Statistical Flow Classification for the IoT

  • Gennaro Cirillo
  • Roberto PasseroneEmail author
  • Antonio Posenato
  • Luca Rizzon
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 627)


The objective of this work is to analyze packet flows and classify them as traffic that belongs to IoT devices or to traditional non-IoT communication. We employ two methods: a clustering approach, which learns directly from the structure of the dataset, and a classification tree, trained with the collected data and evaluated using 10-fold cross validation. The results show that classification trees outperform clustering on all datasets, and achieve high accuracy on both homogeneous simulated and real deployment traffic data.


IoT Traffic classification Clustering J48 


  1. 1.
    Witten IH, Frank E, Hall MA, Pal CJ (2016) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, CambridgeGoogle Scholar
  2. 2.
    Grimaudo L, Mellia M, Baralis E (2012) Hierarchical learning for fine grained internet traffic classification. In: Proceedings of IWCMC, Aug 2012Google Scholar
  3. 3.
    Fontugne R et al (2010) Mawilab: Combining diverse anomaly detectors for automated anomaly labeling and performance benchmarking. In: ACM CoNEXT10, Dec 2010Google Scholar
  4. 4.
    Sivanathan A, Habibi Gharakheili H, Loi F, Radford A, Wijenayake C, Vishwanath A, Sivaraman V (2018) Classifying IoT devices in smart environments using network traffic characteristics. IEEE Trans Mob ComputGoogle Scholar
  5. 5.
    Shafiq MZ, Ji L, Liu AX, Pang J, Wang J (2013) Large-scale measurement and characterization of cellular machine-to-machine traffic. IEEE/ACM Trans Netw 21(6):1960–1973CrossRefGoogle Scholar
  6. 6.
    Grimaudo L, Mellia M, Baralis E, Keralapura R (2014) SeLeCT: self-learning classifier for internet traffic. IEEE Trans Netw Serv Manage 11(2):144–157CrossRefGoogle Scholar
  7. 7.
    Pant V, Passerone R, Welponer M, Rizzon L, Lavagnolo R (2017) Efficient neural computation on network processors for IoT protocol classification. In: Proceedings of the first new generation of circuits and systems conference, NGCAS 2017, Genova, Italy, 7–9 Sept 2017Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Gennaro Cirillo
    • 1
  • Roberto Passerone
    • 1
    Email author
  • Antonio Posenato
    • 2
  • Luca Rizzon
    • 2
  1. 1.DISIUniversity of TrentoPovoItaly
  2. 2.Microtel Innovation SrlBorgo ValsuganaItaly

Personalised recommendations