Efficiency analysis of the rule-based defuzzification approach to fuzzy inference system for regression problems

Resmiye Nasiboglu; Efendi Nasibov

Kybernetika (2025)

  • Issue: 1, page 109-132
  • ISSN: 0023-5954

Abstract

top
A fuzzy inference system (FIS) is an effective prediction method based on fuzzy logic. The performance of this model may vary depending on the defuzzification process. In the Mamdani-type FIS model, the defuzzification process is applied to the fuzzy output of the system only once at the last stage. In the FIS with rule-based defuzzification (FIS-RBD) model, the defuzzification process is applied to the fuzzy consequent part of each rule and the overall result of the system is calculated as the weighted average of the separately defuzzified results of the rules. Note that, the original shapes of the combined rule results are lost in the aggregated fuzzy result of the classical Mamdani-type system and the effect of each rule on the system result decreases when aggregated. However, rule results can affect the overall result more significantly in the FIS-RBD approach. In this study, a comparative analysis was made on the effectiveness of the classical Mamdani-type FIS and FIS-RBD models for regression problems. Five datasets from different domains and various defuzzification methods were used in comparisons. In the results obtained, it was observed that the The FIS-RBD model gave better results than the classical Mamdani-type FIS model. To carry out calculation experiments, a new Python package called Fuzlab was developed by modifying the existing Python library called FuzzyLab. In addition to creating the FIS-RBD model, the developed package also allows the use of the Weighted Average Based on Levels (WABL) defuzzification method in fuzzy logic-based calculations.

How to cite

top

Nasiboglu, Resmiye, and Nasibov, Efendi. "Efficiency analysis of the rule-based defuzzification approach to fuzzy inference system for regression problems." Kybernetika (2025): 109-132. <http://eudml.org/doc/299934>.

@article{Nasiboglu2025,
abstract = {A fuzzy inference system (FIS) is an effective prediction method based on fuzzy logic. The performance of this model may vary depending on the defuzzification process. In the Mamdani-type FIS model, the defuzzification process is applied to the fuzzy output of the system only once at the last stage. In the FIS with rule-based defuzzification (FIS-RBD) model, the defuzzification process is applied to the fuzzy consequent part of each rule and the overall result of the system is calculated as the weighted average of the separately defuzzified results of the rules. Note that, the original shapes of the combined rule results are lost in the aggregated fuzzy result of the classical Mamdani-type system and the effect of each rule on the system result decreases when aggregated. However, rule results can affect the overall result more significantly in the FIS-RBD approach. In this study, a comparative analysis was made on the effectiveness of the classical Mamdani-type FIS and FIS-RBD models for regression problems. Five datasets from different domains and various defuzzification methods were used in comparisons. In the results obtained, it was observed that the The FIS-RBD model gave better results than the classical Mamdani-type FIS model. To carry out calculation experiments, a new Python package called Fuzlab was developed by modifying the existing Python library called FuzzyLab. In addition to creating the FIS-RBD model, the developed package also allows the use of the Weighted Average Based on Levels (WABL) defuzzification method in fuzzy logic-based calculations.},
author = {Nasiboglu, Resmiye, Nasibov, Efendi},
journal = {Kybernetika},
keywords = {fuzzy inference system (FIS); defuzzification; rule-based defuzzification (RBD); regression; Python library},
language = {eng},
number = {1},
pages = {109-132},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Efficiency analysis of the rule-based defuzzification approach to fuzzy inference system for regression problems},
url = {http://eudml.org/doc/299934},
year = {2025},
}

