LEEANDSEO
13of 19
Autoencoder
LSTM−Autoencoder
AUC =
AUC =
0.694
0.715
0.0
0.2
0.4
0.6
0.8
1.0
0.0
0.2
0.4
0.6
0.8
1.0
False Positive Rate
False Positive Rate
Decision Tree
SVM
AUC =
AUC =
0.378
0.594
0.0
0.2
0.4
0.6
0.8
1.0
0.0
0.2
0.4
0.6
0.8
1.0
False Positive Rate
False Positive Rate
RD−LNN
CL−LNN
AUC =
AUC =
0.724
0.601
0.0
0.2
0.4
0.6
0.8
1.0
0.0
0.2
0.4
0.6
0.8
1.0
False Positive Rate
False Positive Rate
FIGURE 5 ROC curves of six different methods. ROC, receiver operating characteristic
4.2 Effects of window size and the number of normal instances In this subsection, the key parameters which highly influence the performance of RD-LNN are examined. First, the win- dowsize m = 20 was determined based on the experiment considering F-measure as well as running time which is also an important factor when it is deployed in the real-life application. Figure 7 represents how F-measure and running time 3 are varied over window size m . F-measure shows the downward trend as the window size is increased while running time is increasing almost linearly due to the fact that lager window size demands more computation to estimate the distance. The relationship between F-measure and window size indicates that we need to find the optimal window size to capture the appropriate patterns that the failures might have. We substitute zero for F-measure when the algorithm is not able to detect the true failure 2 minutes earlier. It is noted that 20 window size shows good performance with decent computing burden, and it is used as the number of window sizes of the proposed algorithm in this article.
3 Running time can be varied based on computer performance. The computer specification used in this experiment: Windows 10 Pro, Intel Core i7, 16 GB RAM, 64-bit
Made with FlippingBook - Online catalogs