EECS doctoral student Hongliang Fei has won the Best Student Paper award from the upcoming IEEE International Conference on Data Mining (ICDM). The paper details research, by Fei and EECS Associate Professor Jun “Luke” Huan, that enables more accurate, efficient predictive models. Their algorithms improved prediction accuracy in the analysis of gene expressions and functional magnetic resonance imaging. Dr. Huan says the research has a wide range of applications and is an important breakthrough in multi-task learning of complex, massive data sets.
ICDM is the IEEE flagship conference on data mining. The conference, to be held Dec. 11-14 in Vancouver, covers all aspects of data mining, including algorithms, software and systems, and applications. This year ICDM selected one best research paper and one best student research paper, which was Fei’s “Structured Feature Selection and Task Relationship Inference for Multi-Task Learning,” among the 101 accepted full papers from approximately 800 original submissions.
The research was conducted at KU’s Information and Telecommunication Technology Center.