A nondestructive testing method for soluble solid content in Korla fragrant pears based on electrical properties and artificial neural network

Abstract

The detection of soluble solid content in Korla fragrant pear is a destructive and time‐consuming endeavor. In effort to remedy this, a nondestructive testing method based on electrical properties and artificial neural network was established in this study. Specifically, variations of electrical properties (e.g., equivalent parallel capacitance, quality factor, loss factor, equivalent parallel resistance, complex impedance, and equivalent parallel inductance) of Korla fragrant pears with accumulated temperature were tested using a workbench developed by ourselves. After that the characteristic variables of electrical properties were constructed by principal component analysis (PCA). In addition, three models were constructed to predict SSC in Korla fragrant pears based on the characteristic variables: general regression neural network (GRNN), back‐propagation neural network (BPNN), and adaptive network fuzzy inference system (ANFIS). The results indicated that the GRNN model has the best prediction effects of SSC (R2 = 0.9743, RMSE = 0.2584), superior to that of the BPNN and ANFIS models. Results facilitate a successful, alternative application for rapid assessment of SSC of the maturation stage Korla fragrant pear.

Bioimpedance Data Statistical Modelling for Food Quality Classification and Prediction

“…Moreover, ANN structured in 20 input, 9-node hidden layer and 1 final output layer, correctly classified 100% of the frozen thawed samples, in accordance with a similar study of the same research group carried out on lemons [21]. Finally, total soluble solid content (SSC) in Korla pears during the maturation process was predicted using three different neural network architectures [22]. After performing a factor analysis and constructing the dataset based on PCA, GRNN, BPNN, and adaptive network fuzzy inference system (ANFIS) were applied.…”

“…In general, especially for meat, fish, and beverages, fixed frequencies are preferred, while for fruits and vegetables the 1 Hz -1 MHz range is mostly used. Concerning the choice of the models, Bria et al [29], Ibba et al [17], Lan et al [22] and Zhu et al [32] made an accurate comparison between multiple algorithms. Moreover, in [17] and [29] the model training and testing were carried out with a large number of samples (as high as 70000 samples in [29]), making the results more robust.…”

Comprehensive evaluation of Korla fragrant pears and optimization of plucking time during the harvest period

“…The SSC is an index for evaluating the quality of fragrant pears. It has a complex composition that directly influences the flavor, taste, and nutrition level of fruits [31] . As nutritious substances are formed through the synthesis of carbon atoms, fruits with high sugar content have the benefits of promoted growth, delayed aging, and protection of the integrity of mitochondria and cytomembranes.…”

Inhibitory effect of CaCl2 and carboxymethyl chitosan coating on the after‐ripening of Korla fragrant pears in cold storage

“…There are varying degrees of correlations and information overlaps between different indicators of Korla fragrant pears. Furthermore, as a large amount of information will hinder the analysis (Lan et al ., 2020), it is challenging to characterise the influence of CaCl 2 , CC, and their combined treatment on the after‐ripening effect of Korla fragrant pears. Therefore, this study uses factor analysis and principal component analysis to analyze these indicators.…”