Home / Pre-Press / JST-3777-2022


Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy Logic Hopfield Neural Network

Farah Liyana Azizan, Saratha Sathasivam and Majid Khan Majahar Ali

Pertanika Journal of Science & Technology, Pre-Press

DOI: https://doi.org/10.47836/pjst.31.4.06

Keywords: 3SAT, alpha-cut, defuzzification, fuzzification, fuzzy logic, Hopfield network

Published: 2023-05-24

This study presents a new way of increasing 3SAT logic programming’s efficiency in the Hopfield network. A new model of merging fuzzy logic with 3SAT in the Hopfield network is presented called HNN-3SATFuzzy. The hybridised dynamic model can avoid locally minimal solutions and lessen the computing burden by utilising fuzzification and defuzzification techniques in fuzzy logic. In addressing the 3SAT issue, the proposed hybrid approach can select neuron states between zero and one. Aside from that, unsatisfied neuron clauses will be changed using the alpha-cut method as a defuzzifier step until the correct neuron state is determined. The defuzzification process is a mapping stage that converts a fuzzy value into a crisp output. The corrected neuron state using alpha-cut in the defuzzification stage is either sharpening up to one or sharpening down to zero. A simulated data collection was utilised to evaluate the hybrid techniques’ performance. In the training phase, the network for HNN-3SATFuzzy was weighed using RMSE, SSE, MAE and MAPE metrics. The energy analysis also considers the ratio of global minima and processing period to assess its robustness. The findings are significant because this model considerably impacts Hopfield networks’ capacity to handle 3SAT problems with less complexity and speed. The new information and ideas will aid in developing innovative ways to gather knowledge for future research in logic programming. Furthermore, the breakthrough in dynamic learning is considered a significant step forward in neuro-symbolic integration.

  • Abdullah, W. A. T. W. (1992). Logic programming on a neural network. International Journal of Intelligent Systems, 7(6), 513-519. https://doi.org/10.1002/int.4550070604

  • Abdullah, W. A. T. W. (1993). The logic of neural networks. Physics Letters A, 176(3-4), 202-206. https://doi.org/10.1016/0375-9601(93)91035-4

  • Alzaeemi, S. A., & Sathasivam, S. (2021). Examining the forecasting movement of palm oil price using RBFNN-2SATRA metaheuristic algorithms for logic mining. IEEE Access, 9, 22542-22557. https://doi.org/10.1109/ACCESS.2021.3054816

  • Alzaeemi, S. A., Sathasivam, S., & Velavan, M. (2021). Agent-based modeling in doing logic programming in fuzzy hopfield neural network. International Journal of Modern Education and Computer Science, 13(2), 23-32. https://doi.org/10.5815/IJMECS.2021.02.03

  • Badawi, M. B., Awad, T. H., & Fahham, I. M. E. (2022). Application of artificial intelligence for the prediction of plain journal bearings performance. Alexandria Engineering Journal, 61(11), 9011-9029. https://doi.org/10.1016/j.aej.2022.02.041

  • Bilal, M., Masud, S., & Athar, S. (2012). FPGA design for statistics-inspired approximate sum-of-squared-error computation in multimedia applications. IEEE Transactions on Circuits and Systems II: Express Briefs, 59(8), 506-510. https://doi.org/10.1109/TCSII.2012.2204841

  • Bodjanova, S. (2002). A generalized α-cut. Fuzzy Sets and Systems, 126(2), 157-176. https://doi.org/10.1016/S0165-0114(01)00062-8

  • Brys, T., Hauwere, Y. M. D., Cock, M. D., & Nowé, A. (2012, August 6-8). Solving satisfiability in fuzzy logics with evolution strategies. [Paper presentation]. 2012 Annual Meeting of the North American Fuzzy Information Processing Society (NAFIPS), Berkeley, California. https://doi.org/10.1109/NAFIPS.2012.6290998

  • Fung, C. H., Wong, M. S., & Chan, P. W. (2019). Spatio-temporal data fusion for satellite images using hopfield neural network. Remote Sensing, 11(18), Article 2077. https://doi.org/10.3390/rs11182077

  • Garcez, A. S. A., & Zaverucha, G. (1999). Connectionist inductive learning and logic programming system. Applied Intelligence, 11(1), 59-77. https://doi.org/10.1023/A:1008328630915

  • Halaby, M. E., & Abdalla, A. (2016, May 9-11). Fuzzy maximum satisfiability. [Paper presentation]. INFOS ‘16: The 10th International Conference on Informatics and Systems, Giza, Egypt. https://doi.org/10.1145/2908446.2908476

  • Kubat, M. (1999). Neural networks: A comprehensive foundation by Simon Haykin, Macmillan, 1994, ISBN 0-02-352781-7. The Knowledge Engineering Review, 13(4), 409-412. https://doi.org/10.1017/s0269888998214044

  • Hopfield, J. J., & Tank, D. W. (1985). “Neural” computation of decisions in optimization problems. Biological Cybernetics, 52(3), 141-152. https://doi.org/10.1007/BF00339943

  • Kho, L. C., Kasihmuddin, M. S. M., Mansor, M. A., & Sathasivam, S. (2020). Logic mining in league of legends. Pertanika Journal of Science and Technology, 28(1), 211-225.

