Term-weighting approaches in automatic text retrieval
Information Processing and Management: an International Journal
Visualization support for a user-centered KDD process
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Detecting Interesting Exceptions from Medical Test Data with Visual Summarization
ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Mining hepatitis data with temporal abstraction
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Hi-index | 0.00 |
A human's process is proposed for data based scenario understanding, by integrating two existing tools in a new way of annotation. Scenario of a patient's hepatitis progress or recovery was obtained, by the presented process integrating a scenario map and a scenario flow diagram which are obtained from data on the patient's blood tests. The data was first visualized by KeyGaph as a scenario map, showing the rough view of event transitions. The user then discussed looking at the visualization, and wrote scenarios his/her thought of from the map. This text was visualized, again by KeyGraph, which externalizes the relations of events in his thought. On this visual output, the user came to be enabled to pay attention to potential chances existing at the cross points of scenarios. Based on this attention, the user annotated on the scenario flow diagram presented by the Discourse Structure Visualizer (DSV), showing the details of event transitions from the same data. As a result, the obtained annotations enabled hepatic experts to understand useful and novel scenarios underlying the patient's chronological history.