Artificial Neural Networks as a Monitoring System in Linux
Abstract
This thesis attempts to show how artificial neural networks can be used to implement computer monitoring systems based on internal state in the operating system running on the computer. Through experiments it will show how to implement such a system for Linux and show that this is a viable method for computer system monitoring. Through exposing the frequencies of system call invocations in the Linux kernel, the neural network will attempt to classify the system state according to training.