TY - JOUR
AU - Nasiboglu, Resmiye
AU - Nasibov, Efendi
TI - Efficiency analysis of the rule-based defuzzification approach to fuzzy inference system for regression problems
JO - Kybernetika
PY - 2025
PB - Institute of Information Theory and Automation AS CR
IS - 1
SP - 109
EP - 132
AB - A fuzzy inference system (FIS) is an effective prediction method based on fuzzy logic. The performance of this model may vary depending on the defuzzification process. In the Mamdani-type FIS model, the defuzzification process is applied to the fuzzy output of the system only once at the last stage. In the FIS with rule-based defuzzification (FIS-RBD) model, the defuzzification process is applied to the fuzzy consequent part of each rule and the overall result of the system is calculated as the weighted average of the separately defuzzified results of the rules. Note that, the original shapes of the combined rule results are lost in the aggregated fuzzy result of the classical Mamdani-type system and the effect of each rule on the system result decreases when aggregated. However, rule results can affect the overall result more significantly in the FIS-RBD approach. In this study, a comparative analysis was made on the effectiveness of the classical Mamdani-type FIS and FIS-RBD models for regression problems. Five datasets from different domains and various defuzzification methods were used in comparisons. In the results obtained, it was observed that the The FIS-RBD model gave better results than the classical Mamdani-type FIS model. To carry out calculation experiments, a new Python package called Fuzlab was developed by modifying the existing Python library called FuzzyLab. In addition to creating the FIS-RBD model, the developed package also allows the use of the Weighted Average Based on Levels (WABL) defuzzification method in fuzzy logic-based calculations.
LA - eng
KW - fuzzy inference system (FIS); defuzzification; rule-based defuzzification (RBD); regression; Python library
UR - http://eudml.org/doc/299934
ER -

