Skip to main content

Advertisement

SpringerLink
Log in

Input-dependent neural network trained by real-coded genetic algorithm and its industrial applications

  • Original Paper
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

This paper presents an input-dependent neural network (IDNN) with variable parameters. The parameters of the neurons in the hidden nodes adapt to changes of the input environment, so that different test input sets separately distributed in a large domain can be tackled after training. Effectively, there are different individual neural networks for different sets of inputs. The proposed network exhibits a better learning and generalization ability than the traditional one. An improved real-coded genetic algorithm (RCGA) Ling and Leung (Soft Comput 11(1):7–31, 2007) is proposed to train the network parameters. Industrial applications on short-term load forecasting and hand-written graffiti recognition will be presented to verify and illustrate the improvement.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aggarwal R, Song YH (1998) Artificial neural networks in power systems. Power Eng J, pp 279–287

  • Buse R, Liu ZQ, Bezdek J (2002) Word recognition using fuzzy logic. IEEE Trans Fuzzy Syst 10(1):65–76

    Article  Google Scholar 

  • Charytoniuk W, Chen MS (2000) Very short-term load forecasting using artificial neural networks. IEEE Trans Power Syst 15(1):263–268

    Article  Google Scholar 

  • Daubechies I (1990) The wavelet transform, time-frequency localization and signal analysis. IEEE Trans Inf Theory 36(5):961–1005

    Article  MATH  MathSciNet  Google Scholar 

  • Davis L (1991) Handbook of genetic algorithms. Van Nostrand Reinhold, New York

    Google Scholar 

  • Drezga I, Rahman S (1999) Short-term load forecasting with local ANN predictors. IEEE Trans Power Syst 14(3):844–850

    Article  Google Scholar 

  • Fieldsend JE, Singh S (2005) Pareto evolutionary neural networks. IEEE Trans Neural Netw 16(2):338–354

    Article  Google Scholar 

  • Gader PD, Khabou MA (1996) Automatic feature generation for handwritten digit recognition. IEEE Trans Pattern Anal Mach Intell 18(12):1256–1261

    Article  Google Scholar 

  • Garcia-Pedrajas N, Hervas-Martinez C, Munoz-Perez J (2003) COVNET: a cooperative coevolutionary model for evolving artificial neural networks. IEEE Trans Neural Netw 14(3): 575–596

    Article  Google Scholar 

  • Gross G, Galiana FD (1987) Short-term load forecasting. IEEE Proc 75:1558–1573

    Article  Google Scholar 

  • Ham FM, Kostanic I (2001) Principles of neurocomputing for science & engineering. McGraw-Hill, New York

    Google Scholar 

  • Haykin S (1999) Neural network: a comprehensive foundation. Prentice Hall, Englewood Cliffs

    MATH  Google Scholar 

  • Heng ETH, Srinivasan D, Liew AC (1988) Short term load forecasting using genetic algorithm and neural networks. In: Proceedings of the 1998 international conference on energy management and power delivery, vol 2, pp 576–581

  • Holland JH (1975) Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor

    Google Scholar 

  • Holmström L, Koistinen P, Laaksonen J, Oja E (1997) Neural and statistical classifiers—taxonomy and two case studies. IEEE Trans Neural Netw 8(1):5–17

    Article  Google Scholar 

  • Hsu CC, Chen CY (2003) Regional load forecasting in Taiwan–applications of artificial neural networks. Energy Convers Manage 44:1941–1949

    Article  Google Scholar 

  • Joines J, Houck C (1994) On the use of non-stationary penalty functions to solve constrained optimization problems with genetic algorithm. In: Proceedings of the 1994 international symposium evolutionary computation, Orlando, pp 579–584

  • Kecman V (2001) Learning and soft computing, support vector machines, neural networks and fuzzy logic models. The MIT Press, Cambridge

    MATH  Google Scholar 

  • Lam HK, Leung FHF (2004) Stability analysis, synthesis and optimization of radial-basis-function neural-network based controller for nonlinear systems. In: Proceedings of the 30th Annual Conference of the IEEE Industrial Electronics Society, IECON, Busan, Korea, pp 2813–2818

  • Lam HK, Leung FHF (2006) Design and stabilization of sampled-data neural-network-based control systems. IEEE Trans Syst Man Cybern B Cybern 36(5):995–1005

    Article  MathSciNet  Google Scholar 

  • Lam HK , Ling SH, Leung FHF, Tam PKS (2004) Function estimation using a neural-fuzzy network and an improved genetic algorithm. Int J Approx Reason 30(3):243–260

    Article  Google Scholar 

  • Leung FHF, Lam HK, Ling SH, Tam PKS (2003) Tuning of the structure and parameters of neural network using an improved genetic algorithm. IEEE Trans Neural Netw 14(1):79–88

    Article  Google Scholar 

  • Leung KF, Leung FHF, Lam HK, Ling SH (2004) On interpretation of graffiti digits and characters for eBooks: neural-fuzzy network and genetic algorithm approach. IEEE Trans Ind. Electron 51(2):464–471

