VizAssist: an interactive user assistant for visual data mining

详细信息    查看全文

• 作者：Fatma Bouali ; Abdelheq Guettala ; Gilles Venturini
• 关键词：Visual data mining ; User assistant ; Interactive genetic algorithm ; D3js ; On ; line visualization tools
• 刊名：The Visual Computer
• 出版年：2016
• 出版时间：November 2016
• 年：2016
• 卷：32
• 期：11
• 页码：1447-1463
• 全文大小：1,322 KB
• 刊物类别：Computer Science
• 刊物主题：Computer Graphics
  Computer Science, general
  Artificial Intelligence and Robotics
  Image Processing and Computer Vision
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1432-2315
• 卷排序：32

文摘

We study in this work how a user can be guided to find a relevant visualization in the context of visual data mining. We present a state of the art on the user assistance in visual and interactive methods. We propose a user assistant called VizAssist, which aims at improving the existing approaches along three directions: it uses simpler computational models of the visualizations and the visual perception guidelines, in order to facilitate the integration of new visualizations and the definition of a mapping heuristic. VizAssist allows the user to provide feedback in a visual and interactive way, with the aim of improving the data to visualization mapping. This step is performed with an interactive genetic algorithm. Finally, VizAssist aims at proposing a free on-line tool (www.vizassist.fr) that respects the privacy of the user data. This assistant can be viewed as a global interface between the user and some of the many visualizations that are implemented with D3js.