Predictions of bridge scour: Application of a feed-forward neural network with an adaptive activation function

In this study, a new procedure to determine the optimum activation function for a neural network is proposed. Unlike previous methods of optimising activation functions, the proposed approach regards selection of the most suitable activation function as a discrete optimisation problem, which involves generating various combinations of function then evaluating their performance as activation functions in a neural network, returning the function or combination of functions which yields best result as the optimum. The efficacy of the proposed optimisation method is compared with conventional approaches using the data generated from several synthetic functions. Numerical results indicate that the network produced using the proposed method achieves a better accuracy with a smaller network size, compared to other approaches. Bridge scour problem is used to further demonstrate the performance of the proposed algorithm. Based on the training and validation results, a better estimation of both equilibrium and time dependent scour depth is produced by the neural network developed using the proposed optimisation method, compared to networks with a priori chosen activation functions. Furthermore, the performance of the proposed model is compared with predictions of empirical methods, with the former making more accurate predictions.

[1]  Dong-Sheng Jeng,et al.  Bayesian neural networks for prediction of equilibrium and time-dependent scour depth around bridge piers , 2007, Adv. Eng. Softw..

[2]  C. Veṅkaṭādri,et al.  Scour Around Bridge Piers and Abutments , 1965 .

[3]  Sydney Nsw,et al.  Neural Network assessment for scour depth around bridge piers , 2006 .

[4]  Timothy Masters,et al.  Multilayer Feedforward Networks , 1993 .

[5]  W. Hager,et al.  Temporal Evolution of Clear-Water Pier and Abutment Scour , 2002 .

[6]  Ashish Kumar,et al.  TEMPORAL VARIATION OF SCOUR AROUND CIRCULAR BRIDGE PIERS , 2010 .

[7]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[8]  J. Sopena,et al.  Neural networks with periodic and monotonic activation functions: a comparative study in classification problems , 1999 .

[9]  D. Jeng,et al.  Estimation of pile group scour using adaptive neuro-fuzzy approach , 2007 .

[10]  Holger R. Maier,et al.  DATA DIVISION FOR DEVELOPING NEURAL NETWORKS APPLIED TO GEOTECHNICAL ENGINEERING , 2004 .

[11]  S. M. Bateni,et al.  Neural network and neuro-fuzzy assessments for scour depth around bridge piers , 2007, Eng. Appl. Artif. Intell..

[12]  Francesco Piazza,et al.  Multilayer feedforward networks with adaptive spline activation function , 1999, IEEE Trans. Neural Networks.

[13]  Abidin Kaya,et al.  Artificial neural network study of observed pattern of scour depth around bridge piers , 2010 .

[14]  Bin-Da Liu,et al.  An adaptive activation function for multilayer feedforward neural networks , 2002, 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering. TENCOM '02. Proceedings..

[15]  Yilong Hao,et al.  The performance of the backpropagation algorithm with varying slope of the activation function , 2009 .

[16]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[17]  Bruce W. Melville,et al.  SCALE EFFECT IN PIER-SCOUR EXPERIMENTS. TECHNICAL NOTE , 1998 .

[18]  Mahmud Güngör,et al.  Generalized Regression Neural Networks and Feed Forward Neural Networks for prediction of scour depth around bridge piers , 2009, Adv. Eng. Softw..

[19]  C. Leung,et al.  Use of periodic and monotonic activation functions in multilayer feedforward neural networks trained by extended Kalman filter algorithm , 2002 .

[20]  B. Melville,et al.  TIME SCALE FOR LOCAL SCOUR AT BRIDGE PIERS , 2000 .

[21]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[22]  Ming Zhang,et al.  Justification of a neuron-adaptive activation function , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[23]  Stanley R. Davis,et al.  Evaluating scour at bridges. , 1995 .

[24]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[25]  Francesco Piazza,et al.  Learning and Approximation Capabilities of Adaptive Spline Activation Function Neural Networks , 1998, Neural Networks.

[26]  Duc Truong Pham,et al.  Adaptive control of dynamic systems using neural networks , 1993, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.