IDVL Team won VAST Mini-Challenge 2 Honorable Mention:
Detailed Analysis of Patterns of Misclassification

The VAST Challenge is an annual contest with the goal of advancing the field of visual analytics through competition. This year, the VAST Challenge asks participants to apply visual analytics to solve three mini-challenges to help a world impacted by a worldwide cyber event.

The IDVL Team consists of four Ph.D. students in Computer Science: Huyen N. Nguyen, Jake Gonzalez, Jian Guo, and Ngan V.T. Nguyen. The team participated in Mini-Challenge 2: Object of the Search, which focused on a process for using visual analytics to correct for classification errors in the results provided by a machine learning model. The ultimate goal of this challenge is to use patterns of misclassification analysis to identify a group of people having a special item - a totem.

The team has built an interactive visual analytics pipeline that included methods for visually analyzing photographic image data as well as performing visual analytics on the statistical data, with responsive visualization.

The report for the challenge can be found here; the video and demonstration can be found here.