Applying Classification Methods for Spectrum Sensing in Cognitive Radio Networks: An Empirical Study

Spectrum sensing is the paramount aspect of cognitive radio network where a secondary user is able to utilize the idle channels of the licensed spectrum band in an opportunistic manner without interfering the primary (license) users. The channel (band) is

  • PDF / 180,289 Bytes
  • 8 Pages / 439.37 x 666.142 pts Page_size
  • 1 Downloads / 202 Views

DOWNLOAD

REPORT


Abstract Spectrum sensing is the paramount aspect of cognitive radio network where a secondary user is able to utilize the idle channels of the licensed spectrum band in an opportunistic manner without interfering the primary (license) users. The channel (band) is considered to be idle (free) when primary signal is absent. The channel accessibility (free) and non-accessibility (occupied) can be modeled as a classification problem where classification techniques can determine the status of the channel. In this work supervised learning techniques is employed for classification on the real-time spectrum sensing data collected in test bed. The power and signal-to-noise ratio (SNR) levels measured at the independent CR device in our test bed are treated as the features. The classifiers construct its learning model and give a channel decision to be free or occupied for unlabelled test instances. The different classification technique’s performances are evaluated in terms of average training time, classification time, and F1 measure. Our empirical study clearly reveals that supervised learning gives a high classification accuracy by detecting low-amplitude signal in a noisy environment.



Keywords Cognitive radio Spectrum sensing Supervised learning techniques

 Primary user detection

N. Basumatary (&)  N. Sarma  B. Nath Department of Computer Science and Engineering, Tezpur University, Napam, Assam, India e-mail: [email protected] N. Sarma e-mail: [email protected] B. Nath e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 A. Kalam et al. (eds.), Advances in Electronics, Communication and Computing, Lecture Notes in Electrical Engineering 443, https://doi.org/10.1007/978-981-10-4765-7_10

85

86

N. Basumatary et al.

1 Introduction Cognitive Radio (CR) is the emerging technology in the domain of new age wireless communication. It can dynamically change its transmission parameters based on changes in environmental factors [1]. In cognitive radio network a secondary or unlicensed user can sense the licensed channels for any opportunity to transmit, which results to efficiently utilize the available channel of primary licensed users. For performing this spectrum access in an opportunistic manner the CR devices need to sense the radio spectrum licensed to primary users. So, efficient spectrum sensing is very important for opportunistic spectrum access. In Cognitive Radio [2, 3] the spectrum sensing is carried out in a co-operative and independent manner. In co-operative sensing all the CR devices co-operate with each other to take a collective decision which results into get high sensing reliability. While, in case of independent sensing each CR device performs the sensing individually and make its own sensing decision to use unoccupied spectrum portion. Here, in this work analysis of the prominent supervised learning techniques [4–6] was done for noncooperating spectrum sensing framework to decide the presence or absence of primary user in a channel. In low SNR environment (fading channels) where there