Strawberry quality prediction based on dielectric spectrum technology combining with genetic algorithm

In order to find rapid non-destructive prediction methods for strawberry quality,dielectric spectrum was tested and its change rule was analyzed with Inductance,Capacitance,Resistance tester( LCR).The characteristic frequency points of quality indicators( respiration intensity,soluble solids content and weightlessness rate) were selected out by genetic algorithm( GA). Partial Least Squares( PLS) quality prediction models were established based on the dielectric parameters at the characteristic frequency points. The results showed that the Relative Percent Deviation( RPD) and R2 values of the GA-PLS model for respiration intensity,soluble solid content( TSS)and weight loss rate established based on dielectric parameters selected out by GA were 5.21,3.14,4.89 and0.941,0.852,0.906,respectively.There was no significant difference between the predicted value and the measured value( p > 0.05) for each quality indicator.Dielectric spectrum technology combining with GA can be used to predict the quality of the storage period of strawberries