An Effective Intrusion Detection System Using Flawless Feature Selection, Outlier Detection and Classification

  • Rajesh Kambattan KovarasanEmail author
  • Manimegalai Rajkumar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 713)


Intrusion detection system (IDS) is playing crucial role to provide the security in the fastest world by protecting the internet applications such as healthcare applications, government secret information, secret banking data and intellectual properties of various scientists. In this paper, we propose new intrusion detection system for improving the detection rate. The proposed system is the combination of feature selection, outlier detection and classification. First, a newly proposed feature selection algorithm called intelligent flawless feature selection algorithm (IFLFSA) is used for selecting optimal number of features which are most useful for identifying the attacks. Second, the proposed entropy-based weighted outlier detection (EWOD) technique is used to identify the outliers from the data set. Third, the existing classification algorithm called intelligent layered approach for effective classification is used. The experiments have been conducted for evaluating the proposed model using the KDD data set. The proposed system achieved better detection accuracy in terms of high detection accuracy and low error rate.


Intrusion detection system Feature selection Outlier detection Classification Flawless feature selection Layered approach 


  1. 1.
    Ru, X., Liu, Z., Huang, Z., Jiang, W.: Normalized residual-based constant false-alarm rate outlier detection. Pattern Recogn. 69, 1–7 (2016)CrossRefGoogle Scholar
  2. 2.
    Aljawarneh, S., Aldwairi, M., Yassein, M.B.: Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model. J. Computat. Sci. Elsevier (2017)Google Scholar
  3. 3.
    Bai, M., Wang, X., Xin, J., Wang, G.: An efficient algorithm for distributed density-based outlier detection on big data. Neurocomputing 181, 19–28 (2016)CrossRefGoogle Scholar
  4. 4.
    Bandyopadhyay, S., Santra, S.: Agenetic approach for efficient outlier detection in projected space. Pattern Recogn. 41, 1338–1349 (2008)CrossRefGoogle Scholar
  5. 5.
    Zhang, J., Yu, X., Li, Y., Zhang, S., Xun, Y., Qin, X.: A relevant subspace based contextual outlier mining algorithm. Knowl. Based Syst. 99, 1–9 (2016)CrossRefGoogle Scholar
  6. 6.
    Bouarfa, L., Dankelman, J.: Workflow mining and outlier detection from clinical activity logs. J. Biomed. Inform. 45, 1185–1190 (2012)CrossRefGoogle Scholar
  7. 7.
    Pai, H.T., Wua, F., Hsueh, S.P.Y.: A relative patterns discovery for enhancing outlier detection in categorical data. Decis. Support Syst. 67, 90–99 (2014)CrossRefGoogle Scholar
  8. 8.
    Kuna, H.D., García-Martinez, R., Villatoro, F.R.: Outlier detection in audit logs for application systems. Inf. Syst. 44, 22–33 (2014)CrossRefGoogle Scholar
  9. 9.
    Muiioz, A., Muruzhbal, J.: Self-organizing maps for outlier detection. Neurocomputing 18, 33–60 (1998)CrossRefGoogle Scholar
  10. 10.
    Fraiman, R., Gimenez, Y., Svarc, M.: Feature selection for functional data. J. Multivar. Anal. 146, 191–208 (2016)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Wang, H., Feng, Y., Sa, Y., Lu, J.Q., Ding, J., Zhang, J., Hu, X.H.: Pattern recognition and classification of two cancer cell lines by diffraction imaging at multiple pixel distances. Pattern Recogn. 61, 234–244 (2016)CrossRefGoogle Scholar
  12. 12.
    Zhou, Y., Huang, T., Huang, G., Zhang, N., Kong, X.Y., Cai, Y.D.: Prediction of protein N-formulation and comparison with N-acetylation based on a feature selection method. Neuro Comput. 217, 53–62 (2016)Google Scholar
  13. 13.
    Fung, C.J., Zhu, Q.: FACID: a trust-based collaborative decision framework for intrusion detection networks. Adhoc Netw. 53, 17–31 (2016)Google Scholar
  14. 14.
    Ganapathy, S., Jaisankar, N., Yogesh, P., Kannan, A.: An intelligent system for intrusion detection using outlier detection. In: IEEE Conference on Recent Trends in Information Technology, pp. 3–5 (2011)Google Scholar
  15. 15.
    Ganapathy, S., Vijayakumar, P., Yogesh, P., Kannan, A.: An intelligent CRF based feature selection for effective intrusion detection. Int. Arab J. Inf. Technol. 13(1), 44–50 (2016)Google Scholar
  16. 16.
    Subba, B., Biswas, S., Karmakar, S.: Intrusion detection in mobile Ad-hoc networks: Bayesian game formulation. Eng. Sci. Technol. 19, 782–799 (2016)Google Scholar
  17. 17.
    Zorarpac, E., Ozel, S.A.: A hybrid approach of differential evolution and artificial bee colony for feature selection. Exp. Syst. Appl. 62, 91–103 (2016)CrossRefGoogle Scholar
  18. 18.
    Pölsterl, S., Conjeti, S., Navab, N., Katouzian, A.: Survival analysis for high-dimensional, heterogeneous medical data: exploring feature extraction as an alternative to feature selection. Artif. Intell. Med. 72, 1–11 (2016)CrossRefGoogle Scholar
  19. 19.
    Raza, M.S., Qamar, U.: An incremental dependency calculation technique for feature selection using rough sets. Inf. Sci. 343–343, 41–65 (2016)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Krawczyk, B., Wozniak, M.: Dynamic classifier selection for one-class classification. Knowl. Based Syst. 107, 43–53 (2016)CrossRefGoogle Scholar
  21. 21.
    KDD Cup 1999 Intrusion Detection Data (2010).
  22. 22.
    Usha, G., Rajesh Babu, M., Saravana Kumar, S.: Dynamic anomaly detection using cross layer security in MANET. Comput. Electr. Eng. Elsevier 59, 231–241 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Rajesh Kambattan Kovarasan
    • 1
    Email author
  • Manimegalai Rajkumar
    • 2
  1. 1.Department of Computer Science and EngineeringDhaanish Ahmed College of EngineeringChennaiIndia
  2. 2.Department of Information TechnologyPSG College of TechnologyCoimbatoreIndia

Personalised recommendations