Research Area:  Machine Learning
The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and testing a neural network intrusion detection system model incorporating a hybrid algorithm composed on genetic and back propagation algorithms. The varying of the number of neurons in the architecture and hybrid algorithm provided quantitative data for determining these effects. It showed that changes in the model architecture affected the models ability to detect malicious behavior with a low failure rate.
Name of the Researcher:  Ray, Loye Lynn
Name of the Supervisor(s):  Henry Felch
Year of Completion:  2014
University:  Colorado Technical University
Thesis Link:   Home Page Url