Figure_9.tif (921.34 kB)
Download file

The performance of using prior knowledge as the weighted regularization.

Download (0 kB)
posted on 27.08.2014, 03:08 by Takanori Hasegawa, Rui Yamaguchi, Masao Nagasaki, Satoru Miyano, Seiya Imoto

This figure illustrates the effectiveness of the weighted regularization (prior knowledge) at simulation time interval using dataset (ii). The histogram represents the number of true positive (TP), false positive (FP), and false negative (FN) findings for each as red, blue, and green bars, respectively. Black lines with circles and crosses represent ‘precision rate (PR)’ and ‘recall rate (RR)’, respectively. The values of the histogram and lines correspond to the left and right axes, respectively.