Abstract
The back-propagation network (BPN) is a popular tool with applications in a variety of fields. Nevertheless, different problems may require different parameter settings for a given network architecture. A dataset may contain many features, but not all features are beneficial for classification by the BPN. Therefore, a particle-swarm-optimization-based approach, denoted as PSOBPN, is proposed to obtain the suitable parameter settings for BPN and to select the beneficial subset of features which result in a better classification accuracy rate. A set of 23 problems with a range of examples and features drawn from the UCI (University of California, Irvine) machine learning repository is adopted to test the performance of the proposed algorithm. The results are compared with several well-known published algorithms. The comparative study shows that the proposed approach improves the classification accuracy rate in most test problems. Furthermore, when the feature selection is taken into consideration, the classification accuracy rates of most datasets are increased. The proposed algorithm should thus be useful to both practitioners and researchers.
Similar content being viewed by others
References
Abe N, Kudo M (2006) Non-parametric classifier-independent feature selection. Pattern Recognit 39: 737–746
Ahluwalia M, Bull L (1999) Coevolving functions in genetic programming: classification using k-nearest-neighbour, In: Banzhaf W, Daida J, Eiben G et al (eds) GECCO-99. In: Proceedings of the genetic and evolutionary computation conference. Morgan Kaufmann, Florida, pp 947–952
Barletta M, Gisario A, Guarino S (2007) Modeling of electrostatic fluidized bed (EFB) coating process using artificial neural networks. Eng Appl Artif Intell 20: 721–733
Berry MJA, Linoff G (eds) (2001) Data mining techniques: for marking, sales and customer support. Wiley, NY
Castillo PA, Carpio J, Merelo JJ et al (2000a) Evolving multilayer perceptrons. Neural Process Lett 12: 115–127
Castillo PA, Merelo JJ, Prieto A et al (2000b) G-prop: global optimization of multilayer perceptrons using GAs. Neurocomputing 35: 149–163
Chen W-C, Fu GL, Tai P-H et al (2009) Process parameter optimization for MIMO plastic injection molding via soft computing. Expert Syst Appl 36: 1114–1122
Choi YS (2001) Discovering text databases with neural nets. Knowl Inf Syst 3: 356–373
Danaher S, Datta S, Waddle I et al (2004) Erosion modeling using bayesian regulated artificial neural networks. Wear 256: 879–888
Dixon PW, Corne DW, Oates MJ (2002) A preliminary investigation of modified XCS as a generic data mining tool. In: Lanai PL, Stolzmann W, Wilson S (eds) Advertences in learning classifier systems. Springer, Berlin, pp 257–269
Ebrahimzadeh A, Ranjbar A (2008) Intelligent digital signal-type identification. Eng Appl Artif Intell 21: 569–577
Fung G, Mangasarian OL (2003) Finite Newton method for Lagrangian support vector machine classification. Neurocomputing 55: 39–55
Ghosh A, Jain LC (2004) Evolutionary computation in data mining. Springer, Germany
Ghosh R, Verma B (2003) A hierarchical method for finding optimal architecture and weights using evolutionary least square based learning. Int J Neural Syst 13: 13–24
Gupta JND, Sexton RS (1999) Comparing backpropagation with a genetic algorithm for neural network training. Int J Manag Sci 27: 679–684
Gusikhin O, Rychtyckyj N, Filev D (2007) Intelligent systems in the automotive industry: applications and trends. Knowl Inf Syst 12: 147–168
Han J, Kamber M (2007) Data mining: concepts and techniques. Morgan Kaufmann, San Francisco
He Q, Wang L (2007) An effective co-evolutionary particle swarm optimization for constrained engineering design problems. Eng Appl Artif Intell 20: 89–99
Heo G-S, Oh I-S (2008) Simultaneous node pruning of input and hidden layers using genetic algorithms. In: Proceedings of IEEE the seventh international conference on machine learning and cybernetics. pp 3428–3433
