Skip to main content

Table 12 Classification performance of all classifiers by applying leave-one-observation-cross-validation techniques with selected features

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

Quality metrics

Water content (%)

SVM

KNN

D-Tree

Coffee leaf

 Day 1

82.84

   

  SENS

 

1

1

1

  SPEC

 

1

1

1

 Day 2

41.22

   

  SENS

 

1

0.929

0.976

  SPEC

 

0.988

0.965

1

 Day 3

12.34

   

  SENS

 

0.963

0.889

1

  SPEC

 

1

0.912

0.99

 Day 4

0.51

   

  SENS

 

1

1

1

  SPEC

 

1

1

1

Peashoot

 Day 1

76.84

   

  SENS

 

1

1

1

  SPEC

 

1

1

1

 Day 2

49.22

   

  SENS

 

1

0.892

1

  SPEC

 

0.962

0.982

0.971

 Day 3

18.91

   

  SENS

 

0.545

0.727

0.636

  SPEC

 

0.984

0.967

0.984

 Day 4

0.21

   

  SENS

 

0.919

0.85

0.833

  SPEC

 

0.987

0.85

0.933

Spinach

 Day1

71.14

   

  SENS

 

0.995

1

1

  SPEC

 

1

1

1

 Day2

34.22

   

  SENS

 

1

1

1

  SPEC

 

0.976

1

1

 Day3

10.34

   

  SENS

 

0.909

0.545

0.851

  SPEC

 

0.923

0.949

0.897

 Day4

0.10

   

  SENS

 

0.727

0.818

0.636

  SPEC

 

0.974

0.872

0.949