Skip to main content
Springer Nature Link
Log in

Optimal Recognition Model Based on Convolutional Neural Networks and Fuzzy Gravitational Search Algorithm Method

  • Chapter
  • First Online:
Hybrid Intelligent Systems in Control, Pattern Recognition and Medicine

Part of the book series: Studies in Computational Intelligence ((SCI,volume 827))

  • 438 Accesses

Abstract

In this paper we propose the optimization of a convolutional neural network (CNN) using the Fuzzy Gravitational Search Algorithm method (FGSA). The FGSA is inspired in extension of the Gravitational Search Algorithm (GSA) using fuzzy logic and this method is used to obtain the number of images per block that will enter in the training phase. The optimized CNN is applied for pattern recognition using the 10 handwritten numbers of the MINIST database. The model of the CNN model presented in this paper can be applied for any recognition or image classification application. In addition, the recognition rate achieved with the CNN optimized by the FGSA was compared against the results obtained with the non-optimized CNN.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. L.D. Le Cun Jackel, B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, B. Le Cun, J. Denker, D. Henderson, Handwritten digit recognition with a back-propagation network. Adv. Neural Inf. Process. Syst., pp. 396–404 (1990)

    Google Scholar 

  2. D. Sánchez, P. Melin, O. Castillo, Fuzzy adaptation for particle swarm optimization for modular neural networks applied to iris recognition. NAFIPS 648, 104–114 (2017)

    Google Scholar 

  3. F. Valdez, O. Castillo, P. Melin, Ant colony optimization for the design of Modular Neural Networks in pattern recognition. Proc. Int. Jt. Conf. Neural Netw. pp. 163–168 (2016 Oct)

    Google Scholar 

  4. C.I. Gonzalez, J.R. Castro, O. Mendoza, P. Melin, General Type-2 fuzzy edge detector applied on face recognition system using neural networks, in 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 2325–2330 (2016)

    Google Scholar 

  5. G.E. Martínez, P. Melin, O.D. Mendoza, O. Castillo, Face recognition with a sobel edge detector and the Choquet integral as integration method in a modular neural networks, in Design of Intelligent Systems Based on Fuzzy Logic, Neural Networks and Nature-Inspired Optimization, ed. by P. Melin, O. Castillo, J. Kacprzyk (Springer International Publishing, Cham, 2015), pp. 59–70

    Chapter  Google Scholar 

  6. P. Melin, I. Miramontes, G. Prado-Arechiga, A hybrid model based on modular neural networks and fuzzy systems for classification of blood pressure and hypertension risk diagnosis. Expert Syst. Appl. 107, 146–164 (2018)

    Article  Google Scholar 

  7. F. Valdez, P. Melin, O. Castillo, Modular Neural Networks architecture optimization with a new nature inspired method using a fuzzy combination of Particle Swarm Optimization and Genetic Algorithms. Inf. Sci. (Ny) 270, 143–153 (2014)

    Article  Google Scholar 

  8. P. Melin, D. Sánchez, O. Castillo, Genetic optimization of modular neural networks with fuzzy response integration for human recognition. Inf. Sci. (Ny) 197, 1–19 (2012)

    Article  Google Scholar 

  9. P. Melin, D. Sánchez, Multi-objective optimization for modular granular neural networks applied to pattern recognition. Inf. Sci. (Ny) 460–461, 594–610 (2018)

    Article  MathSciNet  Google Scholar 

  10. D. Sánchez, P. Melin, O. Castillo, Engineering Applications of Artificial Intelligence Optimization of modular granular neural networks using a firefly algorithm for human recognition. Eng. Appl. Artif. Intell. 64(Oct 2016), 172–186 (2017)

    Article  Google Scholar 

  11. C.I. Gonzalez, P. Melin, J.R. Castro, O. Mendoza, O. Castillo, An improved sobel edge detection method based on generalized type-2 fuzzy logic. Soft Comput. J. 20(2), 773–784 (2016)

    Article  Google Scholar 

  12. C.I. Gonzalez, J.R. Castro, O. Mendoza, P. Melin, O. Castillo, Optimization by cuckoo search of interval type-2 fuzzy logic systems for edge detection. Stud. Fuzziness Soft Comput. 342, 141–154 (2016)

