期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：2
出版社：S.S. Mishra
摘要：In recent years there has been considerable interest in exploring the prospective of Artificial Immune Systems for applications in computer science and engineering. These systems are inspired by various aspects of the immune systems of mammals. Some of these aspects, such as the distinction between self and non-self and the concept of negative selection, have a natural and intuitive fit for applications involving computer security, network intrusion detection. Moreover, research into natural immune systems suggests the existence of learning properties which may be used to advantage in machine learning systems Artificial Immune Systems (AIS) are machine-learning algorithms that embody some of the principles and attempt to take advantages of the benefits of natural immune systems for use in tackling complex problem domains. The Artificial Immune Recognition System (AIRS), is one such supervised learning AIS that has shown significa nt success on broad range of classification problems. The AIRS algorithm is analysed from the perspective of reasonable design goals for an immune inspired AIS and a number of limitations and areas for improvement are identified. A number of original and borrowed augmentations, simplifications and changes to the AIRS algorithm are then proposed to addresses the identified areas. A professional-level implementation of the AIRS algorithm is produced and is provided as a plug-in for the WEKA machine-learning
