The Univeristy of Texas at Arlington

The project strives to complete knowledge graph by soliciting knowledge from the crowd. Currently we focus on missing knowledge detection by leveraging both crowd intelligence and artificial intelligence. Techniques of CrowdSourcing, Collaborative Filtering, and Active Learning are applied to achieve our goal.

The project studies the problem of discovery of long consecutive subsequence consisting of only large (small) values in sequence data, e.g., consecutive games of outstanding performance in sports, consecutive hours of heavy network traffic, and so on. The outcome of this project provides insightful data patterns for data analysis in many real-world applications and is an enabling technique for computational journalism.

South Dakota State University

The project helps to detect breast cancer in early stage, which is the most important stage that can reduce the mortality significantly. We classify breast masses detected in mammograms to tell malignance of the masses. Various image process techniques are applied, for example, Segmentation, Smoothing, Enhancement, and Contour Analysis, etc.