    Article  MathSciNet  Google Scholar 

  13. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2323 (1998)

    Article  Google Scholar 

  14. A. Frome, G. Cheung, A. Abdulkader, M. Zennaro, B. Wu, A. Bissacco, H. Adam, H. Neven, L. Vincent, Large-scale privacy protection in google street view. Evaluation, pp. 2–9 (2009)

    Google Scholar 

  15. R. Hadsell, P. Sermanet, J. Ben, A. Erkan, M. Scoffier, K. Kavukcuoglu, U. Muller, Y. LeCun, Learning long-range vision for autonomous off-road driving. J. F. Robot. 26(2), 120–144 (2009)

    Article  Google Scholar 

  16. A. Sombra, F. Valdez, P. Melin, O. Castillo, A new gravitational search algorithm using fuzzy logic to parameter adaptation, in 2013 IEEE Congress on Evolutionary Computation no. 3, pp. 1068–1074 (2013)

    Google Scholar 

  17. E. Rashedi, H. Nezamabadi-pour, S. Saryazdi, GSA: a gravitational search algorithm. Inf. Sci. (Ny) 179(13), 2232–2248 (2009)

    Article  Google Scholar 

  18. O.P. Verma, R. Sharma, Newtonian gravitational edge detection using gravitational search algorithm. Int. Conf. Commun. Syst. Netw. Technol., pp. 184–188 (2012)

    Google Scholar 

  19. A. Hatamlou, S. Abdullah, Z. Othman, Gravitational search algorithm with heuristic search for clustering problems. Conf. Data Min. Optim., pp. 190–193, (2011 June)

    Google Scholar 

  20. S. Mirjalili, S.Z. Mohd Hashim, H. Moradian Sardroudi, Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm. Appl. Math. Comput. 218(22), 11125–11137 (2012)

    Article  MathSciNet  Google Scholar 

  21. S. Mirjalili, S.Z.M. Hashim, A new hybrid PSOGSA algorithm for function optimization, in Proceedings of ICCIA 2010–2010 International Conference on Computer and Information Application, no. 1, pp. 374–377, 2010

    Google Scholar 

  22. Y. LeCun, Y. Bengio, Convolution networks for images, speech, and time-series. Igarss 2014(1), 1–5 (1998)

    Google Scholar 

  23. Y. Bengio, P. Lamblin, Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst. (1), 153–160 (2007)

    Google Scholar 

  24. K. Chellapilla, S. Puri, P. Simard, High performance convolutional neural networks for document processing. Int. Work. Front. Handwrit. Recognit. (2006)

    Google Scholar 

  25. V. Nair, G.E. Hinton, Rectified linear units improve restricted Boltzmann machines, in Proceedings of the 27th International Conference on Machine Learning, no. 3, pp. 807–814 (2010)

    Google Scholar 

  26. M. Ranzato, F.J. Huang, Y-L. Boureau, Y. LeCun, Unsupervised learning of invariant feature hierarchies applications to object recognition, in IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)

    Google Scholar 

  27. J. Yang, K. Yu, Y. Gong, T.H. Beckman, Linear spatial pyramid matching using sparse coding for image classification, in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1794–1801 (2009)

    Google Scholar 

  28. T. Wang, D.J. Wu, A. Coates, A.Y. Ng, End-to-end text recognition with convolutional neural networks, in ICPR, International Conference on Pattern Recognition, pp. 3304–3308 (2012)

    Google Scholar 

  29. P. Kim, MATLAB Deep Learning (2017)

    Google Scholar 

  30. R. Venkatesan, B. Li, Convolutional Neural Networks in Visual Computing: A Concise Guide (CRC Press, Boca Raton, 2017)

    Google Scholar 

  31. L. Lu, Y. Zheng, G. Carneiro, L. Yang, Deep Learning and Convolutional Neural Networks for Medical Image Computing (2017)

    Google Scholar 

  32. J. Walker, R. Resnick, D. Halliday, Fundamentals of Physics (Wiley, New York, 2008)

    Google Scholar 

  33. B. González, F. Valdez, P. Melin, G. Prado-Arechiga, Fuzzy logic in the gravitational search algorithm for the optimization of modular neural networks in pattern recognition. Expert Syst. Appl. 42(14), 5839–5847 (2015)

