Interactive Visualizations of Temporal Event Sequences

preview_player
Показать описание
Catherine Plaisant, University of Maryland Presents...
Interactive Visualizations of Temporal Event Sequences (with a focus on Electronic Health Record data).

Sequences of events are part of people's life, their travel, hospital visits, even web browsing experiences. Specifying temporal queries to explore collections of event sequences can be challenging even for skilled computer professionals. We will review a series of visualization techniques developed at the Human-Computer Interaction lab over the years to handle temporal data, with a particular focus on the benefits - and challenges - of interaction during the analysis process. Our novel strategies allow for aligning records on important events, ranking, and filtering combined with grouping of results to find common or rare events. Other approaches explore query-by-example, or methods to aggregate thousands of event sequences. Video demonstrations will focus on electronic health record data. Finally we will discuss the methods we use to evaluate the usefulness of our interactive visualizations through case studies developed in collaboration with clinical researchers.

Catherine Plaisant is Senior Research Scientist at the Human-Computer Interaction Lab of the University of Maryland Institute for Advanced Computer Studies. She earned her PhD in France before joining the HCIL to work on diverse subjects such as information visualization, evaluation methods, technology for families, digital libraries, online help, etc. She co-authored with Ben Shneiderman the 4th and 5th Editions of Designing the User Interface, one of the major books on the topic of Human-Computer Interaction. She enjoys working with multidisciplinary teams on designing and evaluating new interface technologies that are useable and useful. Research contributions range from focused user interaction techniques (e.g. Excentric Labeling) to innovative visualizations (such as LifeLines for personal records or SpaceTree for hierarchical data exploration) and interactive search interface techniques such as Query Previews. Those interaction techniques have been carefully validated with user studies and have found applications in industry, government information systems and digital libraries.
Рекомендации по теме