A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database

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.

[1]  Lei Guo,et al.  When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Yih-Guang Leu,et al.  Mean-Based Fuzzy Control for a Class of MIMO Robotic Systems , 2016, IEEE Transactions on Fuzzy Systems.

[3]  Haipeng Wang,et al.  Target Classification Using the Deep Convolutional Networks for SAR Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Yih-Guang Leu,et al.  On-line Adaptive T-S Fuzzy-Neural Control for A Class of General Multi-Link Robot Manipulators , 2008 .

[5]  Chen-Chien James Hsu,et al.  Run-time efficient observer-based fuzzy-neural controller for nonaffine multivariable systems with dynamical uncertainties , 2016, Fuzzy Sets Syst..

[6]  Tristan Perez,et al.  Mixtures of Lightweight Deep Convolutional Neural Networks: Applied to Agricultural Robotics , 2017, IEEE Robotics and Automation Letters.

[7]  Ling Shao,et al.  Transfer Learning for Visual Categorization: A Survey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Xiaoqiang Lu,et al.  Scene Recognition by Manifold Regularized Deep Learning Architecture , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Marios Anthimopoulos,et al.  Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[10]  Yo-Ping Huang,et al.  Developing Transformed Fuzzy Neural Networks to Enhance Medical Data Classification Accuracy , 2018, Int. J. Fuzzy Syst..

[11]  Tsu-Tian Lee,et al.  Observer-Based T–S Fuzzy Control for a Class of General Nonaffine Nonlinear Systems Using Generalized Projection-Update Laws , 2011, IEEE Transactions on Fuzzy Systems.

[12]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[15]  Ioannis O. Vardiambasis,et al.  Applying Neuro-Fuzzy Soft Computing Techniques to the Circular Loop Antenna Radiation Problem , 2018, IEEE Antennas and Wireless Propagation Letters.

[16]  Aysen Apaydin,et al.  A New Spatial Algorithm Based on Adaptive Fuzzy Neural Network for Prediction of Crustal Motion Velocities in Earthquake Research , 2018, Int. J. Fuzzy Syst..

[17]  Ian D. Reid,et al.  Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[19]  Wei-Yen Wang,et al.  Hybrid intelligent output-feedback control for trajectory tracking of uncertain nonlinear multivariable dynamical systems , 2012 .

[20]  Rosdiadee Nordin,et al.  Adaptive Neural Fuzzy Inference System for Accurate Localization of Wireless Sensor Network in Outdoor and Indoor Cycling Applications , 2018, IEEE Access.