Hettich S, Blake CL, Merz CJ (1998) UCI repository of machine learning databases, Department of Information and Computer Sciences, University of California, Irvine, CA. http://www.ics.uci.edu/~mlearn/MLRepository.html
Hou T-H, Su C-H, Chang H-Z (2008) Using neural networks and immune algorithms to find the optimal parameters for an IC wire bonding process. Expert Syst Appl 34: 427–436
Huang C-Y, Chen L-H, Chen Y-L et al (2009) Evaluating the process of a genetic algorithm to improve the back-propagation network: a Monte Carlo study. Expert Syst Appl 36: 1459–1465
Javadi AA, Farmani R, Tan TP (2005) A hybrid intelligent genetic algorithm. Adv Eng Inform 19: 225–262
Karpenko M, Sepehri N (2002) Neural network classifiers applied to condition monitoring of a pneumatic process valve actuator. Eng Appl Artif Intell 15: 273–283
Kennedy J, Eberhart R (1995) Particle swarm optimization. Proc IEEE Conf Neural Netw 4: 1942–1948
Khaw JFC, Lim BS, Lim LEN (1995) Optimal design of neural networks using the Taguchi method. Neurocomputing 7: 225–245
Kim K-J, Han I (2000) Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Syst Appl 19: 125–132
Ko Y-D, Moon P, Kim CE et al (2009) Modeling and optimization of the growth rate for ZnO thin films using neural networks and genetic algorithms. Expert Syst Appl 36: 4061–4066
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97: 273–324
Kwok NM, Liu DK, Dissanayake G (2006) Evolutionary computing based mobile robot localization. Eng Appl Artif Intell 19: 857–868
Lee J, Kang S (2007) GA based meta-modeling of BPN architecture for constrained approximate optimization. Int J Solids Struct 44: 5980–5993
Lezoray O, Cardot H (2001) A neural network architecture for data classification. Int J Neural Syst 11: 33–42
Li S, Li Y, Liu Y et al (2007) A GA-based NN approach for makespan estimation. Appl Math Comput 185: 1003–1014
Li W-S, Clifton C, Liu S-Y (2000) Database integration using neural networks: implementation and experiences. Knowl Inf Syst 2: 73–96
Lin SC, Ting CJ (1996) Drill wear monitoring using neural networks. Int J Mach Tools Manuf 36: 465–475
Lin S-W, Tseng T-Y, Chou S-Y et al (2008) A simulated annealing based approach for simultaneous parameter optimization and feature selection of back-propagation networks. Expert Syst Appl 34: 1491–1499
Lin S-W, Lee Z-J, Chen S-C et al (2008) Parameter determination of support vector machines and feature selection using simulated annealing approach. Appl Soft Comput 8: 1505–1512
Lin S-W, Ying K-C, Chen S-C et al (2008) Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst Appl 35: 1817–1824
Lin S-W, Chou S-Y, Chen S-C (2007) Irregular shapes classification by back-propagation neural network. Int J Adv Manuf Technol 34: 1164–1172
Liu H, Motoda H (1998) Feature selection for knowledge discovery and data mining. Kluwer Academic, Boston
Liu L, Liu W, Cartes DA (2008) Particle swarm optimization-based parameter identification applied to permanent magnet synchronous motors. Eng Appl Artif Intell 21: 1092–1100
Mahesh Parappagoudar B, Pratihar DK, Datta GL (2008) Forward and reverse mappings in green sand mould system using neural networks. Appl Soft Comput 8: 239–260
Malhotra R, Malhotra DK (2003) Evaluating consumer loans using neural networks. Int J Manag Sci 31: 83–96
Mangasarian OL, Musicant DR (2001) Lagrangian support vector machine. J Mach Res 1: 161–177
Pudil P, Novovičová J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15: 1119–1125
Peng T, Zuo W, He F (2008) SVM based adaptive learning method for text classification from positive and unlabeled documents. Knowl Inf Syst 16: 281–301
Qiao W, Gao Z, Harley RG et al (2008) Robust neuro-identification of nonlinear plants in electric power systems with missing sensor measurements. Eng Appl Artif Intell 21: 604–618
Sasaki T, Tokoro M (2000) Comparison between Lamarckian and Darwinian evolution on a model using neural networks and genetic algorithms. Knowl Inf Syst 2: 201–222
Salzberg SL (1997) On comparing classifiers: pitfalls to avoid and a recommended approach. Data Min Knowl Discov 1: 317–327
