Soft sensor design based on phase partition ensemble of LSSVR models for nonlinear batch processes.

Traditional single model based soft sensors may have poor performance on quality prediction for batch processes because of the strong nonlinearity, multiple-phase, and time-varying characteristics. Therefore, a phase partition based ensemble learning framework upon least squares support vector regression (LSSVR) is proposed for soft sensor modeling. Firstly, multiway principal component analysis (MPCA) is employed to handle high-dimensional datasets and extract essential correlation information.

Cloning and identification of a novel thyroid hormone receptor β isoform expressed in the pituitary gland.

We have previously identified a novel Trβ isoform (TrβΔ) in the rat, in which a novel exon N (108 bps) was found between exon 3 and exon 4 of TrβΔ, which represents the only difference between TrβΔ and Trβ1. In this study, we searched for an elongated Trβ2-like subtype with one additional exon N. We successfully isolated the entire mRNA/cDNA of a novel elongated Trβ2 isoform via PCR in the rat pituitary gland.