Skip to main content

Advances, Systems and Applications

Table 8 Running time proportion of each function of the algorithm under different initial window sizes

From: Multi-type concept drift detection under a dual-layer variable sliding window in frequent pattern mining with cloud computing

Time ratio

10K

20 K

30 K

40 K

50 K

Reading data

5.7%

6.3%

5.2%

5.7%

5.4%

Update the window

0.3%

0.3%

0.3%

0.1%

0.3%

Short-window concept drift detection

0.2%

0.1%

0.1%

0.0%

0.1%

Handling of the mutant concept drift

8.9%

8.2%

8.9%

9.3%

8.9%

Update frequent pattern

83.9%

84.3%

84.7%

84.1%

84.5%

Long-window concept drift detection

0.1%

0.1%

0.1%

0.0%

0.0%

Handle the gradient concept drift

0.9%

0.8%

0.7%

0.8%

0.8%