Linear-in-Parameter Models Based on Parsimonious Genetic Programming Algorithm and Its Application to Aero-Engine Start Modeling

A novel Parsimonious Genetic Programming （PGP） algorithm together with a novel aero-engine optimum data-driven dynamic start process model based on PGP is proposed. In application of this method, first, the traditional Genetic Programming（GP） is used to generate the nonlinear input-output models that are represented in a binary tree structure; then, the Orthogonal Least Squares algorithm （OLS） is used to estimate the contribution of the branches of the tree （refer to basic function term that cannot be decomposed anymore according to special rule） to the accuracy of the model, which contributes to eliminate complex redundant subtrees and enhance GP＇s convergence speed; and finally, a simple, reliable and exact linear-in-parameter nonlinear model via GP evolution is obtained. The real aero-engine start process test data simulation and the comparisons with Support Vector Machines （SVM） validate that the proposed method can generate more applicable, interpretable models and achieve comparable, even superior results to SVM.

MODELLING THE POLYALANINE BACKBONE STARTING FROM ALPHA-CARBON GUIDE POSITIONS

An automatic procedure for building a protein polyalanine backbone from guiding alpha-carbon positions is presented here,which is different from a previously developed'spare parts'approach(Jones and Thirup,1986;Claessens et al.,1989). In our procedure,the geometric restraint of angle N-CA-C is used to generate a list of polypeptide chains,and several filters are used later to select the best conformer.The most important filter is based upon the Ramachandran scatter plot of mainchain dihedral angles PHI and PSI.Results for all test cases are satisfactory,with more than 95%of peptide planes correctly reconstructed and the overall root-mean-square deviation less than 0.5 angstrom compared with the refined X-ray coordinates.

Efficacy and moderating factors of the Early Start Denver Model in Chinese toddlers with autism spectrum disorder:a longitudinal study

Background Several studies have shown the effectiveness of the Early Start Denver Model(ESDM),but few studies have explored the long-term efficacy of ESDM.This study aimed to explore the efficacy and moderating factors of ESDM in Chinese toddlers with autism spectrum disorder(ASD)in a longitudinal way.Methods A total of 60 toddlers with ASD were recruited and randomly divided into two groups:ESDM group all received 24 weeks intervention;Control group were waiting for intervention.Baseline assessment(T0)was conducted before intervention,including Gesell Developmental Scale(GDS)and Psycho-educational Profile-3rd Edition(PEP-3).All toddlers with ASD were examined in the first assessment(T1)at 6 months and in the second assessment(T2)at 12 months.Results In T1 assessment,the increments in speech and personal communication development quotient in GDS were significantly larger in the ESDM group than in the control group(P=0.010,0.047).In T2 assessment,the ESDM group had higher elevation in cognitive verbal/preverbal(CVP),social reciprocity and characteristic verbal behaviors assessed by PEP-3(P=0.021,0.046,0.014).In addition,the severity of stereotyped behavior was negatively associated with improvement in CVP.Family income was positively associated with improvement in speech and CVP(all P<0.05).Conclusions ESDM can effectively improve speech and communication in toddlers with ASD after 24-week intervention.More importantly,ESDM can promote cognition and social interaction and can reduce stereotyped verbal behavior in toddlers with ASD in longitudinal observation.The severity of stereotyped behavior and family ecological factors may be considered as affecting the efficacy of ESDM.