, Springer, Boston, MA. 2009, pp. 259-288.
33. Karaduman B., Tezel B. T., ve Challenger M,. Enhancing BDI Agents Using Fuzzy Logic for CPS and IoT Interoperability Using the JaCa Platform. Special Issue on Fuzzy Techniques for Emerging Conditions & Digital Transformation, Symmetry, 14(7), 1447, 2022.
34. Karaduman B., Tezel B. T., ve Challenger M,.. Deployment of Software Agents and Application of Fuzzy Controller on the UWB Localization based Mobile Robots. In: International Conference on Intelligent and Fuzzy Systems. Springer, Cham, 2022. pp. 98-105.