Abstract
In this paper, we propose a novel architecture that combines the convolutional neural network (CNN) with a fuzzy neural network (FNN). We utilize the fuzzy neural network with semi-connected layers to sum up feature information. During the training process, to map membership values, the CNN generates feature maps as outputs and feeds into fuzzifier layers, alternatively called fuzzy maps. The proposed method increases classification accuracy, because fuzzy neural networks can generate not only crisp values but also fuzzy values; this means that there is potentially more information contained in the fuzzy set. Our model is evaluated by cross-validation tests. While big data is necessary for training in general, we train our model with small data and test with big data to demonstrate its ability of object classification in cases where sufficient data are not available.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Yuan, Y., Mou, L., Lu, X.: Scene recognition by manifold regularized deep learning architecture. IEEE Trans. Neural Netw. Learn. Syst. 26(10), 2222–2233 (2015)
Liu, F., Shen, C., Lin, G., Reid, I.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024–2039 (2016)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017)
Anthimopoulos, M., Christodoulidis, S., Ebner, L., Christe, A., Mougiakakou, S.: Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans. Med. Imaging 35(5), 1207–1216 (2016)
McCool, C., Perez, T., Upcroft, B.: Mixtures of lightweight deep convolutional neural networks: applied to agricultural robotics. IEEE Robot. Autom. Lett. 2(3), 1344–1351 (2017)
Chen, S., Wang, H., Xu, F., Jin, Y.-Q.: Target classification using the deep convolutional networks for SAR images. IEEE Trans. Geosci. Remote Sens. 54(8), 4806–4817 (2016)
Chen, Y., Lin, Z., Zhao, X., Wang, G., Gu, Y.: Deep learning-based classification of hyperspectral data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7(6), 2094–2107 (2014)
Cheng, G., Yang, C., Yao, X., Guo, L., Han, J.: When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Trans. Geosci. Remote Sens. 56(5), 2811–2821 (2018)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Shao, L., Zhu, F., Li, X.: Transfer learning for visual categorization: a survey. IEEE Trans. Neural Netw. Learn. Syst. 26(5), 1019–1034 (2015)
Wang, W.-Y., Chien, Y.-H., Lee, T.-T.: Observer-based T-S fuzzy control for a class of general nonaffine nonlinear systems using generalized projection-update laws. IEEE Trans. Fuzzy Syst. 18(3), 493–504 (2011)
Chien, Y.-H., Wang, W.-Y., Hsu, C.-C.: Run-time efficient observer-based fuzzy-neural controller for nonaffine multivariable systems with dynamical uncertainties. Fuzzy Sets Syst. 302, 1–26 (2016)
Gharghan, S.K., Nordin, R., Jawad, A.M., Jawad, H.M., Ismail, M.: Adaptive neural fuzzy inference system for accurate localization of wireless sensor network in outdoor and indoor cycling applications. IEEE Access 6, 38475–38489 (2018)
Wang, W.-Y., Chien, Y.-H., Leu, Y.-G., Hsu, C.-C.: Mean-based fuzzy control for a class of MIMO robotic systems. IEEE Trans. Fuzzy Syst. 24(4), 966–980 (2016)
Kapetanakis, T.N., Vardiambasis, I.O., Lourakis, E.I., Maras, A.: Applying neuro-fuzzy soft computing techniques to the circular loop antenna radiation problem. IEEE Antennas Wirel. Propag. Lett. 17(9), 1673–1676 (2018)
Chien, Y.-H., Wang, W.-Y., Li, I.-H., Lian, K.-Y., Lee, T.-T.: Hybrid intelligent output-feedback control for trajectory tracking of uncertain nonlinear multivariable dynamical systems. Int. J. Fuzzy Syst. 14(1), 141–153 (2012)
Wang, W.-Y., Chien, Y.-H., Leu, Y.-G., Lee, T.-T.: On-line adaptive T-S fuzzy-neural control for a class of general multi-link robot manipulators. Int. J. Fuzzy Syst. 10(4), 240–249 (2008)
Tosunoğlu, N.G., Apaydın, A.: A new spatial algorithm based on adaptive fuzzy neural network for prediction of crustal motion velocities in earthquake research. Int. J. Fuzzy Syst. 20(5), 1656–1670 (2018)
Huang, Y.-P., Singh, A., Liu, S.-I., Wu, S.-I., Quoc, H.A., Sereter, A.: Developing transformed fuzzy neural networks to enhance medical data classification accuracy. Int. J. Fuzzy Syst. 20(6), 1925–1937 (2018)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
ImageNet Database, archived at http://image-net.org/download
Acknowledgements
This work was financially supported by the “Chinese Language and Technology Center” of National Taiwan Normal University (NTNU) from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan, and Ministry of Science and Technology, Taiwan, under Grants no. MOST 108-2634-F-003-002 and MOST 108-2634-F-003-003 through Pervasive Artificial Intelligence Research (PAIR) Labs. We are grateful to the National Center for High-performance Computing for computer time and facilities to conduct this research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hsu, MJ., Chien, YH., Wang, WY. et al. A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database. Int. J. Fuzzy Syst. 22, 1–10 (2020). https://doi.org/10.1007/s40815-019-00764-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40815-019-00764-1