Abstract | ||
---|---|---|
Support Vector Machine (SVM) has become an effective machine learning method characterized by solving learning problems of small samples, nonlinearity and high-dimensional pattern recognition. Based on Support Vector Machine Regression (SVR), the paper presents an ore grade interpolation model by using the cross-validation contrast to select the kernel function and the model parameters including penalty parameter C, the insensitive coefficient e and the kernel function parameter s. Then the model is applied in a typical domestic underground mine and the interpolation result shows the model is feasible and more efficient in contrast with the production data and the results of traditional interpolation methods, such as the Thiessen polygon method, the distance power inverse ratio method and the Kriging interpolation method. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/FSKD.2011.6019907 | FSKD |
Keywords | Field | DocType |
model parameters,machine learning method,domestic underground mine,pattern recognition,model,mine,interpolation,kernal function,learning (artificial intelligence),regression analysis,minerals,kernel function parameter,ore grade interpolation,svm,problem solving,support vector machine,mining,support vector machines,production,kernel function,correlation,machine learning,kernel,learning artificial intelligence,data models,cross validation | Nearest-neighbor interpolation,Pattern recognition,Multivariate interpolation,Computer science,Interpolation,Support vector machine,Artificial intelligence,Kernel method,Machine learning,Bilinear interpolation,Inverse quadratic interpolation,Kernel (statistics) | Conference |
Volume | Issue | ISBN |
3 | null | 978-1-61284-180-9 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cuiping Li | 1 | 3 | 3.85 |
Yaoxia Zheng | 2 | 0 | 0.34 |
Zhongxue Li | 3 | 3 | 3.50 |
Yiqing Zhao | 4 | 0 | 3.04 |