Fuzzy Adaptation for Particle Swarm Optimization for Modular Neural Networks Applied to Iris Recognition

被引：1

作者：

Sanchez, Daniela ^{[1
]}

Melin, Patricia ^{[1
]}

Castillo, Oscar ^{[1
]}

机构：

[1] Tijuana Inst Technol, Tijuana, Mexico

来源：

FUZZY LOGIC IN INTELLIGENT SYSTEM DESIGN: THEORY AND APPLICATIONS | 2018年 / 648卷

关键词：

HYBRID INTELLIGENT SYSTEM; ALGORITHM;

D O I：

10.1007/978-3-319-67137-6_11

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper a new Modular Neural Network (MNN) optimization is proposed, where a particle swarm optimization with a fuzzy dynamic parameter adaptation designs optimal MNNs architectures. This design consists in to find the number of hidden layers for each sub module with their respective number of neurons, learning method, error goal and the percentage of data used for the training phase. The proposed method is applied to pattern recognition based on the iris biometrics and has as objective function to minimize the error of recognition. The proposed fuzzy adaptation seeks to avoid stagnation of error of recognition during iterations updating some PSO parameters such as w, C-1 and C-2.

引用

页码：104 / 114

页数：11

共 50 条

[31] The optimal combination: Grammatical swarm, particle swarm optimization and neural networks
de Mingo Lopez, Luis Fernando
Gomez Blas, Nuria
Arteta, Alberto
JOURNAL OF COMPUTATIONAL SCIENCE, 2012, 3 (1-2) : 46 - 55
[32] Application of Particle Swarm Optimization in Fussy Neural Networks
Wang, Qingnian
Yan, Kun
Wan, Xiaofeng
Yuan, Meiling
FIFTH INTERNATIONAL CONFERENCE ON INFORMATION ASSURANCE AND SECURITY, VOL 1, PROCEEDINGS, 2009, : 158 - 161
[33] Training Neural Networks by Continuation Particle Swarm Optimization
Rojas-Delgado, Jairo
Trujillo-Rasua, Rafael
PROGRESS IN ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION, IWAIPR 2018, 2018, 11047 : 59 - 67
[34] Iris recognition using curvelet transform and accuracy maximization by particle swarm optimization
Ahamed, Afsana
Meerza, Syed Irfan Ali
2022 IEEE WESTERN NEW YORK IMAGE AND SIGNAL PROCESSING WORKSHOP (WNYISPW), 2022,
[35] Iris secondary recognition based on decision particle swarm optimization and stable texture
Liu Y.-N.
Liu S.
Zhu X.-D.
Huo G.
Ding T.
Zhang K.
Jiang X.
Guo S.-J.
Zhang Q.-X.
Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2019, 49 (04): : 1329 - 1338
[36] A New Adaptation of Particle Swarm Optimization Applied to Modern FPGA Placement
Zhou, Yun
Vercruyce, Dries
Stroobandt, Dirk
2019 16TH INTERNATIONAL CONFERENCE ON SYNTHESIS, MODELING, ANALYSIS AND SIMULATION METHODS AND APPLICATIONS TO CIRCUIT DESIGN (SMACD 2019), 2019, : 141 - 144
[37] A Modified Particle Swarm Optimization Procedure for Triggering Fuzzy Flip-Flop Neural Networks
Kowalski, Piotr A.
Sloczynski, Tomasz
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2021, 31 (04) : 577 - 586
[38] Integration of fuzzy logic, particle swarm optimization and neural networks in quality assessment of construction project
Shi H.
Li W.
Journal of Software, 2010, 5 (07) : 737 - 744
[39] An Improved Quantum-Behaved Particle Swarm Optimization Algorithm for Training Fuzzy Neural Networks
Chiang, Cheng-Hsiung
2013 INTERNATIONAL CONFERENCE ON FUZZY THEORY AND ITS APPLICATIONS (IFUZZY 2013), 2013, : 358 - 363
[40] Hierarchical Fuzzy Clustering in Conjunction with Particle Swarm Optimization to Efficiently Design RBF Neural Networks
Niros, Antonios D.
Tsekouras, George E.
Tsolakis, Dimitrios
Manousakis-Kokorakis, Andreas
Kyriazis, Dimosthenis
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2015, 78 (01) : 105 - 125

← 1 2 3 4 5 →