Granular neural networks | Artificial Intelligence Review Skip to main content
Springer Nature Link
Log in

Granular neural networks

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Fuzzy neural networks (FNNs) and rough neural networks (RNNs) both have been hot research topics in the artificial intelligence in recent years. The former imitates the human brain in dealing with problems, the other takes advantage of rough set theory to process questions uncertainly. The aim of FNNs and RNNs is to process the massive volume of uncertain information, which is widespread applied in our life. This article summarizes the recent research development of FNNs and RNNs (together called granular neural networks). First the fuzzy neuron and rough neuron is introduced; next FNNs are analysed in two categories: normal FNNs and fuzzy logic neural networks; then the RNNs are analysed in the following four aspects: neural networks based on using rough sets in preprocessing information, neural networks based on rough logic, neural networks based on rough neuron and neural networks based on rough-granular; then we give a flow chart of the RNNs processing questions and an application of classical neural networks based on rough sets; next this is compared with FNNs and RNNs and the way to integrate is described; finally some advice is given on development of FNNs and RNNs in future.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Bryll R, Gutierrez-Osuna R, Quek F (2003) Attribute bagging: improving accuracy of classifier ensembles by using random feature subset. Pattern Recognit 36(3): 1291–1302

    Article  MATH  Google Scholar 

  • Chang ZL, Wang Q (2009) A new rough neural network construction algorithm. Comput Ear 4: 51–53

    Google Scholar 

  • Chen D, He H (2001) A new neuron model based on weak T-norm cluster. Chin J Comput 24(10): 1115–1120

    Google Scholar 

  • Chen Y, Hu C (2001) Dynamic evaluation method study enterprise supply chain performance based on FCM. Appl Res Comput 28(1): 185–188

    Google Scholar 

  • Chen GC, Yu JS (2005) Particle swarm optimization neural network and its application in soft-sening modeling. Lect Notes Comput Sci 3611: 610–617

    Article  Google Scholar 

  • Chen W, Zhang H, Weng H (2006) Clustering of fuzzy Hopfield neural network and its application in DRP. Comput Eng Appl 42(6): 215–218

    Google Scholar 

  • Cheng J, Chen H (2010) A hybrid forecast marketing timing model based on probabilistic network, rough set and C4.5. Expert Syst Appl 37: 1814–1820

    Article  Google Scholar 

  • Chen Y, Hu C, Peng J (2011) Dynamic evaluation method study enterprise supply chain performance based on FCM. Appl Res Comput 28(1): 185–188

    Google Scholar 

  • Chiang J-h, Ho S-h (2008) A combination of rough-based feature selection and RBF neural network for classification selection gene expression. IEEE Trans Nanobiosci 7(1): 91–99

    Article  Google Scholar 

  • Ding H, Ding S, Hu L (2010) Research progress of attribute reduction based on rough sets. Comput Eng Sci 32(6): 92–94

    Google Scholar 

  • Ding S, Chen J, Xu X et al (2011) Rough neural networks: a review. J Comput Inf Syst 7(7): 2338–2346

    Google Scholar 

  • Dong M, Jiang H (2007) A rough CP neural network model based on rough set. In: Third international conference on natural computation, pp 90–96

  • Dong C, Wu D, He J (2008) Decision analysis of combat effectiveness based on rough set neural network. In: Fourth international conference on natural computation, pp 227–231

  • Eysa S, Saeed G (2005) Optimum design of structures by an improved genetic algorithm using neural networks. Adv Eng Softw 36(11): 757–767

    Google Scholar 

  • Gao H, Gao L, Zhou C, Yu D (2004) Particle swarm optimization based algorithm for neural network learning. Chin J Electron 32(9): 1572–1574

    Google Scholar 

  • Glorennec PY (1996) Neuro-fuzzy logic. In: Proceeding IEEE-FUZZ. New Orleans, pp 512–518

  • Gong W (2009) Application of rough set and fuzzy neural network in information handling. In: International conference on networking and digital society, pp 36–39

  • Han M, Sun Y (2006) Structure and algorithm design of a fuzzy logic inference neural network. Control Decis 21(4): 415–420

    MATH  MathSciNet  Google Scholar 

  • He F (1994) Handwritten numeral recognition of a fuzzy associative memory neural network. Appl Res Comput 11(3): 8–10