References

top
  1. Aggarwal, A., Chakradar, M., Bhatia, M. S., Kumar, M., Stephan, T., Gupta, S. K., Alsamhi, H. S., AL-Dois, H., , J. Healthcare Engrg. (2022), Article ID 4096950. DOI
  2. Amrahov, S. E., Ar, Y., Tugrul, B., Akay, B. E., Kartli, N., , Future Generation Computer Systems 157 (2024), 330-343. DOI
  3. Ansarifar, J., Wang, L., Archontoulis, S. V., , Scientific Reports 11 (2021), Article ID 17754. DOI
  4. Ao, Y., Li, H., Zhu, L., Ali, S., Yang, Z., , J. Petroleum Sci. Engrg. 174 (2019), 776-789. DOI
  5. Ar, Y., Amrahov, S. E., Gasilov, N. A., Yigit-Sert, S., , Kybernetika 58 (2022), 3, 440-455. DOI
  6. Avelar, E., Castillo, O., Soria, J., , J. Automat. Mobile Robotics Intell. Systems 14 (2019), 1, 48-54. DOI
  7. Avelar, E., FuzzyLab. 
  8. Bas, E., Egrioglu, E., , Inform. Sci. 592 (2022), 206-214. DOI
  9. Bas, E., , Inform. Sci. 613 (2022), 419-434. DOI
  10. Bejines, C., , Kybernetika 59 (2023), 5, 752-767. MR4681021DOI
  11. Chakraverty, S., Sahoo, D. M., Mahato, N. R., , In: Concepts of Soft Computing, Springer, Singapore 2019. DOI
  12. Charizanos, G., Demirhan, H., İçen, D., , Inform. Sci. 655 (2024), 119893. DOI
  13. Cruz-Suárez, H., Montes-de-Oca, R., Ortega-Gutiérrez, R. I., , Kybernetika 59 (2023), 1, 160-178. MR4567846DOI
  14. Ding, W., Wang, J., Huang, J., Cheng, C., Jiang, S., , Inform. Sci. 687 (2025), 121376. DOI
  15. Doz, D., Cotič, M., Felda, D., , Mathematics 11 (2023), 19, 4129. DOI
  16. Fiskin, R., Atik, O., Kisi, H., Nasibov, E., Johansen, T. A., , Ocean Engrg. 220 (2021), 108502. DOI
  17. Gao, K., Xu, L., , Expert Syst. Appl. 237 (2024), 121532. DOI
  18. Gao, T., Liu, J., , J. Intell. Fuzzy Syst. 40 (2021), 2, 2041-2053. DOI
  19. Gasilov, N. A., Amrahov, S. E., Fatullayev, A. G., , Int. J. Thermal Sci. 103 (2016), 67-76. DOI
  20. Gasilov, N., Doğan, M., Arici, V., , IETE J. Res. 57 (2011), 3, 278-285. DOI
  21. Gilda, K. S., Satarkar, S. L., Analytical overview of defuzzification methods., Int. J. Advance Res. Ideas Innova. Technol. 6 (2020), 2, 359-365. 
  22. Gu, X., Angelov, P. P., Shen, Q., 10.1109/TFUZZ.2024.3349637, IEEE Trans. Fuzzy Systems 32 (2024), 4, 2318-2330. DOI10.1109/TFUZZ.2024.3349637
  23. Guan, X., Yu, F., Xu, H., Li, C., Guan, Y., Flood risk assessment of urban metro system using random forest algorithm and triangular fuzzy number based analytical hierarchy process approach., Sustainable Cities Soc. 109 (2024), 105546. 
  24. Jang, J. S. R., Sun, C. T., Mizutani, E., Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence., Prentice-Hall, 1997. 
  25. Karaboga, D., Kaya, E., 10.1007/s10462-017-9610-2, Artif. Intell. Rev. 52 (2019), 2263-2293. DOI10.1007/s10462-017-9610-2
  26. Kartli, N., Bostanci, E., Guzel, M. S., , Kybernetika 59 (2023), 1, 45-63. MR4567841DOI
  27. Kartli, N., Bostanci, E., Guzel, M. S., , Computing 106 (2024), 10, 3195-3227. MR4794582DOI
  28. Kelley, P. R., Barry, R., 10.1016/S0167-7152(96)00140-X, Statisr. Probab. Lett. 33 (1997), 3, 291-297. DOI10.1016/S0167-7152(96)00140-X
  29. Kondratenko, Y., Kozlov, O., Lysiuk, H., Kryvda, V., Maksymova, O., Fuzzy automatic control of the pyrolysis process for the municipal solid waste of variable composition., J. Automat. Mobile Robotics Intell. Systems 16 (2022), 1, 83-94. 
  30. Kusumadewi, S., Rosita, L., Wahyuni, E. G., , Int. J. Advanced Sci. Engrg. Inform. Technol. 12 (2022), 5, 2140. DOI
  31. Kusumadewi, S., Rosita, L., Wahyuni, E. G., , Expert Syst. Appl. 227 (2023), 120314. DOI
  32. Li, G., Hu, X., Chen, S., Chang, K., Li, P., Wang, Y., , Int. J. Comput. Commun. Control 19 (2024), 4, 6611. DOI
  33. Mallick, A. K., Das, A., , In: 2021 IEEE 4th International Conference on Computing, Power and Communication Technologies (GUCON), Kuala Lumpur 2021. pp. 1-6. DOI
  34. Mei, Z., Zhao, T., Xie, X., 10.1016/j.ins.2023.119740, Inform. Sci. 652 (2024), 119740. DOI10.1016/j.ins.2023.119740