    Article  Google Scholar 

  • Liang RH, Cheng CC (2002) Short-term load forecasting by a neuro-fuzzy based approach. Energy Power Energy Syst 24:103–111

    Article  Google Scholar 

  • Ling SH, Leung FHF (2007) An improved genetic algorithm with average-bound crossover and wavelet mutation operations. Soft Comput 11(1):7–31

    Article  Google Scholar 

  • Ling SH, Leung FHF, Lam HK, Lee YS, Tam PKS (2003) A novel GA-based neural network for short-term load forecasting. IEEE Trans Ind Electron 50(4):793–799

    Article  Google Scholar 

  • Ling SH, Leung FHF, Wong LK, Lam HK (2005) Computational intelligence techniques for home electric load forecasting and balancing. Int J Comput Intell Appl 5(3):371–391

    Article  MATH  Google Scholar 

  • Lovell DR, Downs T, Tsoi AC (1997) An evaluation of the neocognitron. IEEE Trans Neural Netw 8(5):1090–1105

    Article  Google Scholar 

  • Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693

    Article  MATH  Google Scholar 

  • Michalewicz Z (1994) Genetic algorithm + data structures = evolution programs, 2nd extended edn. Springer, Berlin

    Google Scholar 

  • Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6(4):525–533

    Article  Google Scholar 

  • Momoh JA, Wang Y, Elfayoumy M (1997) Artificial neural network based load forecasting. In: Proceedings of the IEEE International Conference System, Man, and Cybernetics: Computational Cybernetics and Simulation, vol 4, pp 3443–3451

  • Perez CA, Salinas CA, Estévez PA, Valenzuela PM (2003) Genetic design of biologically inspired receptive fields for neural pattern recognition. IEEE Trans. Syst Man Cybern B Cybern 33(2):258–270

    Article  Google Scholar 

  • Pham DT, Karaboga D (2000) Intelligent optimization techniques, genetic algorithms, tabu search, simulated annealing and neural networks. Springer, Berlin

    Google Scholar 

  • Saksornchai T, Lee WJ, Methaprayoon K, Liao JR, Ross RJ (2005) Improve the unit commitment scheduling by using the neural-network-based short-term load forecasting. IEEE Trans Ind App 41(1):169–179

    Article  Google Scholar 

  • Senjyu T, Takara H, Funabashi T (2002) One-hour-ahead load forecasting using neural network. IEEE Trans Power Syst 17(1):113–118

    Article  Google Scholar 

  • Srinivas M, Patnaik LM (1994) Genetic algorithms: a survey. IEEE Comput 27(6):17–26

    Google Scholar 

  • Tan KC, Lim MH, Yao X, Wang LP (eds) Recent advances in simulated evolution and learning. World Scientific, Singapore

  • Taylor JW, Buizza R (2002) Neural network load forecasting with weather ensemble predictions. IEEE Trans Power Syst 17(4):626–632

    Article  Google Scholar 

  • Wang LP, Fu XJ (2005) Data mining with computational intelligence. Springer, Berlin

    MATH  Google Scholar 

  • Widrow B, Lehr MA (1990) 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proc IEEE 78(9):1415–1442

    Article  Google Scholar 

  • Yang KH, Zhu JJ, Wang BS, Zhao LL (2004) Design of short-term load forecasting model based on fuzzy neural networks. In: Proceedings of the 5th World Congress on Intelligent Control and Automation, vol 3, pp 15–19

  • Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447

    Article  Google Scholar 

  • Yao S, Wei CJ, He ZY (1996) Evolving wavelet neural networks for function approximation. Electron Lett 32(4):360–361

    Article  Google Scholar 

  • Zhang Q, Benveniste A (1992) Wavelet networks. IEEE Trans Neural Netw 3(6):889–898

    Article  Google Scholar 

  • Zhang B, Fu M, Yan H, Jabri MA (1997) Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM). IEEE Trans Neural Netw 10(4):939–945

    Article  Google Scholar 

  • Zhang J, Walter GG, Miao Y, Lee WWN (1995) Wavelet neural networks for function learning. IEEE Trans Signal Process 43(6):1485–1497

    Article  Google Scholar 

  • Zurada JM (1992) Introduction to artificial neural systems. West Info Access

Download references

Author information

Authors and Affiliations

  1. School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia

    S. H. Ling

  2. Centre for Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong

    F. H. F. Leung

  3. Division of Engineering, King’s College London, Strand, London, UK

    H. K. Lam

Authors
  1. S. H. Ling
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. F. H. F. Leung
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. H. K. Lam
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. H. Ling.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ling, S.H., Leung, F.H.F. & Lam, H.K. Input-dependent neural network trained by real-coded genetic algorithm and its industrial applications. Soft Comput 11, 1033–1052 (2007). https://doi.org/10.1007/s00500-007-0151-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-007-0151-5

Keywords

Search

Navigation