Earth mover's distances of feature vectors in large data analyses
Anurag Kumar Singh, Henry Chu, Michael A. Pratt · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2015
The earth mover's distance (EMD) measures the difference of two feature vectors that is related to the Wasserstein metric defined for probability distribution functions on a given metric space. The EMD of two vectors is based on the cost of moving the content of individual elements of an anchor vector to match the distribution of a target vector. The EMD is a solution to a transportation problem. We present results of using EMD in large data analysis problems such as those for health data and image data.