“…Least squares support vector regression (LSSVR) (Liu, Xu, Li, & Zeng, ; Liu, Zeng, Liu, Bai, & Song, ; Sun, Lu, Mao, Wu, & Gao, ; Zhang, Zhao, Li, & Niu, ) is an emerging nonlinear algorithm of quantitative correction. In LSSVR, the equality constraint is used to replace the inequality constraint, and the error squared sum loss function is used as the empirical loss of the training set.…”