    Article  Google Scholar 

  34. B. González, F. Valdez, P. Melin, G. Prado-Arechiga, Fuzzy logic in the gravitational search algorithm enhanced using fuzzy logic with dynamic alpha parameter value adaptation for the optimization of modular neural networks in echocardiogram recognition. Appl. Soft Comput. J. 37, 245–254 (2015)

    Article  Google Scholar 

  35. C. Leal Ramírez, O. Castillo, P. Melin, A. Rodríguez Díaz, Simulation of the bird age-structured population growth based on an interval type-2 fuzzy cellular structure. Inf. Sci. 181(3), 519–535 (2011)

    Article  MathSciNet  Google Scholar 

  36. N.R. Cázarez-Castro, L.T. Aguilar, O. Castillo, Designing Type-1 and Type-2 Fuzzy logic controllers via Fuzzy Lyapunov synthesis for nonsmooth mechanical systems. Eng. Appl. AI 25(5), 971–979 (2012)

    Article  Google Scholar 

  37. O. Castillo P. Melin, Intelligent systems with interval type-2 fuzzy logic. Int. J. Innov. Comput. Inf. Control 4(4), 771–783 (2008)

    Google Scholar 

  38. G.M. Mendez, O. Castillo, Interval type-2 TSK fuzzy logic systems using hybrid learning algorithm, in The 14th IEEE International Conference on Fuzzy Systems, 2005. FUZZ’05, pp. 230–235

    Google Scholar 

  39. P. Melin, O. Castillo, Intelligent control of complex electrochemical systems with a neuro-fuzzy-genetic approach. IEEE Trans. Ind. Electron. 48(5), 951–955

    Article  Google Scholar 

  40. P. Melin, A. Mancilla, M. Lopez, O. Mendoza, A hybrid modular neural network architecture with fuzzy Sugeno integration for time series forecasting. Appl. Soft Comput. 7(4), 1217–1226 (2007)

    Article  Google Scholar 

  41. P. Melin, O. Castillo, Modelling, Simulation and Control of Non-Linear Dynamical Systems: an Intelligent Approach Using Soft Computing and Fractal Theory (CRC Press, Boca Raton, 2001)

    Google Scholar 

  42. P. Melin, G Prado-Arechiga: New Hybrid Intelligent Systems for Diagnosis and Risk Evaluation of Arterial Hypertension (Springer, Switzerland, 2018)

    Book  Google Scholar 

  43. P. Melin, C.I. González, J.R. Castro, O. Mendoza, O. Castillo, Edge-detection method for image processing based on generalized Type-2 fuzzy logic. IEEE Trans. Fuzzy Syst. 22(6), 1515–1525 (2014)

    Article  Google Scholar 

Download references

Acknowledgements

We thank our sponsor CONACYT and the Tijuana Institute of Technology for the financial support provided with the scholarship number 816488.

Author information

Authors and Affiliations

  1. Tijuana Institute of Technology, Tijuana, Mexico

    Yutzil Poma, Patricia Melin, Claudia I. González & Gabriela E. Martinez

Authors
  1. Yutzil Poma
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Patricia Melin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Claudia I. González
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gabriela E. Martinez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Patricia Melin .

Editor information

Editors and Affiliations

  1. Division of Graduate Studies and Research, Tijuana Institute of Technology, Tijuana, Baja California, Mexico

    Oscar Castillo

  2. Division of Graduate Studies and Research, Tijuana Institute of Technology, Tijuana, Baja California, Mexico

    Patricia Melin

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Poma, Y., Melin, P., González, C.I., Martinez, G.E. (2020). Optimal Recognition Model Based on Convolutional Neural Networks and Fuzzy Gravitational Search Algorithm Method. In: Castillo, O., Melin, P. (eds) Hybrid Intelligent Systems in Control, Pattern Recognition and Medicine. Studies in Computational Intelligence, vol 827. Springer, Cham. https://doi.org/10.1007/978-3-030-34135-0_6

Download citation

Publish with us

Policies and ethics