Classification of Concrete Strength Grade Using Nearest Neighbor Partitioning
- 3k Downloads
Concrete is an important building material in the field of civil engineering. As an important factor, the strength of concrete affects its quality directly. Although conventional methods are made to forecast concrete strength, the classification of its grade is still an important issue in terms of non-uniformity of mortar and the complexity of curing condition. In this study, the classification of strength grade is implemented by employing the nearest neighbor partitioning method-based neural network classifier, which not only produces flexible decision boundaries but also eliminates centroid-based constraints and further enlarges the opportunity for finding optimal solutions. Experimental results manifest that the adopted method improves the performance of concrete grade classification.
KeywordsNeural network Nearest neighbor partitioning Concrete strength
This work was supported by National Natural Science Foundation of China under Grant No. 61573166, No. 61572230, No. 81671785, No. 61472164, No. 61472163, No. 61672262. Science and technology project of Shandong Province under Grant No. 2015GGX101025. Project of Shandong Province Higher Educational Science and Technology Program under Grant no. J16LN07. Shandong Provincial Key R&D Program under Grant No. 2016ZDJS01A12, No. 2016GGX101001.
- 1.Shi, X.C., Dong, Y.F.: Support vector machine applied to prediction strength of cement. In: 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce, pp. 1585–1588 (2011)Google Scholar
- 4.Wang, L., Yang, B., Abraham, A.: Prediction of concrete strength using floating centroids method. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics. Manchester, pp. 988–992 (2013)Google Scholar
- 19.Bridle, J.S.: Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. In: Soulié, F.F., Hérault, J. (eds.) Neurocomputing. NATO ASI Series (Series F: Computer and Systems Sciences), vol. 68, pp. 227–236. Springer, Berlin, Heidelberg (1990)CrossRefGoogle Scholar