Prediction and optimization of indirect shoot regeneration of Passiflora caerulea using machine learning and optimization algorithms

Table 2 Performance criteria of machine learning algorithms for indirect de novo shoot regeneration of P. caerulea in training and testing subsets

Output	ML Model	subset	R²	RMSE	MAE
Regeneration rate	GRNN	Training	0.99	2.65	0.00
	GRNN	Testing	0.99	3.08	1.21
	RF	Training	0.97	3.02	0.29
	RF	Testing	0.96	3.12	1.45
Shoot number	GRNN	Training	0.99	0.21	0.00
	GRNN	Testing	0.98	0.43	0.14
	RF	Training	0.98	0.45	0.02
	RF	Testing	0.97	0.63	0.25
Shoot length	GRNN	Training	0.94	0.18	0.00
	GRNN	Testing	0.89	0.31	0.07
	RF	Training	0.91	0.25	0.04
	RF	Testing	0.86	0.43	0.12

GRNN: generalized regression neural network; MAE: mean absolute error; ML; machine learning; R²: coefficient of determination; RF: random forest; RMSE: root mean square error.

ISSN: 1472-6750