Determination of moisture content and contaminated blank dried figs (<i>Ficus carica</i> L.) using dielectric property and artificial neural network

Abstract Dried figs are a garden produce that must be graded after harvesting. Moisture levels and contaminated blank two of the most critical effective elements on marketability dried figs, they highly related to fig quality. In present research, an intelligent system was employed classify based moisture content infected fruits. Capacitance characteristics, average diameter, fruit area were all taken into account in this study. The dielectric constant measured at six different frequency levels: 12, 22, 32, 42, 52, 62 MHz. best then chosen using improved distance evaluation feature selection approach. Image processing also used determine diameter figures. Following that, frequency, as input parameters artificial neural network classification model describe porosity level fig. essential information relating frequencies 22 52 MHz, respectively. Finally, accuracy 95.7% for 91.3% attained. results demonstrated excellent performance capabilities proposed approach rating internal quality figs.