Exploiting Pattern Set Dissimilarity for Detecting Changes in Communication Networks

  • Angelo ImpedovoEmail author
  • Corrado Loglisci
  • Michelangelo Ceci
  • Donato Malerba
Part of the Studies in Computational Intelligence book series (SCI, volume 880)


Communication networks are inherently dynamic and the changes are often due to unpredicted causes, for instance, failures of the devices or bulks of user requests. To guarantee the continuation of the services, the providers should keep the typical activities of control and management of the network aligned with respect to these changes. They should handle both the evolution of the network and complexity of the infrastructure, while, actually, most of the existing technologies do not adopt update mechanisms or deal with the problem only for specific categories of networks. We propose a data mining approach to analyze evolving communication data while accounting for the whole network and its parts (devices and connections). The approach is able to detect changes that denote substantial and statistically evident variations in the communication modalities. Changes correspond to variations appearing in the frequent sub-networks discovered from evolving communication data: variations in the frequent sub-networks denote changes occurring in the raw data. We perform experimental evaluation on both real and synthetic networks and provide quantitative and qualitative results.


  1. 1.
    Bell, S., McDiarmid, A., Irvine, J.: Nodobo: Mobile phone as a software sensor for social network research. In: Proceedings of the 73rd IEEE Vehicular Technology Conference, VTC Spring 2011, 15–18 May 2011, Budapest, Hungary, pp. 1–5. IEEE (2011)Google Scholar
  2. 2.
    Berlingerio, M., Coscia, M., Giannotti, F., Monreale, A., Pedreschi, D.: Evolving networks: Eras and turning points. Intell. Data Anal. 17(1), 27–48 (2013)CrossRefGoogle Scholar
  3. 3.
    Brauckhoff, D., Dimitropoulos, X.A., Wagner, A., Salamatian, K.: Anomaly extraction in backbone networks using association rules. IEEE/ACM Trans. Netw. 20(6), 1788–1799 (2012)CrossRefGoogle Scholar
  4. 4.
    Ceci, M., Loglisci, C., Macchia, L.: Ranking sentences for keyphrase extraction: a relational data mining approach. Procedia Comput. Sci. 38, 52–59 (2014). Scholar
  5. 5.
    Chakrabarti, D., Faloutsos, C.: Graph Mining: Laws, Tools, and Case Studies. Synthesis Lectures on Data Mining and Knowledge Discovery. Morgan & Claypool Publishers, San Rafael (2012)Google Scholar
  6. 6.
    Cheng, H., Tan, P., Potter, C., Klooster, S.A.: A robust graph-based algorithm for detection and characterization of anomalies in noisy multivariate time series. In: ICDM Workshops, pp. 349–358. IEEE Computer Society (2008)Google Scholar
  7. 7.
    Gama, J., Gaber, M.M.: Learning from Data Streams: Processing Techniques in Sensor Networks. Springer, Berlin (2007)CrossRefGoogle Scholar
  8. 8.
    He, W., Hu, G., Zhou, Y.: Large-scale IP network behavior anomaly detection and identification using substructure-based approach and multivariate time series mining. Telecommun. Syst. 50(1), 1–13 (2012)CrossRefGoogle Scholar
  9. 9.
    Kim, T., Cho, S.: Web traffic anomaly detection using C-LSTM neural networks. Expert Syst. Appl. 106, 66–76 (2018)CrossRefGoogle Scholar
  10. 10.
    Koh, Y.S.: CD-TDS: change detection in transactional data streams for frequent pattern mining. In: 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, BC, Canada, July 24–29, 2016, pp. 1554–1561 (2016)Google Scholar
  11. 11.
    Loglisci, C., Ceci, M., Impedovo, A., Malerba, D.: Mining microscopic and macroscopic changes in network data streams. Knowl.-Based Syst. 161, 294–312 (2018)CrossRefGoogle Scholar
  12. 12.
    Loglisci, C., Ceci, M., Malerba, D.: Discovering evolution chains in dynamic networks. In: Appice, A., Ceci, M., Loglisci, C., Manco, G., Masciari, E., Ras, Z.W. (eds.) First International Workshop, NFMCP 2012, ECML/PKDD 2012, UK, 2012, Revised Selected Papers, Lecture Notes in Computer Science, vol. 7765, pp. 185–199. Springer (2012). Scholar
  13. 13.
    Loglisci, C., Malerba, D.: Leveraging temporal autocorrelation of historical data for improving accuracy in network regression. Stat. Anal. Data Min. 10(1), 40–53 (2017)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Nohuddin, P.N.E., Coenen, F., Christley, R., Setzkorn, C., Patel, Y., Williams, S.: Finding “interesting” trends in social networks using frequent pattern mining and self organizing maps. Knowl.-Based Syst. 29, 104–113 (2012)CrossRefGoogle Scholar
  15. 15.
    Ranshous, S., Shen, S., Koutra, D., Harenberg, S., Faloutsos, C., Samatova, N.F.: Anomaly detection in dynamic networks: a survey. Wiley Interdiscip. Rev. Comput. Stat. 7(3), 223–247 (2015)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Sanctis, M.D., Bisio, I., Araniti, G.: Data mining algorithms for communication networks control: concepts, survey and guidelines. IEEE Netw. 30(1), 24–29 (2016)CrossRefGoogle Scholar
  17. 17.
    Tan, P., Steinbach, M., Kumar, V.: Introduction to Data Mining. Addison-Wesley, Boston (2005)Google Scholar
  18. 18.
    Tran, D., Gaber, M.M., Sattler, K.: Change detection in streaming data in the era of big data: models and issues. SIGKDD Explor. 16(1), 30–38 (2014)CrossRefGoogle Scholar
  19. 19.
    Wang, H., Tang, M., Park, Y., Priebe, C.E.: Locality statistics for anomaly detection in time series of graphs. IEEE Trans. Signal Process. 62(3), 703–717 (2014)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Wang, Y., Chakrabarti, A., Sivakoff, D., Parthasarathy, S.: Fast change point detection on dynamic social networks. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19–25, 2017, pp. 2992–2998 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Angelo Impedovo
    • 1
    Email author
  • Corrado Loglisci
    • 1
  • Michelangelo Ceci
    • 1
  • Donato Malerba
    • 1
  1. 1.Department of Computer ScienceUniversity of Bari Aldo MoroBariItaly

Personalised recommendations