Dielectric spectroscopy has been employed as a simple,low cost and a non-destructive way for prediction of some physicochemical indices of kiwifruit during storage.A parallel-plate capacitor was developed and supplied...Dielectric spectroscopy has been employed as a simple,low cost and a non-destructive way for prediction of some physicochemical indices of kiwifruit during storage.A parallel-plate capacitor was developed and supplied with sinusoidal voltage waves within a frequency range of 40 kHz–20 MHz.Dielectric properties of samples were measured by the dielectric sensor.Additionally,changes associated with fruit ripening properties,including firmness,total soluble solid(TSS)and pH were determined as a function of time at 2C.The results showed that storage time significantly affected the quality characteristics of kiwifruit.Artificial neural networks(ANNs)were employed to develop models for prediction of quality indices from dielectric properties at the swept frequencies.Dielectric property features were selected as inputs while the quality indices including firmness,TSS and pH were chosen as output for the ANNs.The obtained models were able to predict the firmness,soluble solids content,and pH of kiwifruit non-destructively.Among predictive models,an ANN with a topology of 20-19-1 gave a perfect capability to predict the kiwifruit firmness with R2 value of 0.92.Results of this research show that this technique can be used as an efficient and non-destructive method for kiwifruit quality evaluation and monitoring the ripening.展开更多
文摘Dielectric spectroscopy has been employed as a simple,low cost and a non-destructive way for prediction of some physicochemical indices of kiwifruit during storage.A parallel-plate capacitor was developed and supplied with sinusoidal voltage waves within a frequency range of 40 kHz–20 MHz.Dielectric properties of samples were measured by the dielectric sensor.Additionally,changes associated with fruit ripening properties,including firmness,total soluble solid(TSS)and pH were determined as a function of time at 2C.The results showed that storage time significantly affected the quality characteristics of kiwifruit.Artificial neural networks(ANNs)were employed to develop models for prediction of quality indices from dielectric properties at the swept frequencies.Dielectric property features were selected as inputs while the quality indices including firmness,TSS and pH were chosen as output for the ANNs.The obtained models were able to predict the firmness,soluble solids content,and pH of kiwifruit non-destructively.Among predictive models,an ANN with a topology of 20-19-1 gave a perfect capability to predict the kiwifruit firmness with R2 value of 0.92.Results of this research show that this technique can be used as an efficient and non-destructive method for kiwifruit quality evaluation and monitoring the ripening.
