Article Search
닫기

Original Article

Split Viewer

International Journal of Fuzzy Logic and Intelligent Systems 2020; 20(4): 336-345

Published online December 25, 2020

https://doi.org/10.5391/IJFIS.2020.20.4.336

© The Korean Institute of Intelligent Systems

New Method of Internal Type-2 Fuzzy-Based CNN for Image Classification

P. Murugeswari1 and S. Vijayalakshmi2

1Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore,Tamilnadu, India
2Department of Computer Applications, NMS S. Vellaichamy Nadar College, Madurai, Tamilnadu, India

Correspondence to :
P. Murugeswari (pmurugeswarik7@gmail.com)

Received: August 26, 2020; Revised: December 8, 2020; Accepted: December 15, 2020

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

In the last two decades, neural networks and fuzzy logic have been successfully implemented in intelligent systems. The fuzzy neural network (FNN) system framework infers the union of fuzzy logic and neural network system framework thoughts, which consolidates their advantages. The FNN system is applied in several scientific and engineering areas. Wherever there is uncertainty associated with the data, fuzzy logic places a vital rule. The fuzzy set can effectively represent and handle uncertain information. The main objective of the FNN system is to achieve a high level of accuracy by including the fuzzy logic in either the neural network structures, activation functions, or learning algorithms. In computer vision and intelligent systems, convolutional neural networks (CNNs) have more popular architectures, and their performance is excellent in many applications. In this paper, fuzzy-based CNN image classification methods are analyzed, and an interval type-2 fuzzy-based CNN is proposed. The experimental results indicated that the performance of the proposed method was good.

Keywords: CNN, FCNN, Fuzzy logic, Interval type-2 fuzzy logic, Feature extraction, Computer vision, Image classification

No potential conflict of interest relevant to this article was reported.

P. Murugeswari received the M.Tech degree in Computer Science and Information Technology from MS University, Tamilnadu, India in 2004 and the Ph.D. degree in Information and Communication Engineering from Anna University, Chennai, Tamilnadu, India in in 2014. She is a Professor of Computer Science and Engineering, Karpagam College of Engineering, Tamilnadu, Coimbatore, Tamilnadu, India since 2004. She received research fund from CSIR to conduct seminar, workshop and conference. She research has been published widely, more than 14 paper in reputed national/international journals and she has been invited to lecture on image processing and fuzzy logic. Her research interest spans the domains of Image processing, Fuzzy logic, Neural Networks, Artificial Intelligence, Machine Learning and Data Science. Her research involves development of algorithm on Type-2 fuzzy logic based image classification using Deep learning concepts.

E-mail: pmurugeswarik7@gmail.com


S. Vijayalakshmi received MCA degree from Madurai Kamaraj University, Madurai, Tamilnadu, India in 2000. and M.Phil degree in Computer Science and SET(State Eligibility Test) in Computer Science and Applications from Mother Teresa University, Kodaikanal, Tamilnadu, and the Ph.D. degree in Computer Science from Bharathiar University, Coimbatore, Tamilnadu, India in in 2017. She is an Assistant Professor of Computer Applications Department, NMS S. Vellaichamy Nadar College, Madurai, Tamilnadu, India. She received a research fund from DRDO to conduct a seminar. Her research has been published widely, more than 10 papers in reputed national/international journals and she has been invited to lecture on Information Retrieval. Her research interest spans the domains of Text Mining, Artificial Intelligence, Neural Networks, Machine Learning and Data Science. Her research involves development of algorithms on Semi-Supervised Clustering using Deep learning concepts.

E-mail: pandyviji@gmail.com


Article

Original Article

International Journal of Fuzzy Logic and Intelligent Systems 2020; 20(4): 336-345

Published online December 25, 2020 https://doi.org/10.5391/IJFIS.2020.20.4.336

Copyright © The Korean Institute of Intelligent Systems.