    Google Scholar 

  • He H, Wang H (2001) Principle of universal logics. Science Press, Beijing

    Google Scholar 

  • He H, Zhao N (2009) The research on CMAC network model based on rough set for flatness control. In: Fourth international conference on innovative computing, information and control, pp 1252–1254

  • Hirota K, Pedrycz W (1994) OR/AND neuron in modeling fuzzy connectives. IEEE Trans Fuzzy Syst 2(2): 15l–161

    Article  Google Scholar 

  • Kothari A, Keskar A (2008) Rough neuron based neural classifier. In: First international conference on emerging trends in engineering and technology, pp 624–628

  • Li C, Zhang H (2006) A new pattern recognition model based on heuristic SOM network and rough set theory. In: IEEE international conference on vehicular electronics and safety, pp 45–48

  • Liao Y, Zhang S, Yi D, Yi J (2009) Faults diagnosis of diesels based on rough set genetic neural network. Control Eng China 16(6): 709–712

    Google Scholar 

  • Ling J, Chen Z, Zhou Z (2004) Feature selection based neural network ensemble method. J Fudan University (Nature Sci) 43(5): 685–688

    Google Scholar 

  • Lingras P (1996) Rough neural networks. In: Proceeding of the 6th international conference on information processing and management of uncertainty in knowledge-based systems, pp 1445–1450

  • Mamanadi EH (1974) Application of fuzzy algorithms of simple dynamic plant. Proc IEEE 121(12): 1585–1588

    Google Scholar 

  • Marcek M, Marcek D (2008) Approximation and prediction of wages based on granular neural network. Rough Sets Knowl Technol 5009: 556–563

    Article  Google Scholar 

  • Pal SK, Peters JF, Polkowski L (2002) Rough-neurocomputing: an introduction. In: Rough-neuro computing: technologies for computing with words, pp 15–41

  • Pan W (2008) Rough set theory and its application in the intelligent systems. In: Proceedings of the 7th world congress on intelligent control and automation, pp 3076–3081

  • Pawlak Z (1982) Rough set. Int J Comput Inf Sci 11(15): 341–356

    Article  MATH  MathSciNet  Google Scholar 

  • Pedrycz W, Vukovich G (2001) Granular neural networks. Neurocomputing 36(1–4): 205–224

    Article  MATH  Google Scholar 

  • Peters JF, Szczuka MS (2002a) Rough neurocomputing: a survey of basic models of neurocomputation. In: Rough sets and current trends in comuputing, pp 308–315

  • Peters JF, Szczuka MS (2002b) Rough neurocomputing: a survey of basic models of neurocomputation. In: RSCTC2002, pp 308–315

  • Peters JF, Han L, Ramanna S (2001) Rough neural computing in signal analysis. Comput Intell 17(3): 493–513

    Article  MathSciNet  Google Scholar 

  • Ren X, Zhang F (2010) Application of quantum neural network based on rough set in transformer fault diagnosis. In: Second international conference on machine learning and computing, pp 978–980

  • Shi H, Zhang F, Sun J (2003) Knowledge-based fuzzy multilayer perceptron. Comput Eng Appl 39(1): 99–102

    Google Scholar 

  • Shrikant K, Shivam A (2009) A combined classifier to detect landmines using rough set theory and Hebb net learning & fuzzy filter as neural networks. In: International conference on processing systems, pp 423–427

  • Skowron A (2001) Toward intelligent systems: calculi of information granules. In: JSAI 2001, pp 251–260

  • Skowron A (2002) Approximate reasoning by agents. In: CEEMAS2001, pp 3–14

  • Stetiawan NA, Venkatachalam PA, Hani AFM (2008) Missing attribute value prediction based on artificial neural network and rough set theory. In: 2008 international conference on bioMedical engineering and informatics, pp 306–310

  • Syeda M, Zhang Y-Q, Pan Y (2002) Parallel granular neural networks for fast credit card fraud detection. In: Proceedings of the 2002 IEEE international conference vol 1, pp 572–577

  • Szczuka MS (1998) Rough sets and artificial neural networks. In: Rough sets in knowledge discovery (2): applications, case studies and software systems, pp 449–470

  • Tang C, Gao X (2001) The researching development of evolutionary neural networks. J Syst Eng Electron 23(10): 92–97

    Google Scholar 

  • Thangavel K, Pethalakshmi A (2009) Dimensionality reduction based on rough set theory: a review. Appl Soft Comput 9(1): 1–12

