5th International ICST Conference on Cognitive Radio Oriented Wireless Networks and Communications

Research Article

Automatic network recognition by feature extraction: A case study in the ISM band

Download678 downloads
  • @INPROCEEDINGS{10.4108/ICST.CROWNCOM2010.9274,
        author={Maria-Gabriella Di Benedetto and Stefano Boldrini and Carmen Juana Martin Martin and Jesus Roldan Diaz},
        title={Automatic network recognition by feature extraction: A case study in the ISM band},
        proceedings={5th International ICST Conference on Cognitive Radio Oriented Wireless Networks and Communications},
        publisher={IEEE},
        proceedings_a={CROWNCOM},
        year={2010},
        month={9},
        keywords={Cognitive networking  automatic network classification  network discovery},
        doi={10.4108/ICST.CROWNCOM2010.9274}
    }
    
  • Maria-Gabriella Di Benedetto
    Stefano Boldrini
    Carmen Juana Martin Martin
    Jesus Roldan Diaz
    Year: 2010
    Automatic network recognition by feature extraction: A case study in the ISM band
    CROWNCOM
    IEEE
    DOI: 10.4108/ICST.CROWNCOM2010.9274
Maria-Gabriella Di Benedetto1,*, Stefano Boldrini1, Carmen Juana Martin Martin1, Jesus Roldan Diaz1
  • 1: Info-Com Department, School of Engineering, University of Rome La Sapienza, via Eudossiana 18, 00184, Rome, Italy
*Contact email: dibenedetto@newyork.ing.uniroma1.it

Abstract

Automatic network recognition offers a promising framework for the integration of the cognitive concept at the network layer. This work addresses the problem of automatic classification of technologies operating in the ISM band, with particular focus on Wi-Fi vs. Bluetooth recognition. The proposed classifier is based on feature extraction related to time-varying patterns of packet sequences, i.e. MAC layer procedures, and adopts different linear classification algorithms. Results of classification confirmed the ability to reveal both technologies based on Mac layer feature identification.