TITLE

A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN

AUTHOR(S)
Dehuri, Satchidananda; Cho, Sung-Bae
PUB. DATE
March 2010
SOURCE
Neural Computing & Applications;Mar2010, Vol. 19 Issue 2, p187
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
Functional link neural network (FLNN) is a class of higher order neural networks (HONs) and have gained extensive popularity in recent years. FLNN have been successfully used in many applications such as system identification, channel equalization, short-term electric-load forecasting, and some of the tasks of data mining. The goals of this paper are to: (1) provide readers who are novice to this area with a basis of understanding FLNN and a comprehensive survey, while offering specialists an updated picture of the depth and breadth of the theory and applications; (2) present a new hybrid learning scheme for Chebyshev functional link neural network (CFLNN); and (3) suggest possible remedies and guidelines for practical applications in data mining. We then validate the proposed learning scheme for CFLNN in classification by an extensive simulation study. Comprehensive performance comparisons with a number of existing methods are presented.
ACCESSION #
48464177

 

Related Articles

  • An Improved Particle Swarm Optimization. Wenjuan Zeng; Haibo Gao; Wang Jing // Information Technology Journal;2014, Vol. 13 Issue 16, p2560 

    The basic and improved algorithms of PSO are focused on how to search effectively the optimalsolution in the solution space by using one of the particle swarm. However, the particles are always chasing the global optimal point and such points are currently found on their way of search, rapidly...

  • Research on The Network Optimization Method Based on Improved Particle Swarm Algorithm. Tian Jifeng // Journal of Convergence Information Technology;Mar2013, Vol. 8 Issue 6, p393 

    The paper studied the BP neural network optimization issue of particle swarm algorithm according to psychology and cognitive science theories. We apply the improved particle swarm algorithm into BP neural network learning and training and compare the learning capacity of it with that of...

  • The Research of Temperature Compensation for Thermopile Sensor Based on Improved PSO-BP Algorithm. Li, Yuanjiang; Li, Yuehua; Li, Feng; Zhao, Bin; Li, QingQing // Mathematical Problems in Engineering;8/13/2015, Vol. 2015, p1 

    When thermopile sensor is used for safety monitoring of equipment in industrial environments, particularly for measuring the thermal radiation information of device, the measured result of this kind of sensor is usually affected by ambient temperature due to its unique structure. An improved...

  • Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms. Garro, Beatriz A.; Vázquez, Roberto A. // Computational Intelligence & Neuroscience;6/29/2015, Vol. 2015, p1 

    Artificial Neural Network (ANN) design is a complex task because its performance depends on the architecture, the selected transfer function, and the learning algorithm used to train the set of synaptic weights. In this paper we present a methodology that automatically designs an ANN using...

  • The Quantitative Metallogenic Prediction Model based on PSO-BP algorithm and Fuzzy Neural Network. Zhenwu WANG; Xuejun Zhao // International Journal of Advancements in Computing Technology;Mar2013, Vol. 5 Issue 5, p32 

    This paper proposed a quantitative metallogenic prediction method which based on PSO-BP algorithm and fuzzy neural network. The method used PSO-BP algorithm to train and optimize the weights of prediction quotas and adopted fuzzy neural network to compute the prediction grades, which describe...

  • The Application of DPSO - BP Neural Network in GIS Partial Discharge Typical Defects Recognition. Zekun Liu; Hong Yu; Tieqiao Guo; Chenglong XU; Zhiwang Cheng // Advanced Materials Research;2014, Issue 889-890, p1078 

    The BP neural network is a classifier commonly used in partial discharge type recognition, but the traditional BP algorithm with defects cannot satisfy the actual need. So the optimization algorithm of BP network was studied intensively. DPSO algorithm was used for optimizing the network, and...

  • An Efficient and Improved Artificial Neural Network Algorithm to Solve Unit Commitment Problem with Cooling Banking Constraints. Singh, R. Lal Raja; Rajan, C. Christober Asir // European Journal of Scientific Research;10/9/2011, Vol. 61 Issue 4, p561 

    In power systems, unit commitment problem refers to the optimal commitment of the given generator units so as to satisfy the demand of the given time horizon with minimum cost. As the demand varies day by day, the requirement of more effective optimal solution for the problem gains significance....

  • A combination of Genetic Algorithm, Particle Swarm Optimization and Neural Network for palmprint recognition. Altun, Adem // Neural Computing & Applications;May2013 Supplement, Vol. 22, p27 

    In this study, a new approach to the palmprint recognition phase is presented. 2D Gabor filters are used for feature extraction of palmprints. After Gabor filtering, standard deviations are computed in order to generate the palmprint feature vector. Genetic Algorithm-based feature selection is...

  • Development of Neural Networks for Noise Reduction. Badri, Lubna // International Arab Journal of Information Technology (IAJIT);Jul2010, Vol. 7 Issue 3, p289 

    This paper describes the development of neural network models for noise reduction. The networks used to enhance the performance of modeling captured signals by reducing the effect of noise. Both recurrent and multi-layer Back propagation neural networks models are examined and compared with...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics