Нечеткий классификатор типа Min-Max: обзор

DOI: 10.21293/1818-0442-2023-26-1-65-75

Скачать текст статьи в формате PDF

Скачать JATS xml

Аннотация: В связи с ростом объема обрабатываемой информации и внедрением систем искусственного интеллекта в критически важные сферы деятельности, адаптация в режиме онлайн и интерпретируемость стали одними из важных требований к моделям машинного обучения. Популярные модели, такие как искусственные нейронные сети, не могут в полном объеме их выполнить. Нечеткие классификаторы типа Min-Max являются интерпретируемыми благодаря лежащей в их основе теории нечеткой логики и адаптируемы с приходом новой порции информации. Данная статья представляет всесторонний обзор литературы по моделям машинного обучения на основе нечетких классификаторов типа Min-Max. Представлены архитектура классификатора и принцип его работы. Проводится обзор модификаций и оценивается их эффективность. Указаны применения классификатора и его модификации в решении реальных прикладных задач. В заключение делаются выводы о работе классификатора и проблемах, которые остались нерешенными.

Ключевые слова: машинное обучение, нечеткий классификатор, анализ данных, адаптация классификатора

Сведения о финансировании: Работа выполнена при финансовой поддержке РНФ, грант № 22-21-00021.

Библиография статьи:
Сарин К. С. Нечеткий классификатор типа Min-Max: обзор / К. С. Сарин // Доклады Томского государственного университета систем управления и радиоэлектроники. – 2023. – Т. 26, № 1. – С. 65–75. DOI: 10.21293/1818-0442-2023-26-1-65-75

Авторы и правообладатели:

  • Сарин К. С. , Томский государственный университет систем управления и радиоэлектроники (Томск, Россия)

