Abstract
In this paper methodologies are proposed to estimate the number of hidden neurons that are to be placed numbers in the hidden layer of artificial neural networks (ANN) and certain new criteria are evolved for fixing this hidden neuron in multilayer perceptron neural networks. On the computation of the number of hidden neurons, the developed neural network model is applied for wind speed forecasting application. There is a possibility of over fitting or under fitting occurrence due to the random selection of hidden neurons in ANN model and this is addressed in this paper. Contribution is done in developing various 151 different criteria and the evolved criteria are tested for their validity employing various statistical error means. Simulation results prove that the proposed methodology minimized the computational error and enhanced the prediction accuracy. Convergence theorem is employed over the developed criterion to validate its applicability for fixing the number of hidden neurons. To evaluate the effectiveness of the proposed approach simulations were carried out on collected real-time wind data. Simulated results confirm that with minimum errors the presented approach can be utilized for wind speed forecasting. Comparative analysis has been performed for the estimation of the number of hidden neurons in multilayer perceptron neural networks. The presented approach is compact, enhances the accuracy rate with reduced error and faster convergence.
Similar content being viewed by others
References
Arai M (1993) Bounds on the number of hidden units in binary-valued three-layer neural networks. Neural Netw 6:855–860
Choi B, Lee J-H, Kim D-H (2008) Solving local minima problem with large number of hidden nodes on two layered feed forward artificial neural networks. Neurocomputing 71:3640–3643
Dass HK (2009) Advanced engineering mathematics, 1st edn 1988. S. CHAND & Company Ltd, New Delhi
Doukin CA, Dargham JA, Chekima A (2010) Finding the number of hidden neurons for an MLP neural network using coarse to fine search technique. In: 10th International conference on information sciences signal processing and their applications (ISSPA), pp 606–609
Fujita O (1998) Statistical estimation of the number of hidden units for feed forward neural network. Neural Netw 11:851–859
Gnana Sheela K, Deepa SN (2013) Review on methods to fix number of hidden neurons in neural networks. Math Probl Eng 2013:1–11
Hagiwara M (1994) A simple and effective method for removal of hidden units and weights. Neuro Comput 6:207–218
Han M, Yin J (2008) The hidden neurons selection of the wavelet networks using support vector machines and ridge regression. Neuro Comput 72:471–479
Huang G-B (2003) Learning capability and storage capacity of two-hidden layer feed forward networks. IEEE Trans Neural Netw 14:274–281
Huang S-C, Huang Y-F (1991) Bounds on the number of hidden neurons in multilayer perceptrons. IEEE Trans Neural Netw 2:47–55
Hunter D, Hao Y, Pukish III MS, Kolbusz J, Wilamowski BM (2012) Selection of proper neural network sizes and architecture—a comparative study. IEEE Trans Ind Inf 8:228–240
Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667):78–80
Jiang N, Zhang Z, Ma X, Wang J (2008) The lower bound on the number of hidden neurons in multi-valued multi threshold neural networks. In: Second international symposium on intelligent information technology application, vol 1, pp 103–107
Karsoliya S (2012) Approximating number of hidden layer neuron in multiple hidden layer BPNN architecture. Int J Eng Trends Technol 31:714–717
Keeni K, Nakayama K, Shimodaira H (1999) Estimation of initial weights and hidden units for fast learning of multilayer neural networks for pattern classification. In: International joint conference on neural networks, vol 3, pp 1652–1656
Ke J, Liu X (2008) Empirical analysis of optimal hidden neurons in neural network modeling for stock prediction. In: Pacific-Asia workshop on computational intelligence and industrial application, vol 2, pp 828–832
Li J-Y, Chow TWS, Yu Y-L (1995) The estimation theory and optimization algorithm for the number of hidden units in the higher-order feed forward neural network. In: Proceeding IEEE international conference on neural networks, vol 3, pp 1229–1233
Li J, Zhang B, Mao C, Xie G, Li Y, Lu J (2010) Wind speed prediction based on the Elman recursion neural networks. In: International conference on modelling, identification and control, pp 728–732
Madhiarasan M, Deepa SN (2016) A novel criterion to select hidden neuron numbers in improved back propagation networks for wind speed forecasting. Appl Intell 44(4):878–893
Mao KZ, Huang G-B (2005) Neuron selection for RBF neural network classifier based on data structure preserving criterion. IEEE Trans Neural Netw 16:1531–1540
Meng A, Ge J, Yin H, Chen S (2016) Wind speed forecasting based on wavelet packet decomposition and artificial neural networks trained by crisscross optimization algorithm. Energy Convers Manag 114:75–88
Morris AJ, Zhang J (1998) A sequential learning approach for single hidden layer neural network. Neural Netw 11:65–80
