Laying out and visualizing large trees using a hyperbolic space
UIST '94 Proceedings of the 7th annual ACM symposium on User interface software and technology
Proceedings of the conference on Visualization '98
Exploring Large Graphs in 3D Hyperbolic Space
IEEE Computer Graphics and Applications
IVORY - An Object-Oriented Framework for Physics-Based Information Visualization in Java
INFOVIS '98 Proceedings of the 1998 IEEE Symposium on Information Visualization
A Distributed OLAP Infrastructure for E-Commerce
COOPIS '99 Proceedings of the Fourth IECIS International Conference on Cooperative Information Systems
A Data-Warehouse/OLAP Framework for Scalable Telecommunication Tandem Traffic Analysis
ICDE '00 Proceedings of the 16th International Conference on Data Engineering
A Java-Based Visual Mining Infrastructure and Applications
INFOVIS '99 Proceedings of the 1999 IEEE Symposium on Information Visualization
Aspects of Network Visualization
IEEE Computer Graphics and Applications
| Hi-index | 0.00 |
Business intelligence applications require the analysis and mining of large volumes of transaction data to support business managers in making informed decisions. A key dimension of data mining for human decision making is information visualization: the presentation of information in such a way that humans can perceive interesting patterns. Often, such visual data mining is a powerful prelude to using other, algorithmic, data mining techniques. Additionally, visualization is often important to presenting the results of data mining tasks, such as clustering or association rules. There are several challenges to providing useful visualization for business intelligence applications. First, these applications typically involve the navigation of large volumes of data. Quite often, users can get lost, confused, and overwhelmed with displays that contain too much information. Second, the data is usually of high dimensionality, and visualizing it often involves a series of inter-related displays. Third, different visual metaphors may be useful for different types of data and for different applications. This paper discusses VisMine, a content-driven visual mining infrastructure that we are developing at HP Laboratories. VisMine uses several innovative techniques: (1) hidden visual structure and relationships for uncluttering displays; (2) simultaneous, synchronized visual presentations for high-dimensional data; and (3) an open architecture that allows the plugging in of existing graphic toolkits for expanding its use in a wide variety of visual applications. We have applied this infrastructure to visual data mining for various business intelligence applications in telecommunication, e-commerce, and Web information access.