| Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit |
| |
| 作者姓名： | ZHANG Xunan SONG Shiji LI Jiabiao WU Cheng |
| |
| 作者单位： | Department of Automation, Tsinghua University, Beijing 100084, China;Department of Automation, Tsinghua University, Beijing 100084, China;Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012, China;Department of Automation, Tsinghua University, Beijing 100084, China |
| |
| 基金项目： | Project of China Ocean Association under contact No. DYXM-125-25-02; Independent Research Project of Tsinghua University under contact Nos 2010THZ07002 and 2011THZ07132. |
| |
| 摘 要： | Due to the geological complexities of ore body formation and limited borehole sampling, this paper proposes a robust weighted least square support vectormachine (LS-SVM) regression model to solve the ore grade estimation for a seafloor hydrothermal sulphide deposit in Solwara 1, which consists of a large proportion of incomplete samples without ore types and grade values. The standard LS-SVM classification model is applied to identify the ore type for each in complete sample. Then, a weighted K-nearest neighbor (WKNN) algorithm is proposed to interpolate the missing values. Prior to modeling, the particle swarm optimization (PSO) algorithm is used to obtain an appropriate splitting for the training and test data sets so as to eliminate the large discrepancies caused by randomdivision. Coupled simulated annealing (CSA) and grid search using 10-fold cross validation techniques are adopted to determine the optimal tuning parameters in the LS-SVM models. The effectiveness of the proposed model by comparing with other well-known techniques such as inverse distance weight (IDW), ordinary kriging (OK), and back propagation (BP) neural network is demonstrated. The experimental results show that the robust weighted LS-SVM outperforms the othermethods, and has strong predictive and generalization ability.
|
| 关 键 词： | LS-SVM 硫化物矿床 矿石类型 回归模型 海底热液 品位估计 粒子群优化算法 最小二乘支持向量机 |
| 收稿时间： | 2012/2/21 0:00:00 |
| 修稿时间： | 2012/12/24 0:00:00 |
Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit |
| |
| ZHANG Xunan,SONG Shiji,LI Jiabiao,WU Cheng.Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit[J].Acta Oceanologica Sinica,2013,32(8):16-25. |
| |
| Authors: | ZHANG Xunan SONG Shiji LI Jiabiao and WU Cheng |
| |
| Institution: | 1.Department of Automation, Tsinghua University, Beijing 100084, China2.Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012, China |
| |
| Abstract: | Due to the geological complexities of ore body formation and limited borehole sampling, this paper proposes a robust weighted least square support vector machine (LS-SVM) regression model to solve the ore grade estimation for a seafloor hydrothermal sulphide deposit in Solwara 1, which consists of a large proportion of incomplete samples without ore types and grade values. The standard LS-SVM classification model is applied to identify the ore type for each incomplete sample. Then, a weighted K-nearest neighbor (WKNN) algorithm is proposed to interpolate the missing values. Prior to modeling, the particle swarm optimization (PSO) algorithm is used to obtain an appropriate splitting for the training and test data sets so as to eliminate the large discrepancies caused by random division. Coupled simulated annealing (CSA) and grid search using 10-fold cross validation techniques are adopted to determine the optimal tuning parameters in the LS-SVM models. The effectiveness of the proposed model by comparing with other well-known techniques such as inverse distance weight (IDW), ordinary kriging (OK), and back propagation (BP) neural network is demonstrated. The experimental results show that the robust weighted LS-SVM outperforms the other methods, and has strong predictive and generalization ability. |
| |
| Keywords: | weighted LS-SVM grade estimation incomplete samples data division |
| 本文献已被 维普 SpringerLink 等数据库收录！ |
| 点击此处可从《海洋学报(英文版)》浏览原始摘要信息 |
| 点击此处可从《海洋学报(英文版)》下载免费的PDF全文 |