  • 1. Hastie T. The elements of statistical learning / T. Hastie, R. Tibshirani, J. Friedman. – Switzerland: Springer, 2020. – 764 p.
  • 2. Bengio Y. Deep learning for AI / Y. Bengio, Y. LeCun, G.E. Hinton // Communications of the ACM. – 2021. – Vol. 64. – PР. 58–65.
  • 3. Bappy J.H. Online adaptation for joint scene and object classification / J.H. Bappy, S. Paul, A.K. Roy-Chowdhury // Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science. – 2016. – Vol. 9912. – PР. 227–243.
  • 4. Gheibi O. Lifelong self-adaptation: self-adaptation meets lifelong machine learning / O. Gheibi, D. Weyns // SEAMS '22: Proceedings of the 17th Symposium on Software Engineering for Adaptive and Self-Managing Systems, May 2022. – 2022. – PР. 1–12.
  • 5. McCloskey M. Catastrophic interference in connectionist networks: the sequential learning problem / M. McCloskey, N. J. Cohen // Psychology of Learning and Motivation. – 1989. – Vol. 24. – РP. 109–165.
  • 6. Ridley M. Explainable artificial intelligence (XAI) // Information Technology and Libraries. – 2022. – Vol. 41, No. 2. – PР. 1–17.
  • 7. Cheng Y. Rule extraction based on granulation order in interval-valued fuzzy information system / Y. Cheng, D. Miao // Expert Systems with Applications. – Vol. 8, No. 10. – PР. 12249–12261.
  • 8. Simpson P.K. Fuzzy Min-Max neural networks. Part 1: Classification // IEEE Transaction on Neural Networks. – 1992. – Vol. 3, No. 5. – PР. 776–786.
  • 9. Bargiela A. An inclusion/exclusion fuzzy hyperbox classifier / A. Bargiela, W. Pedrycz, M. Tanaka // International Journal of Knowledge-based and Intelligent Engineering Systems. – 2004. – Vol. 8. – РP. 91–98.
  • 10. Nandedkar A.V. A Fuzzy Min-Max neural network classifier with compensatory neuron architecture / A.V. Nandedkar, P.K. Biswas // IEEE Transactions on Neural Networks. – 2007. – Vol. 18, No. 1. – РP. 42–54.
  • 11. Zhang H. Data-core-based fuzzy min–max neural network for pattern classification / H. Zhang, J. Liu, D. Ma, Z. Wang // IEEE Transactions on Neural Networks. – 2011. – Vol. 22, No. 12. – PР. 2339–2352.
  • 12. Davtalab R. Multi-level fuzzy min-max neural network classifier / R. Davtalab, M.H. Dezfoulian, M. Mansoorizadeh // IEEE Transactions on Neural Networks Learning System. – 2014. – Vol. 25, No. 3. – РP. 470–482.
  • 13. Gabrys B. General fuzzy min-max neural network for clustering and classification / B. Gabrys, A. Bargiela // IEEE Transactions on Neural Networks. – 2000. – Vol. 11, No. 3. – РP. 769–783.
  • 14. Nandedkar A.V. A general reflex fuzzy min-max neural network / A.V. Nandedkar, P.K. Biswas // Engineering Letters. – 2007. – Vol. 14, No. 1. – РP. 195–205.
  • 15. Mohammed M.F. An enhanced fuzzy min-max neural network for pattern classification / M.F. Mohammed, C.P. Lim // IEEE Transactions on Neural Networks and Learning Systems. – 2017. – Vol. 26. – РP. 417–429.
  • 16. Mohammed M.F. Improving the fuzzy min-max neural network with a K-nearest hyperbox expansion rule for pattern classification / M.F. Mohammed, C.P. Lim // Appl. Soft Comput. – 2017. – No. 52. – РP. 135–145.
  • 17. Kumar S. A compact fuzzy min max network with novel trimming strategy for pattern classification / S. Kumar, A. Kumar, V. Bajaj, G.K. Singh // Knowledge-Based Systems. – 2022. – No. 246. – Р. 108620.
  • 18. Alhroob E. Fuzzy min-max classifier based on new membership function for pattern classification: A conceptual solution / E. Alhroob, N.A. Ghani // Proc. 8th IEEE Int. Conf. Control Syst., Comput. Eng. (ICCSCE). – 2018. – РP. 131–135.
  • 19. Azad C. A novel fuzzy min–max neural network and genetic algorithm-based intrusion detection system. / С. Azad, V.K. Jha // Proceedings of the second international conference on computer and communication technologies. – 2016. – РP. 429–439.
  • 20. Azad C. Fuzzy min–max neural network and particle swarm optimization based intrusion detection system / С. Azad, V.K. Jha // Microsystem Technology. – 2017. – Vol. 23, No. 4. – РP. 907–918.
  • 21. Khuat T.T. Random hyperboxes / T.T. Khuat, B. Gabrys // IEEE Transactions on Neural Networks and Learning Systems. – 2023. – Vol. 34, No. 2. – РP. 1008–1022.
  • 22. Huang W. Deep Fuzzy Min–Max Neural Network: Analysis and Design / W. Huang, M. Sun, L. Zhu, S.-K. Oh, W. Pedrycz // IEEE Transactions on Neural Networks and Learning Systems. – 2022. – Vol. 33, No. 12. – РP. 1–12.
