Abstract
Recent advancements in artificial neural networks (ANNs) motivated us to design a simple and faster spectrum prediction model termed the functional link artificial neural network (FLANN). The main objective of this paper is to gather realistic data to obtain utilization statistics for the industrial, scientific and medical band of 2.4–2.5 GHz. To present the occupancy statistics, we conducted measurement in indoors at the Swearingen Engineering Center, University of South Carolina. Further, we introduce different threshold-based spectrum prediction schemes to show the impact of threshold on occupancy, and propose a spectrum prediction algorithm based on FLANN to forecast a future spectrum usage profile from historical occupancy statistics. Spectrum occupancy is estimated and predicted by employing different ANN models including the Feed-forward multilayer perceptron (MLP), Recurrent MLP, Chebyshev FLANN and Trigonometric FLANN. It is observed that the absence of a hidden layer in FLANN makes it more efficient than the MLP model in predicting the occupancy faster and with less complexity. A set of illustrative results are presented to validate the performance of our proposed learning scheme.
Similar content being viewed by others
Notes
Our underlying assumption in this work is that occupancy varies diurnally, but is essentially statistically stationary (wide sense) over our entire measurement/prediction period. Hence, each pairwise difference is equally weighted.
References
Hossain E, Niyato D, Kim DI (2015) Evolution and future trends of research in cognitive radio: a contemporary survey. Wirel Commun Mobile Comput 15(11):1530–1564
Liang Q, Leung VCM, Meng W, Adachi F (2014) Cooperative communications and sensing. Wirel Commun Mobile Comput 14(13):1201–1203
Nekovee M (2009) Quantifying the availability of TV white spaces for cognitive radio operation in the UK. Communications workshops, 2009. In: ICC Workshops 2009. IEEE International Conference 2009; pp 1–5
Jayavalan S, Mohamad H, Aripin NM, Ismail A, Ramli N, Yaacob A, Ng MA (2014) Measurements and analysis of spectrum occupancy in the cellular and TV bands. Lect Notes Softw Eng 2(2):133–138
Martin FL, Correal NS, Ekl RL, Gorday P, O’Dea R (2008) Early opportunities for commercialization of TV whitespace in the US. In: Cognitive Radio Oriented Wireless Networks And Communications, 2008. CrownCom, pp 1–5
Petty VR, Rajbanshi R, Datla D, Weidling F, DePardo D, Kolodzy PJ, Marcus MJ, Wyglinski AM, Evans JB, Minden GJ, Roberts JA (2007) Feasibility of dynamic spectrum access in underutilized television bands. In: New frontiers in dynamic spectrum access networks, pp 331–339
López-Benítez M, Umbert A, Casadevall F (2009) Evaluation of spectrum occupancy in Spain for cognitive radio applications. In: Vehicular Technology Conference, 2009. VTC Spring, pp 1–5
Xue J, Feng Z, Zhang P (2013) Spectrum occupancy measurements and analysis in Beijing. IERI Procedia 4:295–302
Valenta V, Maršálek R, Baudoin G, Villegas M, Suarez M, Robert F (2010) Survey on spectrum utilization in Europe: measurements, analyses and observations. Cognitive Radio Oriented Wireless Networks & Communications (CROWNCOM), pp 1–5
Biggs M, Henley A, Clarkson T (2004) Occupancy analysis of the 2.4 GHz ISM band. IEE Proc Commun 151(5):481–488
Kokkoniemi J, Lehtomäki J (2012) Spectrum occupancy measurements and analysis methods on the 2.45 GHz ISM band. In: Cognitive Radio Oriented Wireless Networks and Communications (CROWNCOM), pp 285–290
Matinmikko M, Mustonen M, Höyhtyä M, Rauma T, Sarvanko H, Mämmelä A (2010) Distributed and directional spectrum occupancy measurements in the 2.4 GHz ISM band. In: ISWCS, pp 676–980
Jianli Z, Mingwei W, Jinsha Y (2011) Based on neural network spectrum prediction of cognitive radio. In: Electronics, Communications and Control (ICECC), pp 762–765
Najashi BG, Feng W (2014) Cooperative spectrum occupancy based spectrum prediction modeling. J Comput Inf Syst 10(10):4093–4100
Tumuluru VK, Wang P, Niyato D (2010) A neural network based spectrum prediction scheme for cognitive radio. Communications (ICC), pp 1–5
Shamsi N, Mousavinia A, Amirpour H (2013) A channel state prediction for multi-secondary users in a cognitive radio based on neural network. In: Electronics, Computer and Computation (ICECCO), pp 200–203
Akbar IA, Tranter WH (2007) Dynamic spectrum allocation in cognitive radio using hidden Markov models: Poisson distributed case. SoutheastCon, pp 196–201
Liu X, Zhang C, Tan X (2014) Double-threshold cooperative detection for cognitive radio based on weighing. Wirel Commun Mobile Comput 14(13):1530–8677
Bai Z, Wang L, Kwak KS (2014) Different sensing durations-based cooperative spectrum sensing in cognitive radio systems. Wirel Commun Mobile Comput 14(16):1522–1529
Pao Y-H, Phillips SM, Sobajic DJ (1992) Neural-net computing and the intelligent control of systems. Int J Control 56(2):263–289
Majhi R, Panda G, Sahoo G (2009) Development and performance evaluation of FLANN based model for forecasting of stock markets. Expert Syst Appl 36(3):6800–6808
Patra JC, Kot AC (2002) Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks. IEEE Trans Syst Man Cybern Part B: Cybern 32(4):505–511
Liang Y-C, Zeng Y, Peh EC, Hoang AT (2008) Sensing-throughput tradeoff for cognitive radio networks. IEEE Trans Wirel Commun 7(4):1326–1337
Bureau R (2002) HANDBOOK spectrum monitoring. In: International Telecommunication Union (ITU)
Luenberger DG, Ye Y (2008) Linear and nonlinear programming. Springer, Berlin, p 116
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Das, D., Matolak, D.W. & Das, S. Spectrum occupancy prediction based on functional link artificial neural network (FLANN) in ISM band. Neural Comput & Applic 29, 1363–1376 (2018). https://doi.org/10.1007/s00521-016-2653-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2653-5