Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Proposed Methodology: (a) Shows Phase I, where Parallel and Distributed Processing is Conducted; (b) Shows Phase II, which Includes the Training of Deep Learning Model Using None-faulty Data from Phase I, (c) Shows the Phase III, where the Output of the Faulty Processor is Produced Using Deep Learning Model.

More »

Fig 1 Expand

Fig 2.

Example of missing data in human gait dataset [50].

More »

Fig 2 Expand

Fig 3.

Some examples of missing data in driver distraction dataset [51].

More »

Fig 3 Expand

Table 1.

Datasets description.

More »

Table 1 Expand

Fig 4.

Driver distraction dataset results using four deep learning models.

More »

Fig 4 Expand

Table 2.

Driver distraction results.

More »

Table 2 Expand

Fig 5.

Gait human dataset results using four deep learning models.

More »

Fig 5 Expand

Table 3.

Human gait detection results.

More »

Table 3 Expand

Fig 6.

Vulnerability dataset results using four deep learning models.

More »

Fig 6 Expand

Fig 7.

Best vulnerability dataset results based on loss function.

More »

Fig 7 Expand

Fig 8.

Best missing vulnerability dataset results based on loss function.

More »

Fig 8 Expand

Fig 9.

KDD Cup99 dataset results using four deep learning models.

More »

Fig 9 Expand

Fig 10.

Best KDD Cup99 dataset results based on loss function.

More »

Fig 10 Expand

Fig 11.

Best missing KDD Cup99 dataset results based on loss function.

More »

Fig 11 Expand