Two problems are analyzed in the paper: 1) prediction and identification of critical loads and concrete strength in compressed R/C columns, 2) identification of compaction characteristics in granular soils. The main goal of the paper is to compare the numerical efficiency of the Method of Gaussian Processes with the results obtained by means of other methods (Extended Back Propagation Neural Network, Semi Bayesian Neural Networks and Bayesian methods).
1. Waszczyszyn Z.: Artificial neural networks in civil and structural engineering: ten years of research in Poland. Computer Assisted Mech. and Eng. Sc., 13: 489-512, 2006.
2. Waszczyszyn Z.: Artificial neural networks in civil engineering: another five years of research in Poland. Computer Assisted Mech. and Eng. Sci., 18: 131-146, 2013.
3. Bishop C.M.: Pattern Recognition and Machine Learning. Springer Science & Business Media, LLC, 2006.
4. Nabney I. T.: NETLAB − Algorithms for Pattern Recognition. Springer, London, 2004.
5. http://www.ce.washinton.edu/peera1/, 2007.
6. Chudyba K.: The influence of material and geometric characteristics on the compressive load capacity of reinforced concrete columns (in Polish). Ph.D. Thesis, Cracow Univ. of Technology, 1999.
7. Jakubek M.: Neural network prediction of load carrying capacity for eccentrically loaded reinforced concrete columns. Computer Assisted Methods in Eng. and Sci., 19: 339-549, 2012.
8. Neural Network Toolbox for Use with MATLAB. User’s Guide, Version 3. The Math Works Inc, Nattik, MA,1998.
9. Kłos M, Sulewska M., J. and Waszczyszyn Z.: Neural identification of compaction characteristics for granular soils. Computer Assisted Mech. and Eng. Sci., 18: 265-274, 2013.
10.Sulewska M.: Artificial Neural Networks for Evaluation of Compaction Parameters of Cohesionless Soils (in Polish). Committee of Civil Eng. of the Polish Acad. Sci., Warsaw – Białystok, 2009.