Cooperative Spectrum Sensing with Data Mining of Multiple Users’ Historical Sensing Data

Cooperative Spectrum Sensing with Data Mining of
Multiple Users’ Historical Sensing Data

ABSTRACT:

•                           The current cooperative spectrum sensing still can not effectively exploit the temporal correlations among sensing data, especially the correlations between the current sensing data and the historical data.

•      This paper uses sticky hierarchical Dirichlet process-hidden Markov model to exploit the historical sensing data of multiple users, and classifies the historical sensing data into groups according to their latent spectrum states.

•       The proposed spectrum sensing algorithm can fuse the historical sensing data into prior knowledge, which can be used to improve the accuracy in spectrum decision.

•       Furthermore, a rejection process is proposed to filter out some sensing data with high uncertainty in classification, which guarantees the effectiveness of historical sensing data.

EXIXTING SYSTEM:

•                 Furthermore, the  sequential spectrum sensing data are temporally correlated, which means their spectrum states may keep consistent in high probability.

•      The historical sensing data will be classified according to their statistical property, and some historical sensing data that can not be classified clearly will be rejected through rejection process.

•      Due to the uncertainty of spectrum sensing data, the rejection process is proposed to remove uncorrelated spectrum sensing data, in order to ensure the effectiveness of Bayesian inference.

•      Historical sensing data are fused into prior knowledge using sticky HDP-HMM, where temporal correlation and statistical correlation are exploited, in order to reduce the uncertainty of current spectrum sensing and improve the accuracy of spectrum decision.

PROPOSED SYSTEM:

•                 In this paper, a novel cooperative spectrum sensing algorithm has been proposed, where the sticky HDP-HMM model is adopted to exploit the historical sensing data.

•      The historical sensing data has been refined through rejection process, in order to filter out some sensing data with high uncertainty.

•      In the proposed cooperative spectrum sensing algorithm, the CRF-LC model could achieve the exploitation of the temporal correlations among sensing data, and thus the spectrum decision performance can be improved.

•      The proposed algorithm has more than 10%, 60%, 5% detection probability improvement under false alarm probability 0.2, compared with centralized spectrum sensing algorithm, Consensus spectrum sensing algorithm and DP-based spectrum sensing algorithm, respectively.

HARDWARE REQUIREMENTS:

•      Processor             -        Pentium –III

•       Speed                  -        1.1 Ghz

•       RAM                   -        256 MB(min)

•       Hard Disk           -         20 GB

•       Key Board           -        Standard Windows                                                          Keyboard

•      Mouse                  -        Two or Three Button Mouse

•      Monitor                -        SVGA

SOFTWARE REQUIREMENTS:

•                Tool                    -        MATLAB R2012

•      Operating system    -       Windows Xp, 7

REFERENCES:

•          H. Ning, H. Liu, J. Ma, L.T. Yang, Y. Wan, X. Ye, and R.Huang, “From Internet to Smart World,” IEEE Access, vol.3, pp. 1994-1999, Aug. 2015.

•      C. Thomes, “The National Broadband Plan: Connecting America,” Government information quarterly, vol. 28,  no. 3, pp. 435-436, Jul. 2011.

•      J. Mitola III, “Cognitive Radio for Flexible Mobile Multimedia Communications,” Mobile Networks and Applications, vol. 6, no. 5, pp. 435-441, Sep. 2006.