Data field for mining big data

作者：Shuliang Wang,Ying Li,Dakui Wang

摘要：Big data is a highlighted challenge for many fields with the rapid expansion of large-volume, complex, and fast-growing sources of data. Mining from big data is required for exploring the essence of data and providing meaningful information. To this end, we have previously introduced the theory of physical field to explore relations between objects in data space and proposed a framework of data field to discover the underlying distribution of big data. This paper concerns an overview of big data mining by the use of data field. It mainly discusses the theory of data field and different aspects of applications including feature selection for high-dimensional data, clustering, and the recognition of facial expression in human-computer interaction. In these applications, data field is employed to capture the intrinsic distribution of data objects for selecting meaningful features, fast clustering, and describing variation of facial expression. It is expected that our contributions would help overcome the problems in accordance with big data.

發文機構：State Key Laboratory of Information Engineering in Surveying School of Software State Key Laboratory of Information Engineering in Surveying International School of Software

關鍵詞：PhysicalFIELDDATAFIELDBIGDATAMININGfeatureselectionHIERARCHICALCLUSTERINGrecognitionoffaceexpressionPhysical fielddata fieldbig data miningfeature selectionhierarchical clusteringrecognition of face expression

分類號： R73[醫藥衛生—腫瘤][醫藥衛生—臨床醫學]