New Method of Internal Type-2 Fuzzy-Based CNN for Image Classification

P. Murugeswari1 and S. Vijayalakshmi2

1Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore,Tamilnadu, India
2Department of Computer Applications, NMS S. Vellaichamy Nadar College, Madurai, Tamilnadu, India

Correspondence to:P. Murugeswari (pmurugeswarik7@gmail.com)

Received: August 26, 2020; Revised: December 8, 2020; Accepted: December 15, 2020

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

In the last two decades, neural networks and fuzzy logic have been successfully implemented in intelligent systems. The fuzzy neural network (FNN) system framework infers the union of fuzzy logic and neural network system framework thoughts, which consolidates their advantages. The FNN system is applied in several scientific and engineering areas. Wherever there is uncertainty associated with the data, fuzzy logic places a vital rule. The fuzzy set can effectively represent and handle uncertain information. The main objective of the FNN system is to achieve a high level of accuracy by including the fuzzy logic in either the neural network structures, activation functions, or learning algorithms. In computer vision and intelligent systems, convolutional neural networks (CNNs) have more popular architectures, and their performance is excellent in many applications. In this paper, fuzzy-based CNN image classification methods are analyzed, and an interval type-2 fuzzy-based CNN is proposed. The experimental results indicated that the performance of the proposed method was good.

Keywords: CNN, FCNN, Fuzzy logic, Interval type-2 fuzzy logic, Feature extraction, Computer vision, Image classification

Fig 1.

Figure 1.

Case of three kinds of fuzzy sets. A similar information p is applied to each fuzzy set. (a) T1FS, (b) IT2FS, and (c) T2FS.

The International Journal of Fuzzy Logic and Intelligent Systems 2020; 20: 336-345https://doi.org/10.5391/IJFIS.2020.20.4.336

Fig 2.

Figure 2.

Perspective on the secondary membership functions (three dimensions) initiated by an information p for (a) T1FS, (b) IT2FS, and (c) T2FS.

The International Journal of Fuzzy Logic and Intelligent Systems 2020; 20: 336-345https://doi.org/10.5391/IJFIS.2020.20.4.336

Fig 3.

Figure 3.

Structure of a convolutional neural network (CNN).

The International Journal of Fuzzy Logic and Intelligent Systems 2020; 20: 336-345https://doi.org/10.5391/IJFIS.2020.20.4.336

Fig 4.

Figure 4.

Outline of the proposed method IT2FCNN.

The International Journal of Fuzzy Logic and Intelligent Systems 2020; 20: 336-345https://doi.org/10.5391/IJFIS.2020.20.4.336

Fig 5.

Figure 5.

Performance comparison analysis for Dog vs. Cat with fine tuning epochs 3 (a), fine tuning epochs 5 (b), and fine tuning epochs 7 (c).

The International Journal of Fuzzy Logic and Intelligent Systems 2020; 20: 336-345https://doi.org/10.5391/IJFIS.2020.20.4.336

Table 1 . Performance comparison analysis with various fine tuning epochs (3, 5, and 7).

ModelFine tuning epochsDog Vs CatLion Vs TigerHorse Vs Donkey



RegularFCNN model 1FCNN model 2IT2FCNNRegularFCNN model 1FCNN model 2IT2FCNNRegularFCNN model 1FCNN model 2IT2FCNN
AlexNet34054585860586064
5516061656164656860626468
7546568726668727465687174

ZFNet3415356615658616453586164
5536261656263656862646870
7546467736869737664697276

GoogLeNet3425657615861616456616464
5546164686468687261687073
7576870746870747868707478

VGGNet163445857615857616558576265
5536264686466687262666972
7557072767072767870727478

ResNet503435656635961636556616465
5546162676362676961626569
7566971786872767969727479

Table 2 . Comparison of FCNN models with IT2FCNN based on MSE and RMSE.

ModelsMSERMSEMAPE
AlexNet
 FCNN Model 1.00245.0524.4
 FCNN Model 2.00183.0433.2
 IT2FCNN.00123.0352.4

ZFNet
 FCNN Model 1.00254.0544.2
 FCNN Model 2.00143.0453.1
 IT2FCNN.00134.0372.1

GoogLeNet
 FCNN Model 1.00249.0534.2
 FCNN Model 2.00197.0413.2
 IT2FCNN.00123.0362.0

VGGNet16
 FCNN Model 1.00244.0564.2
 FCNN Model 2.00158.0473.0
 IT2FCNN.00198.0392.2

ResNet50
 FCNN Model 1.00268.0584.1
 FCNN Model 2.00139.0463.1
 IT2FCNN.00132.0372.1

Share this article on :

Related articles in IJFIS

Most KeyWord