  • 23. Khuat T.T. A comparative study of general fuzzy min-max neural networks for pattern classification problems / T.T. Khuat, B. Gabrys // Neurocomputing. – 2020. – Vol. 386. – РP. 110–125.
  • 24. Al Sayaydeha O.N. Diagnosis of the Parkinson disease using enhanced fuzzy Min-Max neural network and OneR attribute evaluation method / O.N.Al. Sayaydeha, M.F. Mohammad // 2019 International Conference on Advanced Science and Engineering (ICOASE), Zakho-Duhok, Iraq. – 2019. – PР. 64–69.
  • 25. The combination of fuzzy Min–Max neural network and semi-supervised learning in solving liver disease diagnosis support problem / T.N. Tran, D.M. Vu, M.T. Tran, B.D. Le // Arabian Journal for Science and Engineering. – 2019. – Vol. 44. – РP. 2933–2944.
  • 26. A fuzzy Min-Max neural network based classification of histopathology images / S.A. Kumar, A. Kumar, V. Bajaj, G.K. Singh, B. Kuldeep // 2019 International Conference on Signal Processing and Communication (ICSC), NOIDA, India. – 2019. – РP. 143–146.
  • 27. Computer-aided detection of lung nodules with fuzzy Min-Max Neural network for false positive reduction / Z. Zhai, D. Shi, Y. Cheng, H. Guo // 2014 Sixth International Conference on Intelligent Human-Machine Systems and Cybernetics, Hangzhou, China. – 2014. – РP. 66–69.
  • 28. Bangare S.L. Classification of optimal brain tissue using dynamic region growing and fuzzy min-max neural network in brain magnetic resonance images // Neuroscience Informatics. – 2022. – Vol. 2, No. 3. – P. 100019.
  • 29. Abdulghani A.A. SAIRF: A similarity approach for attack intention recognition using fuzzy min-max neural network / A.A. Abdulghani, M.F. Mohammed // Journal of Computational Science. – 2018. – Vol. 25. – РP. 467–473.
  • 30. Online signature classification using modified fuzzy Min-Max neural network with compensatory neuron topology / B.M. Chaudhari, R.S. Patil, K.P. Rane, U.B. Shinde // Contemporary Computing. IC3 2010. Communications in Computer and Information Science. – 2010. – Vol. 94. – РP. 467–478.
  • 31. Bird swarm algorithm with fuzzy Min-Max neural network for financial crisis prediction / K.P.M. Kumar, S. Dhanasekaran, I.S.H. Punithavathi, P. Duraipandy, A.K. Dutta, I.V. Pustokhina, D.A. Pustokhin // Computers, Materials & Continua. – 2022. – Vol. 73, No. 1. – РP. 1541–1555.
  • 32. Seera M. Improving the fuzzy min-max neural network performance with an ensemble of clustering trees / M. Seera, K. Randhawa, C.P. Lim // Neurocomputing. – 2018. – Vol. 275. – РP. 1744–1751.
  • 33. Seera M. Classification of ball bearing faults using a hybrid intelligent model / M. Seera, M.L.D. Wong, A.K. Nandi // Applied Soft Computing. – 2017. – Vol. 57. – РP. 427–435.
  • 34. Seera M. Online motor fault detection and diagnosis using a hybrid FMM-CART model / M. Seera, C.P. Lim // IEEE Transactions on Neural Networks and Learning Systems. – 2014. – Vol. 25. – РP. 806–812.
  • 35. Liu J. Semi-supervised fuzzy min–max neural network for data classification / J. Liu, Y. Ma, F. Qu, D. Zang // Neural Processing Letters. – 2020 – Vol. 51. – РP. 1445–1464.
  • 36. A hybrid model of fuzzy min–max and brain storm optimization for feature selection and data classification / F. Pourpanaha, C.P. Lim, X. Wang, C.J. Tand, M. Seerae, Y. Shi // Neurocomputing. – 2019. – Vol. 333. – РP. 440–451.
  • 37. A modified fuzzy min–max neural network for data clustering and its application on pipeline internal inspection data / J. Liu, Y. Ma, H. Zhang, H. Su, G. Xiao // Neurocomputing. – 2017. – Vol. 238. – РP. 56–66.
  • 38. Evolved fuzzy min-max neural network for newlabeled data classification / Y. Ma, J. Liu, F. Qu, H. Zhu // Applied Intelligence. – 2022. – Vol. 52. – РP. 305–320.
  • 39. Ma Y. Evolved fuzzy min-max neural network for unknown labeled data and its application on defect recognition in depth / Y. Ma, J. Liu, Y. Zhao // Neural Processing Letters. – 2021. – Vol. 53. – РP. 85–105.
  • 40. A modified fuzzy min–max neural network for data clustering and its application to power quality monitoring / M. Seera, C.P. Lim, C.K. Loo, H. Singh // Applied Soft Computing. – 2015. – Vol. 28. – РP. 19–29.
  • 41. Power quality analysis using a hybrid model of the fuzzy min–max neural network and clustering tree / M. Seera, C.P. Lim, C.K. Loo, H. Singh // IEEE Transactions on Neural Networks and Learning Systems. – 2016. – Vol. 27. – PР. 2760–2767.
Адрес редакции

  634050, г. Томск, пр. Ленина, 40, МК, каб. 310/2

  (3822) 701-582, внутр.: 1456

  journal@tusur.ru