    Article  Google Scholar 

  • Wang W, Cai L (2001) The neural network based on rough set. Comput Eng 27(5): 19–21

    Google Scholar 

  • Wang W, Mi H (2010) The application of rough neural network in RMF model. In: 2010 2nd international Asia conference on informatics in control, automation and robotics, pp 210–213

  • Wang W, Xie B (2009) The evaluation and application research about regional innovation capability based on rough set and BP neural network. In: Second international conference on information and computing science, pp 308–311

  • Wang G, Zhang C, Huang L (2001) A study classification algorithm for data ming based on hybrid intelligent systems. In: Ninth ACIS international conference on software engineering, artificial intelligence, Networking, and parallel/dostributed computing, pp 371–375

  • Xie Z, Shang L, Li N, Wan J (2004) Research on rough set application in neural network. Comput Appl 21(9): 71–74

    Google Scholar 

  • Xu S, He X (2002) A normal fuzzy neural network and its application to sedimentary facies identification. Control Decis 17(3): 332–335

    Google Scholar 

  • Xue F, Kong-Lin KE (2008) Five-category evaluation of commercial bank’s load by the integration of rough set and neural network. Syst Eng Theory Pract 28(1): 40–45

    Article  Google Scholar 

  • Yager R (1992) OWA neurons: a new of fuzzy neurons. In: Proceeding IEEE-FUZZ. San Diego, pp 2326–2340

  • Yao W, Wang Q, Chen Z, Wang J (2004) The researching overview of evolutionary neural network. Comput Sci 31(3): 125–129

    Google Scholar 

  • Zadeh LA (1965) Fuzzy set. Inf Control 8(3): 338–358

    Article  MATH  MathSciNet  Google Scholar 

  • Zhang D (2007) Integrated methods of rough sets and neural network and their applications in pattern recognition. Hunan University, Hunan

    Google Scholar 

  • Zhang D, Wang Y (2005) Filtering image impulse noise based on fuzzy rough neural network. J Comput Appl 25(10): 2336–2338

    Google Scholar 

  • Zhang D, Wang Y (2006) Fuzzy-rough neural network and its application to vowel recognition. Control Decis 21(2): 221–224

    MATH  Google Scholar 

  • Zhang D, Wang Y (2007a) The researche of a kind of rough logic neual network. J Electron Inf Technol 29(3): 611–615

    Google Scholar 

  • Zhang D, Wang Y (2007b) Variable discretization precision rough logic neural network based on approximation area partition and its application to remote sensing image classification. J Electron Inf Technol 29(11): 2720–2723

    Google Scholar 

  • Zhang YQ, Fraser MD, Gagliano RA, Kandel A (2000) Granular neural networks for numerical-linguistic data fusion and knowledge discovery. IEEE Trans Neural Netw 11(3): 658–667

    Article  Google Scholar 

  • Zhang X, Cheng L, Yu J (2006) Study of fault diagnosis based on new rough set-neural networks. Appl Res Comput 23(5): 156–158

    Google Scholar 

  • Zhang D, Wang Y, Huan H (2008a) Rough neural network based on variable precision rough set. J Electron Inf Technol 30(8): 1913–1916

    Article  Google Scholar 

  • Zhang YQ, Jin B, Tang YC (2008b) Granular neural networks with evolutionary interval learning. IEEE Trans Fuzzy Syst 16(2): 309–319

    Article  Google Scholar 

  • Zhao W, Chen G (2002) A survery for the integration of rough set theory with neural networks. Syst Eng Electron 24(10): 103–107

    Google Scholar 

  • Zhong J, Yang S, Huang L (2004) Application of fuzzy artmap for tone recognition of Chinese trisyllabic word. Comput Eng Des 25(1): 52–55

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, 221116, China

    Shifei Ding, Hongjie Jia & Jinrong Chen

  2. Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China

    Shifei Ding

  3. Geomatics College, Shandong University of Science and Technology, Qingdao, 266510, China

    Fengxiang Jin

Authors
  1. Shifei Ding
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Hongjie Jia
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Jinrong Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Fengxiang Jin
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Shifei Ding.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ding, S., Jia, H., Chen, J. et al. Granular neural networks. Artif Intell Rev 41, 373–384 (2014). https://doi.org/10.1007/s10462-012-9313-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-012-9313-7

Keywords