Values of variables obtained following modeling of the cold pain thresholds (rescaled for stimulus intensity, <i>SI = 32°C - CPT</i> to accommodate the increasing perception with increasing stimulus strength and zero-invariant log-transformed as <i>LogSI = Ln(SI+1)</i>), by means of the Gaussian mixture model (GMM given as px = ∑i = 0MwiN(x|mi,si), for which the optimum number of mixes was found to be <i>M</i> = 3 (Figs 2 and 3), where <i>m</i><sub><i>i</i></sub>, <i>s</i><sub><i>i</i></sub> and <i>w</i><sub><i>i</i></sub> are the parameters mean, standard deviation and relative weight of each of the Gaussians, respectively, obtained for the <i>LogSI</i> data.
收藏资源简介：
Due to the data transformations, retransformation of the modes to CPT values is thus obtained as CPT = 32°C—eLogSI+ 1. This retransformation of the mi values provides the modes of the three Gaussians in the linear temperature range over which CPT was measured, i.e., 23.6, 13.3 and 1.5°C for Gaussian number i = 1, 2 and 3, respectively. Values of variables obtained following modeling of the cold pain thresholds (rescaled for stimulus intensity, SI = 32°C - CPT to accommodate the increasing perception with increasing stimulus strength and zero-invariant log-transformed as LogSI = Ln(SI+1)), by means of the Gaussian mixture model (GMM given as p x = ∑ i = 0 M w i N(x| m i , s i ) , for which the optimum number of mixes was found to be M = 3 (Figs 2 and 3), where mi, si and wi are the parameters mean, standard deviation and relative weight of each of the Gaussians, respectively, obtained for the LogSI data.
