ณัฐพล เกียรติวงศ์หงส์. Intelligent Log Analyzer. Master's Degree(Computer Engineering). King Mongkut's University of Technology Thonburi. KMUTT Library.. : King Mongkut's University of Technology Thonburi, 2010.
Abstract:
In this paper, I present a technique to analyze and correlate the different types of
computer log files. Log files are generated from servers and network devices to record
operations that occur in the computers and networks. As log files are too enormous to
manualize, I develop a tool to maximize accuracy as well as efficiency when high speed
processing is the goal. Firstly, I must improve the accuracy by using learning algorithms
to separate the normal operations from the abnormal ones. Those algorithms can be
divided into 1) measurement methods that are TF-IDF, Jaccard Distance, Simplified
Fellegi-Sunter and Jensen-Shannon and 2) decision algorithms that are rules based, Kmeans
clustering, and decision tree. Secondly, I may adjust parameters of algorithms for
less accuracy in order to gain higher speed for both with or without parallel processing
techniques. I also construct an adaptive learning algorithm to update the model. I also
flush out out-of-date data while the logs are being captured and processed. The results
are ranging between 70-80 percent and the false positive is below 5 percent.