6th International ICST Conference on Cognitive Radio Oriented Wireless Networks and Communications

Research Article

Automatic Modulation Classification in Wireless Disaster Area Emergency Network (W-DAEN)

Download165 downloads
  • @INPROCEEDINGS{10.4108/icst.crowncom.2011.245915,
        author={Md Abdur Rahman and Azril Haniz and Minseok Kim and Jun-ichi Takada},
        title={Automatic Modulation Classification in Wireless Disaster Area Emergency Network (W-DAEN)},
        proceedings={6th International ICST Conference on Cognitive Radio Oriented Wireless Networks and Communications},
        publisher={IEEE},
        proceedings_a={CROWNCOM},
        year={2012},
        month={5},
        keywords={Modulation classification emergency network SSC time-frequency},
        doi={10.4108/icst.crowncom.2011.245915}
    }
    
  • Md Abdur Rahman
    Azril Haniz
    Minseok Kim
    Jun-ichi Takada
    Year: 2012
    Automatic Modulation Classification in Wireless Disaster Area Emergency Network (W-DAEN)
    CROWNCOM
    IEEE
    DOI: 10.4108/icst.crowncom.2011.245915
Md Abdur Rahman1,*, Azril Haniz1, Minseok Kim1, Jun-ichi Takada1
  • 1: Tokyo Institute of Technology
*Contact email: abdur@ap.ide.titech.ac.jp

Abstract

Post-disaster situation requires quick and effective rescue efforts by the first responders. Generally the rescue teams use wireless radios for intra-agency communications. Lack of collaboration among different rescue agencies may create interference among the emergency radios. Identification of some physical parameters of these active radios is necessary for collaboration. Carrier frequency and bandwidth can be estimated by spectrum sensing, whereas modulation classification requires further signal processing and classification operations. Processing speed and performance of the classification system can be controlled by appropriate selection of signal parameters, signal processing techniques and the classification algorithms. A wireless disaster area emergency network (W-DAEN) can be installed in the disaster area to detect and capture data (time samples) of the occupied frequencies. This study consists of some simulation results of a machine learning based cooperative automatic modulation classification technique by using six unique features. The classification performance and processing time of the proposed algorithm is quite satisfactory for real-time classification system.