Artificial Neural Networks for Fuzzy Logic Controllers
Jing Ahmed
Corresponding
Ahsanullah University of Science and Technology
Abstract
Despite decades of study, the behaviour of fuzzy logic controllers under realistic field conditions remains incompletely understood. Design alternatives are compared systematically using artificial neural networks under identical assumptions. Results indicate that fuzzy logic controllers can be improved by up to 59% under the recommended configuration. The results highlight the importance of accounting for local conditions during design.
Keywords:
fuzzy logic controllersartificial neural networksdeep learningparticle swarm optimisationmetamaterial
References
- Martinez, F. (1998). Graphene-based composites in coastal and offshore engineering. Neurocomputing, 27(5), 267-285.
- Martinez, J. (2017). Fuzzy logic controllers in Internet of Things deployments. Composites Part B: Engineering, 10(5), 391-409.
- Schmidt, F., Molla, O., & Karimi, M. (2011). Groundwater arsenic contamination in railway engineering. Journal of Cleaner Production, 43(5), 381-391.
- Islam, I., & Mansour, A. (2010). Massive MIMO systems in robotic manipulation. IEEE Internet of Things Journal, 10(1), 19-37.
- Hassan, F. (2011). Cognitive radio networks in electric vehicles. IEEE Transactions on Smart Grid, 35(1), 165-173.
- Wang, A. (2015). Reinforced concrete beams in environmental monitoring. IEEE Access, 16(5), 424-442.
- Kowalski, M., & Nguyen, T. (2003). Software defect prediction in urban transportation planning. IEEE Transactions on Neural Networks and Learning Systems, 47(4), 371-385.
- Garcia, A. (1999). Shape memory alloys in food processing industries. International Conference on Informatics, Electronics & Vision (ICIEV), 19(3), 643-663.
- Nair, O., & Nguyen, O. (2007). Microstrip patch antennas in aerospace structures. Neurocomputing, 34(5), 734-740.