JIA-2018-09

2004 TU Ke-ling et al. Journal of Integrative Agriculture 2018, 17(9): 1999–2006 only 53 of the 67 seeds were correctly and 14 were incorrectly classified by the multilayer perceptron network classifier. Therefore, the predicted germination percentage of category A was 79.1% with a predicted selection rate of 90.0%. Similarly for category B, the predicted germination percentage and selection rate of the test set were 79.1 and 89.7%, respectively. The stability rates of these two models were 99.4 and 99.9%, respectively. Stability rate is the ratio of accuracy rates of the test to training sets, where more similar rates indicate more stable models. The holdout set was used to independently assess the MLP network and the efficacy of these models. 3.4. Binary logistic regression As shown in Table 4, in category A, 101 of the 119 germinated seeds and 57 of the 81 un-germinated seeds were classified correctly, in the selected cases. Overall, the germination percentage of category A was 80.8% and was obtained by calculating the number of correctly predicted germinated seeds (101) and dividing it by the total of number of seeds predicted to germinate (101+24). The selection rate was 84.9%. Similarly, the germination percentage and selection rate of category B were 80.3 and 85.7%, respectively. Because the model appeared to be “over-fitting”, those pepper seeds that were not used to develop the model were selected as part of two validation sets, and the results were shown under the unselected cases columns in Table 4. The germination percentages of the validation set for category A and B were 80.2 and 81.7%, and the selection rates were 82.2 and 83.1%, respectively. The respective stability rates of the model for category A and B were 98.1 and 100%, respectively. 4. Discussion 4.1. Comparison of several results From Table 5, the seed selection based on a single predictor, germination percentage increased from 59.3 to 71.8% when a*≥3, with a selection rate at 57.8%. Germination percentage also increased from 59.3 to 79.4%, and the selection rate reached 76.8% when single- kernel weight≥0.0064g. Compared to the single predictor selection method based on a single feature predictor model, the selection based on multilayer perceptron network and binary logistic regression models obtained higher germination percentages while maintaining a high selection rate. Moreover, the stabilities of these models remained high. Thus, it was feasible to select kernels that would likely germinate using this model. A comparison of all the models showed that the multilayer perceptron neural network, with 15 features (ten color features: R, G, B, L*, a*, b*, hue, saturation, brightness, and Gray, three geometric features: width, length, and projected area, seed weight and density) employed as variables to determine seed quality Table 4 The classification table of binary logistic regression Category 1) Observed 2) Predicted for selected cases 2) Predicted for unselected cases 2) 0 1 Accuracy (%) 0 1 Accuracy (%) A Seeds 0 57 24 70.4 58 24 70.7 1 18 101 84.9 21 97 82.2 Overall percentage (%) 79.0 77.5 B Seeds 0 56 25 69.1 60 22 73.2 1 17 102 85.7 20 98 83.1 Overall percentage (%) 79.0 79.0 1) In category A, all 15 features were used as the independent variables; in category B, nine seed-vigor features were used as the independent variables. 2) 0, un-germinated seed; 1, germinated seed. Table 5 Comparison of model results Method 1) Category 2) Germination percentage (%) Selected rate (%) Stability (%) Feature a*≥3 71.8 57.8 / Weight≥0.0064 g 79.4 76.8 / MLP A 79.1 90.0 99.4 B 79.1 89.7 99.9 BLR A 80.8 84.9 98.1 B 80.3 85.7 100.0 1) MLP, multilayer perceptron; BLR, binary logistic regression. 2) In category A, all 15 features were used as the independent variables; in category B, nine seed-vigor features were used as the independent variables.