  • Kowalski, R., & Sergot, M. (1986). A logic-based calculus of events. New Generation Computing, 4(1), 67-95. https://doi.org/10.1007/BF03037383

  • Lee, C. C., & Gyvez, J. P. (1996). Color image processing in a cellular neural-network environment. IEEE Transactions on Neural Networks, 7(5), 1086-1098. https://doi.org/10.1109/72.536306

  • Little, W. A. (1974). The existence of persistent states in the brain. Mathematical Biosciences, 19(1-2), 101-120. https://doi.org/10.1016/0025-5564(74)90031-5

  • Maandag, P. (2012). Solving 3-SAT [Bachelor dissertation]. Radboud University Nijmegen, Netherlands. https://www.cs.ru.nl/bachelors-theses/2012/Peter_Maandag___3047121___Solving_3-Sat.pdf

  • Mansor, M. A., & Sathasivam, S. (2021). Optimal performance evaluation metrics for satisfiability logic representation in discrete hopfield neural network. International Journal of Mathematics and Computer Science, 16(3), 963-976.

  • Mansor, M. A., Sathasivam, S., & Kasihmuddin, M. S. M. (2018). 3-satisfiability logic programming approach for cardiovascular diseases diagnosis. AIP Conference Proceedings, 1974(1), Article 020022. https://doi.org/10.1063/1.5041553

  • De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38-48. https://doi.org/10.1016/j.neucom.2015.12.114

  • Nasir, M., Sadollah, A., Grzegorzewski, P., Yoon, J. H., & Geem, Z. W. (2021). Harmony search algorithm and fuzzy logic theory: An extensive review from theory to applications. Mathematics, 9(21), 1-46. https://doi.org/10.3390/math9212665

  • Novák, V., Perfilieva, I., & Močkoř, J. (1999). Mathematical principles of fuzzy logic. Springer. https://doi.org/10.1007/978-1-4615-5217-8

  • Pan, J., Pottimurthy, Y., Wang, D., Hwang, S., Patil, S., & Fan, L. S. (2020). Recurrent neural network based detection of faults caused byparticle attrition in chemical looping systems. Powder Technology, 367, 266-276. https://doi.org/10.1016/j.powtec.2020.03.038

  • Pourabdollah, A., Mendel, J. M., & John, R. I. (2020). Alpha-cut representation used for defuzzification in rule-based systems. Fuzzy Sets and Systems, 399, 110-132. https://doi.org/10.1016/j.fss.2020.05.008

  • Rhodes, P. C., & Menani, S. M. (1992). Towards a fuzzy-logic programming system: A 1st-order fuzzy logic. Knowledge-Based Systems, 5(2), 106-116. https://doi.org/10.1016/0950-7051(92)90001-V

  • Sathasivam, S. (2006). Logic mining in neural networks. [Unpublished Doctoral Dissertation] Universiti Malaya, Malaysia.

  • Sathasivam, S. (2010). Upgrading logic programming in hopfield network. Sains Malaysiana, 39(1), 115-118.

  • Sathasivam, S., & Abdullah, W. A. T. W. (2008). Logic learning in hopfield networks. Modern Applied Science, 2(3), 57-63. https://doi.org/10.5539/mas.v2n3p57

  • Sathasivam, S., Mamat, M., Kasihmuddin, M. S. M., & Mansor, M. A. (2020). Metaheuristics approach for maximum k satisfiability in restricted neural symbolic integration. Pertanika Journal of Science and Technology, 28(2), 545-564.

  • Velavan, M., Yahya, R. Z., Halif, M. N. A., & Sathasivam, S. (2015). Mean field theory in doing logic programming using hopfield network. Modern Applied Science, 10(1), 154-160. https://doi.org/10.5539/mas.v10n1p154

  • Wang, L. X. (1996). A course in fuzzy systems and control. Prentice-Hall Inc.

  • Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79-82. https://doi.org/10.3354/cr030079

  • Zadeh, L. A. (1973). Outline of a new approach to the analysis of complex systems and decision processes. IEEE Transactions on Systems, Man and Cybernetics, SMC-3(1), 28-44. https://doi.org/10.1109/TSMC.1973.5408575

  • Zadeh, L. A. (1974). The concept of a linguistic variable and its application to approximate reasoning. In K. S. Fu & J. T. Tou (Eds.), Learning Systems and Intelligent Robots (pp. 1-10). Springer. https://doi.org/10.1007/978-1-4684-2106-4_1

  • Zadeh, L. A. (1979). A theory of approximation reasoning. In J. E. Hayes, D. Mishie & L. I. Mikulish (Eds.), Machine Intelligence (pp. 149-194). Elservier.

  • Zamri, N. E., Alway, A., Mansor, M. A., Kasihmuddin, M. S. M., & Sathasivam, S. (2020). Modified imperialistic competitive algorithm in hopfield neural network for boolean three satisfiability logic mining. Pertanika Journal of Science and Technology, 28(3), 983-1008.

ISSN 0128-7702

e-ISSN 2231-8534

Article ID


Download Full Article PDF

Share this article

Related Articles