X=NSL_KDD the performance evaluation of STL for the NIDS,

X=NSL_KDD Dataset/KDD Train.txt;T= NSL_KDD Dataset/KDD Test.txt;X,T =NSL_KDD Dataset;

rng(0,’twister’); % For reproducibility

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

hiddenSize = 15;






features1 = encode(autoenc1,X);

hiddenSize = 10;

autoenc2 = trainAutoencoder(features1,hiddenSize,…






features2 = encode(autoenc2,features1);

softnet =


deepnet = stack(autoenc1,autoenc2,softnet);

deepnet = train(deepnet,X,T);

NSL_KDD_type = deepnet(X);





Feature Learning
from pre-processed data


Soft-max Regression
classifier training for the derived training data




                          Self-taught Learning

using self-taught learning


                                         Figure 3


4.2. Performance Evaluation

To ascertain the performance evaluation of STL for the
NIDS, execute three types of classification

Normal and
anomaly (2-class)

Normal and four
different attack categories(5-class)

Normal and 22
different attack (23- class)



Evaluate the accuracy metric using the following

  Accuracy: “which
is the percentage of correctly classified records over the total number of


 Precision (P): which is the percentage ratio of the number of “true
positives” (TP) records divided by the number of true positives (TP) and false
positives (FP) classified records.




Recall (R): which is the percentage ratio of number of “true positives
records” divided by the number of true positives and false negatives (FN)
classified records.




(F): The harmonic mean of precision and
recall and represents a balance between them.




4.2.1 Evaluation Based on training dataset

Create a 10- fold cross validation on the training
data to classify the accuracy of STL for 2-class,5-class and 23-class.
Thereafter compare its performance with the soft-max regression when its
applied on the NSL-NDD data set without feature learning.








          Accuracy for various Classification

Figure 4


If the Accuracy is evaluated
for 2, 5, and 23-classes, the STL should achieved >98% accuracy 4. for all


4.2.2 Evaluation Based on training with test dataset

Evaluate the STL and SMR
for class 2 and 5 – class using the test data. Perform the accuracy metric for
the STL



for various Classification”


                                          Figure 5


If applied on testing
and training data, the STL should achieved accuracy of ~88% for 2-class 4
which is far better than other previous researched methods


I'm Neil!

Would you like to get a custom essay? How about receiving a customized one?

Check it out