Lin ching

Department

  • Electrical Engineering and Computer Science
  • School

  • School of Engineering
  • Expertise

  • Machine Learning
  • Computational Informatics
  • Medical Image Processing and Analysis
  • Data Analytics
  • Algorithm Design
  • Education

  • D.Sc., Computer Science, George Washington University, Washington DC, 1998
  • M.Sc., Computer Science, George Washington University, Washington DC, 1993
  • B.Sc., Information and Computer Engineering, Chung-Yuan Christian University, Taiwan, 1991
  • Bio

    Lin-Ching Chang's research interests include medical informatics, modeling and simulation, machine learning, pattern recognition, parallel processing, and telecommunication applications. During her career at the National Institutes of Health (NIH), she worked on several computational neuroscience projects focusing on algorithm design and software development for medical image processing and quantitative diffusion tensor magnetic resonance imaging (DTI) analysis. She was associated with the NIH pediatric neuroimaging project, a study to learn the brain development in normal healthy children and adolescents using MRI techniques. Prior to NIH, she was a senior software engineer at 3Com Corporation and worked on several commercial telecommunication projects including 3Com's unified messaging system, data encryption, and database systems migration. She also led several wireless applications projects including an interactive voice response system and short message service.

    Selected Publications

    1. L Dao, B Lucotte, B Glancy, L-C Chang, L-Y Hsu, R S Balaban Use of Independent Component Analysis to Improve Signal-to-noise Ratio in Multi-probe Fluorescence Microscopy. Journal of Microscopy, doi: 10.1111/jmi.12167, 2014.

    2. L-C Chang, E El-Araby, V Dang, L Dao, GPU Acceleration of Nonlinear Diffusion Tensor Estimation Using CUDA and MPI, Neurocomputing 135: 328–338, 2014.

    3. L-C Chang, L Walker L, C Pierpaoli, Informed RESTORE: A Method for Robust Estimation of Diffusion Tensor from Low Redundancy Datasets in the Presence of Physiological Noise Artifacts, Magnetic Resonance in Medicine 68:1654-1663, 2012.

    Read more publications