Skip to main content
. 2011 Nov 10;6(11):e27602. doi: 10.1371/journal.pone.0027602

Table 3. Pearson correlation coefficient of each integrated characteristic method.

Mechanism Integrated method r a r b
SVR Binary + F162 0.756 0.534
Binary + F85 0.696 0.563
Binary + F65 0.688 0.564
Binary + F47 0.679 0.543
Hybrid + F162 0.773 0.534
Hybrid + F85 0.686 0.577
Hybrid + F65 0.678 0.588
Hybrid + F47 0.670 0.541
Neural networkc Binary + F162 0.783 0.566
Binary + F85 0.691 0.579
Binary + F65 0.686 0.585
Binary + F47 0.680 0.580
Hybrid + F162 0.784 0.562
Hybrid + F85 0.685 0.579
Hybrid + F65 0.678 0.586
Hybrid + F47 0.670 0.580
a

Pearson correlation coefficient of integrated methods trained with dataset A.

b

Pearson correlation coefficient of integrated methods validated with dataset B.

c

Neural network has an input layer of two nodes, a hidden layer of six nodes, and an output layer of one node.