earticle

영어

For providing security to computer systems various approaches like firewalls, anti-virus tool, network security tools, malware removal tools, monitoring tools and many more are being used in present scenario. Computer security tools available in present era need regular updating and monitoring. If any computer users do not regularly update the security tools, then the system may be infected by any virus or any other attack. In this paper a learning system is proposed to identify the operating system process as self and non-self using the concepts of Machine Learning. Three concepts of machine learning have been used to provide the efficient learning system. As a first concept the approach of Concept Learning and the general-to-specific ordering of hypotheses has been used in which Version Space has been generated using the Candidate-Elimination algorithm to provide the learning. As second concept Decision Tree Learning has been used in which ID3 algorithm has been used to construct a decision tree. As a third concept an Artificial Neural Network (ANN) has been used and this concept uses the Gradient Descent Algorithm. Finally, it has been observed that the Decision Tree and Artificial Neural Network learning are the best suited learning approach for identifying self and non-self process.