An efficient network traffic classification based on vital random forest for high dimensional dataset / \c Alhamza Munther Wardi Alalousi
The aim this thesis is to propose a Vital Random Forest (VRF); an efficient network traffic classification for high dimensional dataset. VRF is a onepackage introducing a new features selection technique, data inputs reduction and a new build model for random forest method. The objectives are as fol...
Saved in:
| Main Author: | |
|---|---|
| Corporate Author: | |
| Format: | Thesis Book |
| Language: | English |
| Published: |
Perlis, Malaysia
School of Computer and Communication Engineering, Universiti Malaysia Perlis
2017
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The aim this thesis is to propose a Vital Random Forest (VRF); an efficient network traffic classification for high dimensional dataset. VRF is a onepackage introducing a new features selection technique, data inputs reduction and a new build model for random forest method. The objectives are as follows ; to design a new features selection technique based on four techniques and two filters targeted to reduce both the processing time and the memory space, and keep high accuracy ; to implement redundant inputs removal based on data reduction and the abovementioned proposed features selection technique to reduce memory consumption ; to design a new build model for random forest method called active build model ABRF which is built based on active trees only in order to increase accuracy classificationwith low processing time ; to evaluate the proposed Vital Random Forest (VRF)in terms of classification accuracy, processing time and memory consumption, thereafter compare VRF with original Random Forest and state-of-art methods. |
|---|---|
| Physical Description: | xxi, 180 pages colour illustrations 30 cm |
| Bibliography: | Includes bibliographical references. |