Lossless Visual Knowledge Discovery in High Dimensional Data with Elliptic Paired Coordinates

被引:3
作者
McDonald, Rose [1 ]
Kovalerchuk, Boris [1 ]
机构
[1] Cent Washington Univ, Dept Comp Sci, Ellensburg, WA 98926 USA
来源
2020 24TH INTERNATIONAL CONFERENCE INFORMATION VISUALISATION (IV 2020) | 2020年
关键词
Machine learning; data visualization; knowledge discovery; elliptic paired coordinates;
D O I
10.1109/IV51561.2020.00053
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Data with more than two or three dimensions are difficult for humans to conceptualize and facilitate knowledge discovery. Novel Elliptic Paired Coordinates (EPCs) allow for multidimensional data to be represented in 2-D without loss of multidimensional information. In addition, EPC halves the required visual elements in the graph in comparison with parallel and radial coordinates. This research explores the effectiveness of constructing predictive machine learning models interactively using EPC visualizations. For this research EllipseVis, an interactive software system, was developed to process high-dimensional datasets, create corresponding EPC visualizations, and build predictive classification models based on dominance rules. The EllipseVis system allows both interactive and automatic discovery of areas that are located with a high percentage of single-class dominance. The experiments using it on benchmark datasets suggest EPC approach is a promising method for discovering predictive models with high coverage and precision that could be useful in many fields allowing for visually appealing dominance rules to be easily interpreted in the application domains.
引用
收藏
页码:286 / 291
页数:6
相关论文
共 6 条
[1]  
[Anonymous], 2009, Parallel Coordinates, DOI DOI 10.1007/978-0-387-68628-8
[2]  
Dua D, 2019, Machine learning repository
[3]  
Kovalerchuk B, 2018, INTEL SYST REF LIBR, V144, P1, DOI 10.1007/978-3-319-73040-0
[4]   Decreasing Occlusion and Increasing Explanation in Interactive Visual Knowledge Discovery [J].
Kovalerchuk, Boris ;
Gharawi, Abdulrahman .
HUMAN INTERFACE AND THE MANAGEMENT OF INFORMATION: INTERACTION, VISUALIZATION, AND ANALYTICS, HIMI 2018 HELD AS PART OF HCI 2018, PART I, 2018, 10904 :505-526
[5]   RuleMatrix: Visualizing and Understanding Classifiers with Rules [J].
Ming, Yao ;
Qu, Huamin ;
Bertini, Enrico .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2019, 25 (01) :342-352
[6]  
van der Maaten L, 2008, J MACH LEARN RES, V9, P2579