prediction of relative sensitivity of the olfactory and nasal trigeminal chemosensory systems for a series of the volatile organic compounds based on local lazy regression method文档.pdf

Sensors and Actuators B 138 (2009) 55–63 Contents lists available at ScienceDirect Sensors and Actuators B: Chemical j o u rn al h omepage: w w w. elsev /locate/snb Prediction of relative sensitivity of the olfactory and nasal trigeminal chemosensory systems for a series of the volatile organic compounds based on local lazy regression method Hongying Du a , Jie Wang a,b , Zhide Hu a,∗ , Mancang Liu a , Xiaojun Yao a a Department of Chemistry, Lanzhou University, Lanzhou 730000, China b Department of Biomedical Engineering, Yale University, New Haven, CT, USA a r t i c l e i n f o a b s t r a c t Article history: Quantitative structure–activity relationship (QSAR) models were successfully developed for predicting Received 31 July 2008 the relative sensitivities odor detection thresholds (ODTs) and nasal pungency thresholds (NPTs) for the Received in revised form 27 December 2008 olfaction and nasal trigeminal chemosensory systems of a set of volatile organic compounds (VOCs). The Accepted 16 February 2009 best multi-linear regression (BMLR) method was used to select the most important molecular descriptors Available online 5 March 2009 and build a linear regression model. The methods support vector machine (SVM) and local lazy regression (LLR) were also used to build regression models. By comparing the results of these methods for the test Keywords: set of ODTs and NPTs, the LLR model gave bet