Skip to main content

Table 7 Dataset IV, and test 1 and 2 parameters

From: A graphical heuristic for reduction and partitioning of large datasets for scalable supervised training

Parameter of

Parameter

Test 1

Test 2

Dataset

# of data points

19,226

9613

Feature extraction

tf-idf

word2vec

Training/total ratio

0.75

0.75

Classification algorithm

Tensorflow CNN

LIBSVM

Step 2

\(C_I\)

\(e^{1.0}\)

\(e^{1.0}\)

\(C_E\)

\(e^{3.0}\)

\(e^{4.0}\)

Step 3

GS edge cut

400.01

3.50