Spectrum Handoff by Baum-Welch algorithm for services in Cognitive Radio Networks
Deepak Kumar. V1, Gokulamaanickam. B2, S. Nandakumar3

1Deepak Kumar. V, Department of Electronics and Communication Engineering, Vellore Institute of Technology, Vellore, India.
2Gokulamaanickam. B, Department of Electronics and Communication Engineering, Vellore Institute of Technology, Vellore, India.
3S. Nandakumar, Department of Electronics and Communication Engineering, Vellore Institute of Technology, Vellore, India. 

Manuscript received on September 16, 2019. | Revised Manuscript received on 24 September, 2019. | Manuscript published on October 10, 2019. | PP: 1717-1721 | Volume-8 Issue-12, October 2019. | Retrieval Number: L31841081219/2019©BEIESP | DOI: 10.35940/ijitee.L3184.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Cognitive Radio Networks (CRN) is the upcoming future prospect in 5G networks. Lack of available spectrum is a serious problem in the networking industry nowadays since, for each individual organization only a limited spectrum bandwidth is offered by National Telecommunications and Information Administration (NTIA). The problem arises due to the increase in the number of users who are supposed to use a limited amount of available bandwidth. Using spectrum handoff allows a cognitive user to access the available licensed spectrum in the absence of the primary user in that particular channel. Efficient spectrum sensing has to be done to check the availability of unused spectrum holes. Machine learning models such as Markov model and Hidden Markov model are used to predict the probabilities. In this paper we have presented a model for efficient sensing using Baum-Welch algorithm, a neural network algorithm which can train inner layer channel traits for given sequence of switching services to yield accurate results without huge datasets. Following emission probabilities are obtained for the channels that are trained from transition probabilities of channel services such as video, voice and data. From the obtained probability values each channel can be offered with best suited services. Keywords: Baum-Welch algorithm, Cognitive Radio Networks (CNR), Emission Probability, Hidden Markov model (HMM), Markov model, Transition Probability.
Keywords: Fuzzy Number, Hexagonal Fuzzy
Scope of the Article: Algorithm Engineering