Schittenkopf C, Deco G, Brauer W (1997) Two strategies to avoid overfitting in feedforward networks. Neural Netw 10: 505–516
Senthil Arumugam M, Rao MVC, Chandramohan A (2008) A new and improved version of particle swarm optimization algorithm with global-local best parameters. Knowl Inf Syst 16: 331–357
Sedki A, Ouazar D, El Mazoudi E (2009) Evolving neural network using real coded genetic algorithm for daily rainfall-runoff forecasting. Expert Syst Appl 36: 4523–4527
Sexton RS, Alidaee B, Dorsey RE et al (1998) Global optimization for artificial neural networks: a tabu search application. Eur J Oper Res 106: 570–584
Sexton RS, Dorsey RE, Johnson JD (1999) Optimization of neural networks: a comparative analysis of the genetic algorithm and simulated annealing. Eur J Oper Res 114: 589–601
Sexton RS, McMurtrey S, Cleavenger DJ (2006) Knowledge discovery using a neural network simultaneous optimization algorithm on a real world classification problem. Eur J Oper Res 168: 1009–1018
Shi Y, Eberhart R (1998) A modified particle swarm optimizer. In: Proceeding of the IEEE congress on Evolutionary Computation. pp 69–73
Shi Y, Eberhart R (1998) Parameter selection in particle swarm optimization. Lecture notes in computer science, vol 1447. pp 591–600
Sivagaminathan RK, Ramakrishnan S (2007) A hybrid approach for feature subset selection using neural networks and ant colony optimization. Expert Syst Appl 33: 49–60
Smith M, Bull L (2005) GAP: constructing and selection features with evolutionary computing. In: Ghosh A, Jain LC (eds) Evolutionary computation in data mining. Springer, Heidelberg
Srinivas V, Ramanjaneyulu K (2007) An integrated approach for optimum design of bridge decks using genetic algorithms and artificial neural networks. Adv Eng Softw 38: 475–487
Tsai C-Y, Chou S-Y, Lin S-W et al (2009) Location determination of mobile devices for an indoor WLAN application using a neural network. Knowl Inf Syst 20: 81–93
Verikas A, Bacauskiene M (2002) Feature selection with neural networks. Pattern Recognit Lett 23: 1323–1335
Wang G, Zhang C, Huang L (2008) A study of classification algorithm for data mining based on hybrid intelligent systems. In: Proceeding of IEEE Ninth ACIS international conference on software engineering, artificial intelligence, networking, and parallel/distributed computing. pp 371–375
Wang T-Y, Huang C-Y (2007) Applying optimized BPN to a chaotic time series problem. Expert Syst Appl 32: 193–200
Wang X, Wang W, Huang Y et al (2008) Design of neural network-based estimator for tool wear modeling in hard turning. J Intell Manuf 19: 383–396
Yamazaki A, de Souto MCP, Ludermir TB (2002) Optimization of neural network weights and architectures for odor recognition using simulated annealing. Proc IEEE Neural Netw 1: 547–552
Yan H, Jiang Y, Zheng J et al (2006) A multilayer perceptorn-based medical decision support system for heart disease diagnosis. Expert Syst Appl 30: 272–281
Yang J, Honavar V (1998) Feature subset selection using a genetic algorithm. IEEE Intell Syst 34: 44–49
Yeung DS, Zeng X-Q (2002) Hidden neuron pruning for multilayer perceptrons using a sensitivity measure. Proc IEEE Mach Learn Cybern 4: 1751–1757
Yu S, Zhu K, Diao F (2008) A dynamic all parameters adaptive BP neural networks model and its application on oil reservoir prediction. Appl Math Comput 195: 66–75
Yuen CWM, Wong WK, Qian SQ et al (2009) A hybrid model using genetic algorithm and neural network for classifying garment defects. Expert Syst Appl 36: 2037–2047
Zhang L, Jack LB, Nandi AK (2005) Fault detection using genetic programming. Mech Syst Signal Process 19: 271–289
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, SW., Chen, SC., Wu, WJ. et al. Parameter determination and feature selection for back-propagation network by particle swarm optimization. Knowl Inf Syst 21, 249–266 (2009). https://doi.org/10.1007/s10115-009-0242-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-009-0242-y