Entity

Time filter

Source Type


Qin C.,Tsinghua University | Song S.,Tsinghua University | Huang G.,Tsinghua University | Zhu L.,China Ocean Mineral Resources R and D Association
Neurocomputing | Year: 2015

In this paper, we propose a novel unsupervised distance metric learning algorithm. The proposed algorithm aims to maximize a stochastic variant of the leave-one-out K-nearest neighbor (KNN) score on unlabeled data, which performs distance metric learning and clustering simultaneously. We show that the joint distance metric learning and clustering problem is formulated as a trace optimization problem, and can be solved efficiently by an iterative algorithm. Moreover, the proposed approach can also learn a low dimensional projection of high dimensional data, thus it can serve as an unsupervised dimensionality reduction tool, which is capable of performing joint dimensionality reduction and clustering. We validate our method on a number of benchmark datasets, and the results demonstrate the effectiveness of the proposed algorithm. © 2015 Elsevier B.V. Source


Cui W.-C.,China Ship Scientific Research Center | Liu F.,China Ocean Mineral Resources R and D Association | Hu Z.,China Ship Scientific Research Center | Zhu M.,CAS Beijing Institute of Acoustics | And 2 more authors.
Chuan Bo Li Xue/Journal of Ship Mechanics | Year: 2012

Development of the deep manned submersible, "JIAOLONG", is one of the key projects of the national "863" high technology program. Its target is to build a practical product to carry out the predefined missions. Sea trial is the last stage of the development program with higher risks. In the periods from August to October 2009, from May to July 2010 and from July to August 2011, the 1000 m, 3000 m and 5000 m depth class tests were successfully finished respectively. Main purpose of this paper is to introduce the results of 7000 m depth class test which was just carried out from June 3 to July 16, 2012 and successfully completed. The contents include a description of basic information on the sea trials, technological and scientific achievements made in the tests, main faults in operation and dispose measure and their implications to future application. Finally, some conclusions are drawn from this sea trial. Source


He G.-W.,Guangzhou Marine Geological Survey | Sun X.-M.,Sun Yat Sen University | Yang S.-X.,Guangzhou Marine Geological Survey | Zhu K.-C.,Guangzhou Marine Geological Survey | Song C.-B.,China Ocean Mineral Resources R and D Association
Geology in China | Year: 2011

Polymetallic nodules and cobalt-rich crusts are two types of ferro-manganese deposits in the ocean. In order to probe into their REE geochemical characteristics in different oceanic areas of the Pacific Ocean, the authors collected samples from eastern Pacific basin, central Pacific Ocean and western Pacific Ocean and examined REE characteristics by means of ICP-AES. There are obvious positive Ce anomalies, rich LREE (light REE) and high total REE (XlREE) in the crusts. In contrast, there are rich HRjEE (heave REE) and relatively low X REE in the nodules, Ce anomalies have different styles, such as positive, negative and indistinct anomalies caused by different genetic types of nodules. The "M" type tetrad effects of nodules indicate that the nodules have suffered diagenesis, while the crusts have not been subjected to this effect. There exist different modes of occurrence of REE in nodules and crusts in different oceanic areas. REE in the crusts from central Pacific Ocean and in the nodules from eastern Pacific Ocean probably exist in the Fe-mineral phase, whereas REE in the crusts from western Pacific Ocean might exist in the Mn-mineral phase. REE in the nodules and crusts might have been mainly derived from seawater and seamount altered basalt respectively, with limited hydrothermal contribution. Source


Zhang X.-N.,Tsinghua University | Song S.-J.,Tsinghua University | Li J.-B.,State Oceanic Administration | Zhou N.,China Ocean Mineral Resources R and D Association
Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology) | Year: 2011

Seafloor hydrothermal sulphide is a new poly metallic ore resource as well as oceanic poly metallic nodules and rich-Co crust containing huge amounts of metals and rare metals. The appropriate and accurate estimation of ore grade plays an important role for the prediction of total mineral resources and further exploitation. Kriging and neural network methods have already been successfully used for grade estimation problem. However, the performance of these methods is not perfect for the limited borehole data. Therefore, this paper introduces a new nonlinear method to the issue of ore grade estimation based on the least squares support vector regression (LS-SVR). The borehole data obtained from Solwara 1 region are heterogeneous and discontinuities with huge missing values. Data preprocessing methods including weighted K-nearest neighbor (WKNN) imputation and Genetic algorithm (GA) for data segmentation were used before using LS-SVR algorithm. Finally the performance and efficacy of the LS-SVR were compared with BP, RBF neural network and geostatistical techniques such as inverse distance weight (IDW) and ordinary kriging (OK). The outcome indicates that the LS-SVR method outperforms other four methods. Source


Cui W.,China Ship Scientific Research Center | Liu F.,China Ocean Mineral Resources R and D Association | Hu Z.,China Ship Scientific Research Center | Zhu M.,CAS Beijing Institute of Acoustics | And 2 more authors.
Marine Technology Society Journal | Year: 2013

Development of the deep manned submersible Jiaolong was one of the key projects of the National 863 high-tech program. The program's target was to build a practical product to carry out a set of predefinedmissions. The 7,000msea trial was the last stage of the development process, a final phase that incorporated higher risks. During the preceding periods from August 6 to October 20, 2009, May 31 to July 18, 2010, and July 1 to August 18, 2011, the 1,000, 3,000, and 5,000mdepth class tests were successfully completed. The main purpose of this paper is to introduce the results of the 7,000 m depth class test, which was conducted from June 3 to July 16, 2012. The paper describes the general sea trial procedures, and technological and scientific achievements realized during the tests, main faults experienced in the field, along with corresponding troubleshooting methods and suggestions for future application of the Jiaolong submersible. In addition, several conclusions are drawn from all the experiences gained from these sea trials. Source

Discover hidden collaborations