[Partial least squares regression variable screening studies on apple soluble solids NIR spectral detection].

Abstract To improve the predictive ability and robustness of the NIR correction model of the soluble solid content (SSC) of apple, the reverse interval partial least squares method, genetic algorithm and the continuous projection method were implemented to select variables of the NIR spectroscopy of the soluble solid content (SSC) of apple, and the partial least squares regression model was established. By genetic algorithm for screening of the 141 variables of the correction model, prediction has the best effect. And compared to the full spectrum correction model, the correlation coefficient increased to 0.96 from 0.93, forecast root mean square error decreased from 0.30 degrees Brix to 0.23 degrees Brix. This experimental results show that the genetic algorithm combined with partial least squares regression method improved the detection precision of the NIR model of the soluble solid content (SSC) of apple.