An approach to improve functional link neural network training using modified artificial bee colony for classification task

Classification is one of the most frequent studies in the area of Artificial Neural Network (ANNs) . One of the best known types of ANNs is the Multilayer Perceptron (MLP). However, MLP usually requires a rather large amount of available measures in order to achieve good classification accuracy. To overcome this, a Functional Link Neural Networks (FLNN), which has single layer of trainable connection weight is used. The standard method for tuning the weight in FLNN is using a Backpropagation (BP) learning algorithm. Still, BP-learning algorithm has difficulties such as trapping in local optima and slow convergence especially for solving non-linearly separable classification problems. In this paper, a modified Artificial Bee Colony (mABC) is used to recover the BP drawbacks. With modifications on the employed bee’s exploitation phase, the implementation of the mABC as a learning scheme for FLNN has given a better accuracy result for the classification tasks.

[1]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[2]  Sung-Bae Cho,et al.  A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN , 2010, Neural Computing and Applications.

[3]  B. B. Misra,et al.  Functional Link Artificial Neural Network for Classification Task in Data Mining , 2007 .

[4]  Dervis Karaboga,et al.  Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks , 2007, MDAI.

[5]  Yoh-Han Pao,et al.  Unconstrained word-based approach for off-line script recognition using density-based random-vector functional-link net , 2000, Neurocomputing.

[6]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[7]  Rozaida Ghazali,et al.  Training a Functional Link Neural Network Using an Artificial Bee Colony for Solving a Classification Problems , 2012, ArXiv.

[8]  Hantian Wu,et al.  A Combined Neural Network Approach to Soccer Player Prediction , 2015 .

[9]  José A. Macías,et al.  Evolution of functional link networks , 2001, IEEE Trans. Evol. Comput..

[10]  Jagdish Chandra Patra,et al.  Nonlinear dynamic system identification using Legendre neural network , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[11]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[12]  Ganapati Panda,et al.  Development and performance evaluation of FLANN based model for forecasting of stock markets , 2009, Expert Syst. Appl..

[13]  Jagdish C. Patra,et al.  A functional link artificial neural network for adaptive channel equalization , 1995, Signal Process..

[14]  Rozaida Ghazali,et al.  Using Artificial Bee Colony to Improve Functional Link Neural Network Training , 2012 .

[15]  Alex ChiChung Kot,et al.  Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[16]  Sung-Bae Cho,et al.  Evolutionarily optimized features in functional link neural network for classification , 2010, Expert Syst. Appl..

[17]  Hazem M. Abbas.  System Identification Using Optimally Designed Functional Link Networks via a Fast Orthogonal Search Technique , 2009, J. Comput..

[18]  C PatraJagdish,et al.  A functional link artificial neural network for adaptive channel equalization , 1995 .

[19]  Bernard Widrow,et al.  Neural networks: applications in industry, business and science , 1994, CACM.

[20]  F. Amar,et al.  Image classification in remote sensing using functional link neural networks , 1994, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation.

[21]  Joost N. Kok,et al.  Finding Functional Links for Neural Networks by Evolutionary Computation , 2007 .

[22]  Dervis Karaboga,et al.  AN IDEA BASED ON HONEY BEE SWARM FOR NUMERICAL OPTIMIZATION , 2005 .

[23]  Abir Jaafar Hussain,et al.  Dynamic Ridge Polynomial Neural Network: Forecasting the univariate non-stationary and stationary trading signals , 2011, Expert Syst. Appl..

[24]  Sung-Bae Cho,et al.  Genetic Feature Selection for Optimal Functional Link Artificial Neural Network in Classification , 2008, IDEAL.

[25]  Joost N. Kok,et al.  Feature Selection for Neural Networks through Functional Links Found by Evolutionary Computation , 1997, IDA.

[26]  Bayya Yegnanarayana,et al.  A combined neural network approach for texture classification , 1995, Neural Networks.

[27]  Issam Abu-Mahfouz,et al.  A comparative study of three artificial neural networks for the detection and classification of gear faults , 2005, Int. J. Gen. Syst..

[28]  Y.-H. Pao,et al.  The functional link net in structural pattern recognition , 1990, IEEE TENCON'90: 1990 IEEE Region 10 Conference on Computer and Communication Systems. Conference Proceedings.

[29]  Dervis Karaboga,et al.  Artificial Bee Colony (ABC) Optimization Algorithm for Solving Constrained Optimization Problems , 2007, IFSA.

[30]  Y. Takefuji,et al.  Functional-link net computing: theory, system architecture, and functionalities , 1992, Computer.