1. Beijing Technology and Business University, 海淀区阜成路11号 , Beijing ChinaChina 100048
2. Beijing Technology and Business University, 海淀区阜成路11号,北京工商大学耕耘楼310 , Beijing ChinaChina 100048
3. Beijing Technology and Business University, 海淀区阜成路11号,北京工商大学耕耘楼310 , Beijing China 100048
4. 计算机学院 , 杭州 China 710049
5. University of California Davis, One Shields Avenue, Davis, CA , Davis California United States 95616-5270
Associated data refer to a set of entities with some specific relations and relational weights that can usually be expressed with a relational matrix. They exists widely in many fields, such as pesticide residue data in food safety, in which pesticides are associated with agricultural products. However, when the data scale becomes large, analyzing this type of data, to find key entities or mine hidden patterns for example, becomes difficult and time consuming. An ordered matrix can help analysts quickly locate the entity of interest. When ranking the entities, relations and their weights should be considered. The existing ranking algorithms, such as PageRank, only consider the relations but ignore the influence of their weights on ranking result. In this paper, we present a ranking algorithm on the basis of Relations and Weights, called RW-Rank, which is inspired by the PageRank algorithm and can be used to create an ordered relational matrix. In RW-Rank, we also propose the definition of RW-value and its calculation method for evaluating the importance of an entity in a relational structure quantitatively. Based on the RW-Rank algorithm, we design and implement a visual analysis system called Rank-Vis for analyzing complex associated data. We use pesticide residue dataset and students’ course achievement dataset as case studies to verify the effectiveness of this approach.
1. National Key R&D program of China (grant no. 2018YFC1603602); 2.National Natural Science Foundation of China (61972010, 61772456, 61761136020) 3. Basic Research Project of the Ministry of Science and Technology (grant no. 2015FY111200)
Copyright 2020 CHINA SCIENCE PUBLISHING & MEDIA LTD. 中国科技出版传媒股份有限公司 版权所有