Improvement of Software Maintenance and Reliability using Data Mining Techniques

This document discusses the implementation of a secured network-based intrusion detection system using the support vector machine (SVM) algorithm. It begins with an abstract that outlines hardening different intrusion detection implementations and proposals. The paper then discusses using naive Bayes, a classification method for intrusion detection, to analyze transmitted data for malicious content and block transmissions from corrupted hosts. It also discusses using flow correlation information to improve classification accuracy while minimizing effects on network performance.

This academic article summarizes a research paper that proposes a new process analysis method using process mining to discover user behaviors and predict the next application a user will access based on audit logs. The method introduces building a weighted directed graph to represent relationships between different processes accessed in user sessions. It then uses this "reference graph" and random walk theory to evaluate future user sessions and determine which processes are most likely to be explored next. The paper outlines collecting log data from multiple systems, managing the data using classification algorithms, and applying the proposed random walk technique to detect user behaviors and predict the next application.

This document presents a static malware detection system using data mining techniques. The system extracts raw features from Windows Portable Executable (PE) files including PE header information, DLLs, and API functions. It then selects important features using Information Gain and reduces dimensions using Principal Component Analysis. Three classifiers (SVM, J48, Naive Bayes) are trained on the transformed feature vectors to classify files as malicious or benign. When evaluated on a dataset of over 247,000 files, the system achieved a detection rate of 99.6%.