Premium
Cover Image, Volume 36, Issue 8
Publication year - 2015
Publication title -
journal of computational chemistry
Language(s) - English
Resource type - Reports
SCImago Journal Rank - 0.907
H-Index - 188
eISSN - 1096-987X
pISSN - 0192-8651
DOI - 10.1002/jcc.23885
Subject(s) - outlier , computer science , cover (algebra) , citation , set (abstract data type) , volume (thermodynamics) , image (mathematics) , identification (biology) , information retrieval , data set , data mining , artificial intelligence , pattern recognition (psychology) , library science , engineering , biology , mechanical engineering , physics , botany , quantum mechanics , programming language
A new iterative method for the identification and removal of outliers from QSAR data sets is described on page 493 (DOI: 10.1002/jcc.23803 ) by Abraham Yosipof and Hanoch Senderowitz. This method is based on a k NN optimization algorithm, and named k NN optimization‐based outlier removal. The method is able to maintain the internal diversity of the parent data set and at the same time produce QSAR models with better prediction statistics than other outlier removal methods.