Dr. Corcoran's research is focused on fast and accurate Markov chain Monte Carlo (MCMC) algorithms with applications to problems in high-dimensional Bayesian network inference, target tracking, statistical mechanics, high-energy physics, and rarefied gas dynamics. Most recently, she has been involved in target tracking via data fusion, perfect sampling for Bayesian principal components analysis, the development of perfect simulation algorithms for chemical kinetic networks, and new statistical methods for edge detection in images.
keywords
Monte Carlo algorithms, multi-target tracking, Bayesian network recovery, edge detection in image processing, particle filtering , chemical reaction networks, data fusion