Murata N, Yoshizawa S, Amari S-I (1994) Network information criterion determining the number of hidden units for an artificial neural network model. IEEE Trans Neural Netw 5:865–872
Onoda T (1995) Neural network information criterion for the optimal number of hidden units. In: Proceeding IEEE international conference on neural networks, vol 1, pp 275–280
Panchal G, Ganatra A, Kosta YP, Panchal D (2011) Behaviour analysis of multilayer perceptrons with multiple hidden neurons and hidden layers. Int J Comput Theory Eng 3:332–337
Peter SE, Kulkarni S, Raglend IJ, Simon SP (2013) Wavelet based spike propagation neural network (WSPNN) for wind power forecasting. Int Rev Model Simul (IREMOS) 6(5):1513–1522
Qian G, Yong H (2013) Forecasting the rural per capita living consumption based on Matlab BP neural network. Int J Bus Soc Sci 4:131–137
Ramadevi R, Sheela Rani B, Prakash V (2012) Role of hidden neurons in an Elman recurrent neural network in classification of cavitation signals. Int J Comput Appl 37:9–13
Shibata K, Ikeda Y (2009) Effect of number of hidden neurons on learning in large-scale layered neural networks. In: ICROS-SICE international joint conference, pp 5008–5013
Sivanandam SN, Sumathi S, Deepa SN (2008) Introduction to neural networks using Matlab 6.0, 1st edn. Tata McGraw Hill, New Delhi
Sun J (2012) Learning algorithm and hidden node selection scheme for local coupled feed forward neural network classifier. Neuro Comput 79:158–163
Tamura S, Tateishi M (1997) Capabilities of a four-layered feed forward neural network: four layer versus three. IEEE Trans Neural Netw 8:251–255
Teoh EJ, Tan KC, Xiang C (2006) Estimating the number of hidden neurons in a feed forward network using the singular value decomposition. IEEE Trans Neural Netw 17:1623–1629
Trenn S (2008) Multilayer perceptrons: approximation order and necessary number of hidden units. IEEE Trans Neural Netw 19:836–844
Urolagin S, Prema KV, Subba Reddy NV (2012) Generalization capability of artificial neural network incorporated with pruning method. Lect Notes Comput Sci 7135:171–178
Vora K, Yagnik S (2014) A new technique to solve local minima problem with large number of hidden nodes on feed forward neural network. Int J Eng Dev Res 2:1978–1981
Wang J, Hu J (2015) A robust combination approach for short-term wind speed forecasting and analysis—combination of the ARIMA (autoregressive integrated moving average), ELM (extreme learning machine), SVM (support vector machine) and LSSVM (least square SVM) forecasts using a GPR (Gaussian process regression) model. Energy 93:41–56
Xu S, Chen L (2008) A novel approach for determining the optimal number of hidden layer neurons for FNN’s and its application in data mining. In: 5th International conference on information technology and application (ICITA), pp 683–686
Yuan HC, Xiong FL, Huai XY (2003) A method for estimating the number of hidden neurons in feed-forward neural networks based on information entropy. Comput Electron Agric 40:57–64
Zeng X, Yeung DS (2006) Hidden neuron purning of multilayer perceptrons using a quantified sensitivity measure. Neuro Comput 69:825–837
Zhang Z, Ma X, Yang Y (2003) Bounds on the number of hidden neurons in three-layer binary neural networks. Neural Netw 16:995–1002
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Considers the applicability of different criteria with ‘n’ as input parameters. All developed criteria should satisfy the convergence theorem. If the limit of a sequence is finite, the sequence is called a convergent sequence. If the limit of a sequence does not tend to be a finite number, the sequence is called divergent (Dass 2009).
The convergence theorem characteristics are given below.
-
1.
A convergent sequence has a finite limit.
-
2.
All convergent sequences are bounded sequence.
-
3.
All bounded point has a finite limit.
-
4.
Convergent sequence needed condition is that it has finite limit and is bounded.
-
5.
An oscillatory sequence does not tend to have a unique limit.
In a network there is no change occurring in the state of the network, regardless of the operation is called the stable network. For neural network model most important property is it always converges to a stable state. In real-time optimization problem the convergence plays a major role, the risk of getting stuck at some local minima problem in a network is prevented by the convergence. The convergence of sequence infinite has been established in convergence theorem because of the discontinuities in the model. The real-time neural optimization solvers are designed with the use of convergence properties.
Presenting the convergence of the considered sequence as follows,
Apply convergence theorem,
Hence, the terms of a sequence have a finite limit value and are bounded so the considered sequence is convergent sequence.
Apply convergence theorem,
Hence, the terms of a sequence have a finite limit value and are bounded so the considered sequence is convergent sequence.
Rights and permissions
About this article
Cite this article
Madhiarasan, M., Deepa, S.N. Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting. Artif Intell Rev 48, 449–471 (2017). https://doi.org/10.1007/s10462-016-9506-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-016-9506-6