Machine learning driven non-invasive approach of water content estimation in living plant leaves using terahertz waves

Table 13 The confusion accuracy with leave-one-observations-out cross-validation method of all leaves for each day along with monitoring the water content values for each day

Samples	Classes	Classifiers test accuracy performance (%)			Water content (%)
Samples	Classes	SVM	KNN	D-Tree	Water content (%)
Coffee leaf	Day1	100	100	100	82.84
	Day2	95.2	88.1	100	41.22
	Day3	100	92.6	92.3	12.34
	Day4	100	100	100	0.71
	Variance	0.58	1.09	0.92
Peashoot leaf	Day1	100	100	100	76.84
	Day2	100	87.5	87.5	49.22
	Day3	93.6	78.4	74.2	18.91
	Day4	95.0	89.3	91.7	0.21
	Variance	1.55	2.27	3.60
Baby spinach leaf	Day1	100	100	100	71.14
	Day2	100	100	100	34.22
	Day3	92.6	88.6	75.5	10.34
	Day4	94.7	89.7	91.3	0.10
	Variance	1.76	2.90	4.60

ISSN: 1746-4811