Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-92537-0_33 | ADVANCES IN NEURAL NETWORKS - ISNN 2018 |
Keywords | Field | DocType |
Neural network,Nearest neighbor partitioning,Concrete strength | k-nearest neighbors algorithm,Neural network classifier,Pattern recognition,Computer science,Mortar,Artificial intelligence,Artificial neural network,Building material,Centroid | Conference |
Volume | ISSN | Citations |
10878 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 9 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xuehui Zhu | 1 | 3 | 2.06 |
Lin Wang | 2 | 162 | 27.96 |
Bo Yang | 3 | 519 | 52.33 |
Jin Zhou | 4 | 32 | 14.41 |
Shi-Yuan Han | 5 | 40 | 8.80 |
Yu Liu | 6 | 1 | 1.03 |
Jifeng Guo | 7 | 51 | 5.53 |
Shuangrong Liu | 8 | 3 | 2.74 |