%0 Journal Article %1 song:2005:TEC %A Song, Dong %A Heywood, Malcolm I. %A Zincir-Heywood, A. Nur %D 2005 %J IEEE Transactions on Evolutionary Computation %K (DSS), (artificial KDD-99 RSS-DSS algorithm, algorithms, anomaly cost data data, dataset detection detection, dynamical filtering, fitness function, functions, genetic hierarchical intelligence), intrusion large learning mining, of programming programming, real-world security selection set,Dynamic sets subset training, %N 3 %P 225--239 %R doi:10.1109/TEVC.2004.841683 %T Training genetic programming on half a million patterns: an example from anomaly detection %V 9 %X The hierarchical RSS-DSS algorithm is introduced for dynamically filtering large datasets based on the concepts of training pattern age and difficulty, while using a data structure to facilitate the efficient use of memory hierarchies. Such a scheme provides the basis for training genetic programming (GP) on a data set of half a million patterns in 15 min. The method is generic, thus, not specific to a particular GP structure, computing platform, or application context. The method is demonstrated on the real-world KDD-99 intrusion detection data set, resulting in solutions competitive with those identified in the original KDD-99 competition, while only using a fraction of the original features. Parameters of the RSS-DSS algorithm are demonstrated to be effective over a wide range of values. An analysis of different cost functions indicates that hierarchical fitness functions provide the most effective solutions.

@article{song:2005:TEC, abstract = {The hierarchical RSS-DSS algorithm is introduced for dynamically filtering large datasets based on the concepts of training pattern age and difficulty, while using a data structure to facilitate the efficient use of memory hierarchies. Such a scheme provides the basis for training genetic programming (GP) on a data set of half a million patterns in 15 min. The method is generic, thus, not specific to a particular GP structure, computing platform, or application context. The method is demonstrated on the real-world KDD-99 intrusion detection data set, resulting in solutions competitive with those identified in the original KDD-99 competition, while only using a fraction of the original features. Parameters of the RSS-DSS algorithm are demonstrated to be effective over a wide range of values. An analysis of different cost functions indicates that hierarchical fitness functions provide the most effective solutions.}, added-at = {2008-06-19T17:35:00.000+0200}, author = {Song, Dong and Heywood, Malcolm I. and Zincir-Heywood, A. Nur}, biburl = {https://www.bibsonomy.org/bibtex/272cf7ee5f7d66e96cb347faabbc8f1fd/brazovayeye}, doi = {doi:10.1109/TEVC.2004.841683}, interhash = {ea2a6186317c1d8ffd37d55ac1bac3cd}, intrahash = {72cf7ee5f7d66e96cb347faabbc8f1fd}, issn = {1089-778X}, journal = {IEEE Transactions on Evolutionary Computation}, keywords = {(DSS), (artificial KDD-99 RSS-DSS algorithm, algorithms, anomaly cost data data, dataset detection detection, dynamical filtering, fitness function, functions, genetic hierarchical intelligence), intrusion large learning mining, of programming programming, real-world security selection set,Dynamic sets subset training,}, month = {June}, notes = {INSPEC Accession Number: 8458415 Quest Software Inc., Halifax, NS, Canada p226 only uses {"}8 of 41 features{"}. Linear GP, L-GP. p227 {"}No benefits were observed in making such a mutation operator field specific{"} p235 {"}not all training set patterns are equally significant{"}}, number = 3, pages = {225--239}, size = {15 pages}, timestamp = {2008-06-19T17:51:57.000+0200}, title = {Training genetic programming on half a million patterns: an example from anomaly detection}, volume = 9, year = 2005 }