Test

Event

HSI Research Seminar Series :: Self Similarity in Medical Data and Applications

Brani Vidakovic, Professor, The Wallace H. Coulter Department of Biomedical Engineering

DATE: Tuesday, April 22, 2008

TIME: 1:00 PM – 3:00 PM

[ Video Archive ]

LOCATION: Health System Institute, 2nd Floor, Event Room 207

Abstract: Measured bio and neuro responses, MRI, NMR spectra, etc, have intrinsic high frequency components and strong persistent serial correlations inhibiting statistical modeling by traditional techniques. In many modeling scenarios the low-frequency-trend may be irrelevant and researchers focus on the noise and its lowdimensional descriptors.

The talk provides an overview of several traditional wavelet-based techniques for assessing scaling in 1-, 2-, and 3-D data and some novel related techniques that are being developed by Dr. Vidakovic and his colleagues at Georgia Institute of Technology and Emory University.

The applications include analysis and modeling of spectral responses in 1H NMR spectroscopy describing metabolic fluctuations in human plasma, prediction of age-related macular degeneration by high frequency pupil diameter measurements, building classifiers by scaling signatures in 3-D MRI data taken from breast cancer patients and healthy controls, detecting vasospasm signatures in EEG data, and filtering turbulent ground-level ozone concentrations.

Bio: Brani Vidakovic is a Professor of Biostatistics at the departments of ISyE and BME at Georgia Tech, where he directs the Center for Bio-Engineering Statistics (BESTA). He also has joint appointments in the departments of Biostatistics at the Rollins School of Public Health, Emory University and at J-P Hsu College of Public Health at Georgia Southern University.

Dr. Vidakovic obtained his B.S. and M.S. in Mathematics at the University of Belgrade and a Ph.D. in Statistics at Purdue University. He was on the faculty at Duke University prior to joining Georgia Tech. in 2000.

Dr. Vidakovic�s research is at the interface of statistics and processing massive data sets in the context of medical, health, and environmental applications. His interests include wavelets, high frequency data, and Bayesian methodology, functional data analysis, statistical machine learning, applied biostatistics, and statistical consulting and education. He is author of several books, and over sixty archival papers and book chapters. He is a member of several scientific societies including the American Statistical Association, the Institute of Mathematical Statistics, the International Society for Bayesian Analysis, the Bernoulli Society and is an elected member of International Statistical Institute.