TY - JOUR
TI - Regression SVM for Incomplete Data
AU - Struski, Łukasz
AU - Śmieja, Marek
AU - Zieliński, Bartosz
AU - Tabor, Jacek
TI - Regression SVM for Incomplete Data
AB - 
	The use of machine learning methods in the case of incomplete data is an important task in many scientific fields, like medicine, biology, or face recognition. Typically, missing values are substituted with artificial values that are estimated from the known samples, and the classical machine learning algorithms are applied. Although this methodology is very common, it produces less informative data, because artificially generated values are treated in the same way as the known ones. In this paper, we consider a probabilistic representation of missing data, where each vector is identified with a Gaussian probability density function, modeling the uncertainty of absent attributes. This representation allows to construct an analogue of RBF kernel for incomplete data. We show that such a kernel can be successfully used in regression SVM. Experimental results confirm that our approach capture relevant information that is not captured by traditional imputation methods.
VL - 2017
IS - Volume 26
PY - 2018
SN - 1732-3916
C1 - 2083-8476
SP - 23
EP - 35
DO - 10.4467/20838476SI.17.001.6807
UR - https://ejournals.eu/en/journal/schedae-informaticae/article/regression-svm-for-incomplete-data
KW - regression SVM
KW - incomplete data
KW - missing attributes
KW - RBF kernel