The Computational Informatics Laboratory is a research and training unit in the department of Electric Engineering and Computer Science at the Catholic University of America. The primary focus of the lab is to develop novel computational methods to the application of various aspects of scientific disciplines. Its educational purpose is to train students with algorithmic thinking and proficient programming skills to solve large scale of scientific and engineering problems.

Current Research

The current emphasis of the lab is on designing computational approaches with applications to biomedical data analysis. It includes projects in quantitative diffusion tensor magnetic resonance image processing and analysis, computational T1 map estimation, error propagation and analysis on diffusion tensor derived quantities, robust diffusion tensor estimation, and outlier detection, etc.

Past Projects

NIH Pediatric Neuroimaging Project

Research Interests

Machine Learning, Medical Image Processing and Analysis, Pattern Recognition, Data Science, and Computational Neuroscience.

Ph.D. Graduates and Dissertations

  • Ibrahim Almubark (2021): Machine Learning Approaches for Early Diagnostic Classification of Alzheimer’s Disease
  • Vy Bui (2020): Machine Learning for Anatomical Heart Structures Segmentation of Contrast Enhanced Cardiac Computed Tomography Images
  • Matthew James Jacobs (2018): Advanced Image Processing in Cardiac Magnetic Resonance Imaging with Application in Myocardial Perfusion Quantification
  • Eyad Makki (2017): An Enhanced Quantitative Performance Model for Automatic E-commerce Websites Evaluation
  • Vladimir Kirnosov (2016): Automatic Three-dimensional Reconstruction of Coronal Mass Ejection from STEREO A/B White-light Coronagraph Images

Master Graduates and Thesis

  • Edward Trudeau (2023): Classifying Cognitive-Aesthetic Experience Through Machine Learning and EEG Data
  • Mai Bui (2022): A Comparison Study of Point Cloud Compression Algorithms (co-advise with Dr. Hang Liu)
  • Tan Tran (2019): Machine Learning Methods to Classify Functional and Nonfunctional Arm Movement after Stroke Using a Single Wrist-Worn Sensor Device
  • Jeffrey C. Jenkins (2017): Harmonization of Methods to Facilitate Reproducibility in Medical Data Processing: Applications to Diffusion Tensor Magnetic Resonance Imaging
  • László István Etesi (2010): A Message-Based Interoperability Framework With Application to Astrophysics
  • Mikhail A. Gorbachev (2010): Ordinary and Weighted Least Square Algorithm Implementation for Multivariate Linear Regression on General Purpose Graphical Processing Units

Current Graduate Students

  • Anh Thai
  • Jeffrey C. Jenkins
  • An-Yu Sun
  • Tan Tran
  • Edward Trudeau