Paper Presentation at IEEE Pacific VIS!
Dimensionality Explorer for Single-Cell Analysis
We introduced a novel visual analytics system, for
interactively determining the optimal dimensionality for dimensionality reduction of the data for the task of cell type identification. By
providing a novel visualization scheme, such as the hull heatmap and
several interactive cell filtering methods, our method significantly reduces the effort required to review a large number of dimensionality
reduction plots.
A novel visual analytics framework for neuroscientists!
MitoVis: A Unified Visual Analytics System for End-to-End Neuronal Mitochondria Analysis (IEEE TVCG, 2023)
We introduced MitoVis, an all-in-one visual analytics system, to perform neuronal mitochondria morphology analysis quickly and effectively. MitoVis enables rapid analysis by drastically reducing the time required for data processing through deep learning and enables precise analysis through effective visualization, interaction, and interactive learning approaches.
Paper Published in Briefings in Bioinformatics (IF:13.998, JCR < 1.8%)!
RAMP: Response-Aware Multi-task Learning with Contrastive Regularization for Cancer Drug Response Prediction
RAMP is the high-throughput prediction of cancer drug sensitivity and will be useful for guiding cancer drug selection processes.
High-performance Visual Computing Lab (HVCL) at Korea University focuses on developing novel visual computing algorithms and visualization systems for scientific discoveries. Specifically, our research interests lie across diverse research fields such as Image Processing, Visualization, Machine Learning, and Computer Graphics.
We are looking for self-motivated undergrad/graduate students and postdoc researchers who are interested in visual computing. If you want to join our lab, please contact Prof. Won-Ki Jeong (wkjeong@korea.ac.kr) !