首页|Federal University Pernambuco Reports Findings in Machine Learning (Machine lear ning classification based on k-Nearest Neighbors for PolSAR data)
Federal University Pernambuco Reports Findings in Machine Learning (Machine lear ning classification based on k-Nearest Neighbors for PolSAR data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting out of Recife, Brazil, by New sRx editors, research stated, “In this work, we focus on obtaining insights of t he performances of some well-known machine learning image classification techniq ues (k-NN, Support Vector Machine, randomized decision tree and one based on sto chastic distances) for PolSAR (Polarimetric Synthetic Aperture Radar) imagery. W e test the classifiers methods on a set of actual PolSAR data and provide some c onclusions.” Our news journalists obtained a quote from the research from Federal University Pernambuco, “The aim of this work is to show that suitable adapted standard mach ine learning methods offer excellent performances vs. computational complexity t rade-off for PolSAR image classification. In this work, we evaluate well-known m achine learning techniques for PolSAR (Polarimetric Synthetic Aperture Radar) im age classification, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), randomized decision tree, and a method based on the Kullback-Leibler stoc hastic distance. Our experiments with real PolSAR data show that standard machin e learning methods, when adapted appropriately, offer a favourable trade-off bet ween performance and computational complexity. The KNN and SVM perform poorly on these data, likely due to their failure to account for the inherent speckle pre sence and properties of the studied reliefs.”
NETL
NSTL