  35. Mert, A., 10.1080/16583655.2020.1804157, J. Taibah Univ. Sci. 14 (2020), 1, 1100-1109. DOI10.1080/16583655.2020.1804157
  36. Nachaoui, M., Nachaoui, A., Shikhlinskaya, R. Y., Elmoufidi, A., 10.19139/soic-2310-5070-1706, Statist. Optim. Inform. Comput. 11 (2023), 1, 29-43. DOI10.19139/soic-2310-5070-1706
  37. Namgung, H., Ohn, S. W., , Sensors 22 (2022), 13. DOI
  38. Nasiboglu, R., Abdullayeva, R., 10.5121/ijsc.2018.9301, Int. J. Soft Comput. (IJSC) 9 (2018), 2/3, 1-15. DOI10.5121/ijsc.2018.9301
  39. Nasiboglu, R., Akdogan, A., Estimation of the second hand car prices from data extracted via web scraping techniques., J. Modern Technol. Engrg. 5 (2020), 2, 157-166. 
  40. Nasiboglu, R., Erten, Z. T., 10.3906/elk-1811-142, Turkish J. Electr. Engrg. Computer Sci. 27 (2019), 6, 4023-4037. DOI10.3906/elk-1811-142
  41. Nasiboglu, R., Nasibov, E., 10.1016/j.simpa.2022.100430, Software Impacts 14 (2022), 100430. DOI10.1016/j.simpa.2022.100430
  42. Nasiboglu, R., Nasibov, E., 10.1016/j.eswa.2022.118771, Expert Syst. Appl. 212 (2023), 118771. DOI10.1016/j.eswa.2022.118771
  43. Nasiboglu, R., A novel fuzzy inference model with rule-based defuzzification approach., J. Modern Technol. Engrg. 7 (2022), 2, 124-133. 
  44. Nasiboglu, R., An approach to solution of verbal stated mathematical problems., J. Modern Technol. Engrg. 5 (2020), 1, 25-35. 
  45. Nasiboglu, R., Analysis of different approaches to regression problem with fuzzy information., J. Modern Technol. Engrg. 7 (2022), 3, 187-198. 
  46. Nasibov, E. N., Kinay, A. O., , Inform. Sci. 179 (2009), 5, 688-698. DOI
  47. Nasibov, E. N., Mert, A., , Automat. Control Computer Sci. 41 (2007), 265-273. DOI
  48. Pourabdollah, A., Mendel, J. M., John, R. I., Alpha-cut representation used for defuzzification in rule-based systems., Fuzzy Sets Syst. 399 (2020), 110-132. MR4154438
  49. Ramly, N., Rusiman, M. S., Nasibov, E., Nasiboglu, R., 10.37934/araset.46.1.218236, J. Advanced Res. Appl. Sci. Engrg. Technol. 46 (2024), 1, 218-236. DOI10.37934/araset.46.1.218236
  50. Rashidi, S., Xu, W., Lin, D., Turpin, A., Kulik, L., Ehinger, K., An active foveated gaze prediction algorithm based on a Bayesian ideal observer., Pattern Recogn. 143 (2023), 109694. 
  51. Riman, C. F., Abi-Char, P. E., 10.18178/ijmerr.12.5.313-323, Int. J. Mechan. Engrg. Robotics Res. 12 (2023), 5, 313-323. DOI10.18178/ijmerr.12.5.313-323
  52. Savaş, S. K., Nasibov, E. N., , Int. J. Intell. Syst. 33 (2018), 858-878. DOI
  53. Samet, R., Amrahov, S. E., Ziroğlu, A. H., , In: 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA), Istanbul 2012. pp. 402-406. DOI
  54. Tian, Y., Nie, G., Tian, H., Cui, Q., 10.1007/s00607-022-01115-z, Computing 105 (2023), 1, 115-129. MR4530130DOI10.1007/s00607-022-01115-z
  55. Vafakhah, M., Loor, S. M. H., Pourghasemi, H., Katebikord, A., Comparing performance of random forest and adaptive neuro-fuzzy inference system data mining models for flood susceptibility mapping., Arabian J. Geosci. 13 (2020), 1-16. 
  56. Wahba, M., Essam, R., El-Rawy, M., Al-Arifi, N., Abdalla, F., Elsadek, W. M., , Heliyon 10 (2024), 13, e33982. DOI
  57. Yagiz, S., Gokceoglu, C., 10.1016/j.eswa.2009.07.046, Expert Systems Appl. 37 (2010), 2265-2272. DOI10.1016/j.eswa.2009.07.046
  58. Yazid, E., Garratt, M., Santoso, F., , Appl. Soft Comput. 78 (2019), 373-392. DOI
  59. Yıldırım, H. B., Kullu, K., Amrahov, S. E., , Univ. Acces Inform. Soc. 23 (2024), 2, 901-911. DOI
  60. Zhang, H., Hu, X., Zhu, X., Liu, X., Pedrycz, W., , IEEE Trans. Knowl. Data Engrg. 36 (2024), 5621-5632. DOI
  61. Zhang, Q., Yao, Y., Kong, J., Ma, X., Zhu, H., , IEEE Trans. Geosci. Remote Sensing 61 (2023), 1-12. DOI
  62. Zhu, X., Hu, X., Yang, L., Pedrycz, W., Li, Z., , IEEE Trans. Fuzzy Systems 32 (2024), 5, 2976-2986. DOI
  63. Zimmermann, K., , Kybernetika 59 (2023), 4, 527-536. MR4660376DOI

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.