Modeling and Analysis of Intentional And Unintentional Security Vulnerabilities in a Mobile Platform Page: 69
xi, 149 pages : illustrations (chiefly color)View a full description of this dissertation.
Extracted Text
The following text was automatically extracted from the image on this page using optical character recognition software:
TABLE 7.4. Confusion matrices of the three classifiers in the TCV test procedure.
Naive Bayesian MLP Random Forest
Confusion Matrix Confusion Matrix Confusion Matrix
Class,- L S A L S A L S A
Leaders(L) 224 0 0 220 4 0 223 1 0
Spammers(S) 0 163 1 1 161 2 2 162 0
Associates(A) 0 0 140 4 2 134 0 0 140
Classification
Accuracy- 99.81% 97.54% 99.43%
TABLE 7.5. Confusion matrices of the three classifiers in the R66T test procedure.
Naive Bayesian MLP Random Forest
Confusion Matrix Confusion Matrix Confusion Matrix
Classt- L S A L S A L S A
Leaders(L) 75 0 0 73 1 1 75 0 0
Spammers(S) 0 56 0 0 55 1 0 56 0
Associates(A) 0 0 49 1 2 46 0 1 48
Classification
Accuracy- 100% 96.67% 99.44%
for each one of the 528 data records. For the MLP I have used 9 neurons (corresponding to the
components of the pattern vector) in the input layer, 11 neurons in the hidden layer, and 3 neurons
(corresponding to the 3 classes) in the output layer.
Since the classification results depend not only on the classifier chosen, but also on the
training procedure adopted, I have considered three training/test procedures as follows for this ex-
perimentation: i) Ten-fold cross validation (TCV) method- Here the data is split into 10 sub-parts,
and each sub-part is used in a round robin fashion as the test set with the remaining nine as training
sets, ii)R66T method where randomly Selected 66% records form the training set and the rest are
used for testing, and iii) 066T method where the first (oldest) 66% of the time ordered records form69
Upcoming Pages
Here’s what’s next.
Search Inside
This dissertation can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Dissertation.
Mohamed Issadeen, Mohamed Fazeen. Modeling and Analysis of Intentional And Unintentional Security Vulnerabilities in a Mobile Platform, dissertation, December 2014; Denton, Texas. (https://digital.library.unt.edu/ark:/67531/metadc700067/m1/83/: accessed July 18, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; .