Table 3 Performance evaluation of physiological/biochemical variables in the prediction of plant stress

From: Machine learning provides specific detection of salt and drought stresses in cucumber based on miRNA characteristics

Kernel type	Stress type	Model
		SVM		SVM-GA		SVM-PSO
		MSE	R²	MSE	R²	MSE	R²
Linear	Drought	0.98	0.73	0.91	0.76	0.90	0.76
	Salinity	1.20	0.66	1.13	0.68	1.18	0.67
	Drought + Salinity	0.82	0.79	0.80	0.79	0.75	0.82
Polynomial	Drought	1.37	0.60	1.31	0.62	1.30	0.63
	Salinity	1.13	0.68	1.07	0.70	1.04	0.71
	Drought + Salinity	1.17	0.67	1.15	0.68	1.07	0.70
Gaussian	Drought	0.94	0.75	0.92	0.75	0.88	0.77
	Salinity	0.92	0.75	0.87	0.77	0.90	0.76
	Drought + Salinity	1.28	0.63	1.19	0.66	1.27	0.64
Sigmoid	Drought	1.10	0.69	1.07	0.70	1.08	0.70
	Salinity	1.13	0.68	1.07	0.70	1.04	0.71
	Drought + Salinity	1.01	0.72	0.98	0.73	0.98	0.73

Back to article page

ISSN: 1746-4811

Contact us

Submission enquiries: journalsubmissions@springernature.com