Applying Artificial Immune System for Outlier Detection: A Comparative Study

Outlier detection is a data mining meth od for discovering exceptional, abnormal or suspici ously unusual samples in a data set. Outliers typically represent the data rich but information poor dilemma. Data m ining methods are applied to solve this problem in broad range of application fields like credit card fraud detectio n, network intrusion detection, error extraction, clinical dis ea e researches and sport statistics. Besides class ica di tance based outlier detection techniques, nature-inspired evolu ti nary approaches exist for outlier detection. How ever, except some limited application fields, artificial immune systems are not applied to the fundamental outlier detection problem. In this study, we use the Artificial Immun e System Algorithm to solve the outlier detection p roblem. We compare the outlier detection performance of the Ar tificial Immune System with K-Nearest Neighbor Algo rithm, Distance Based Outlier Detection Algorithm and Box Plot method, using one artificial and two real-life datasets. When we compare the results, we found out that Arti ficial Immune System Algorithm gives better results and works with a lower error rate than the distance based met hods.

[1]  F. E. Grubbs.  Procedures for Detecting Outlying Observations in Samples , 1969 .

[2]  T. Santhanam,et al.  Application of CART Algorithm in Blood Donors Classification , 2010 .

[3]  Dimitri Lefebvre,et al.  Neural Networks and Fault Probability Evaluation for Diagnosis Issues , 2014, Comput. Intell. Neurosci..

[4]  Cheng-Jian Lin,et al.  Efficient Immune-Based Particle Swarm Optimization Learning for Neuro-Fuzzy Networks Design , 2008, J. Inf. Sci. Eng..

[5]  Andrew McCallum,et al.  Efficient clustering of high-dimensional data sets with application to reference matching , 2000, KDD '00.

[6]  Pradeep Ray,et al.  Artificial immune systems for the detection of credit card fraud: an architecture, prototype and preliminary results , 2012, Inf. Syst. J..

[7]  Bianca Zadrozny,et al.  Outlier detection by active learning , 2006, KDD '06.

[8]  Jidong Wang,et al.  An Improved Artificial Immune System-Based Network Intrusion Detection by Using Rough Set , 2012 .

[9]  Zaiying Wang,et al.  Adaptive fault-tolerant control based on artificial immune principle , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[11]  Krishna Kumar Tripathi,et al.  Survey on Credit Card Fraud Detection Methods , 2012 .

[12]  Walmir M. Caminhas,et al.  Design of an Artificial Immune System for fault detection: A Negative Selection Approach , 2010, Expert Syst. Appl..

[13]  Yumin Chen,et al.  Neighborhood outlier detection , 2010, Expert Syst. Appl..

[14]  Banu Diri,et al.  Software defect prediction using artificial immune recognition system , 2007 .

[15]  Joseph L. Breault,et al.  Data Mining Diabetic Databases: Are Rough Sets a Useful Addition? , 2001 .

[16]  Ronald K. Pearson,et al.  The problem of disguised missing data , 2006, SKDD.

[17]  Donald E. Brown,et al.  An Outlier-based Data Association Method for Linking Criminal Incidents , 2003, SDM.

[18]  S. Nithya,et al.  An Efficient Clustering Algorithm for , 2011 .

[19]  M.M. Deris,et al.  A Comparative Study for Outlier Detection Techniques in Data Mining , 2006, 2006 IEEE Conference on Cybernetics and Intelligent Systems.

[20]  Gregg H. Gunsch,et al.  An artificial immune system architecture for computer security applications , 2002, IEEE Trans. Evol. Comput..

[21]  VARUN CHANDOLA,et al.  Outlier Detection : A Survey , 2007 .

[22]  Sunita Sarawagi,et al.  Mining Surprising Patterns Using Temporal Description Length , 1998, VLDB.

[23]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[24]  Aboul Ella Hassanien,et al.  Artificial Immune System Inspired Intrusion Detection System Using Genetic Algorithm , 2012, Informatica.

[25]  Wei Wang,et al.  A comparison of outlier detection algorithms for ITS data , 2010, Expert Syst. Appl..

[26]  Jianzhong Li,et al.  Unsupervised Outlier Detection in Sensor Networks Using Aggregation Tree , 2007, ADMA.

[27]  Mehdi Sadeghi,et al.  Using artificial immunity network for face verification , 2014, Int. Arab J. Inf. Technol..

[28]  Raymond T. Ng,et al.  Algorithms for Mining Distance-Based Outliers in Large Datasets , 1998, VLDB.

[29]  Regina Y. Liu,et al.  DD-Classifier: Nonparametric Classification Procedure Based on DD-Plot , 2012 .

[30]  Shuchita Upadhyaya,et al.  Outlier Detection: Applications And Techniques , 2012 .

[31]  Douglas M. Hawkins.  Identification of Outliers , 1980, Monographs on Applied Probability and Statistics.

[32]  Youlin Shang,et al.  Semi-supervised outlier detection based on fuzzy rough C-means clustering , 2010, Math. Comput. Simul..

[33]  Yunus Dogan,et al.  Outlier Detection with Double-Sided Control Mechanism and Different Priority Weight Values for Network Security , 2010, 2010 Second World Congress on Software Engineering.

[34]  Takehisa Yairi,et al.  An approach to spacecraft anomaly detection problem using kernel feature space , 2005, KDD '05.

[35]  Muhammad Tahir Khan,et al.  Autonomous and Market-Based Fault Tolerant Algorithms for Multi-Robot Cooperation , 2014, J. Inf. Sci. Eng..

[36]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.