| ZHANG Xunan,SONG Shiji,LI Jiabiao,WU Cheng. 2013. Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit. Acta Oceanologica Sinica, 32(8):16－25 |
| Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit |
|
| Received:February 21, 2012 Revised:December 24, 2012 |
| DOI：10.1007/s13131-013-0337-x |
| Key words:weighted LS-SVM grade estimation incomplete samples data division |
| 中文关键词: |
| 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. |
| Author Name | Affiliation | E-mail | | ZHANG Xunan | Department of Automation, Tsinghua University, Beijing 100084, China | shijis@mail.tsinghua.edu.cn | | SONG Shiji | Department of Automation, Tsinghua University, Beijing 100084, China | | | LI Jiabiao | Second Institute of Oceanography, State Oceanic Administration, Hangzhou 310012, China | | | WU Cheng | Department of Automation, Tsinghua University, Beijing 100084, China | |
|
| Hits: 1777 |
| Download times: 2460 |
| Abstract: |
| 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. |
| 中文摘要: |
| 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. |
|
HTML
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
