Least-squares support vector machine-based learning and decision making in cognitive radios

Cognitive radio (CR) can improve system performance and increase its adaptation ability because of its high intelligence in configuring system parameters dynamically. The key of intelligence in CR is its learning capability. After comparing the conventional optimisation decision-making methods and the learning-based ones in intelligent reconfiguration in CR, this study proposes a general learning-based decision-making model framework. According to the framework, a concrete implementation of learning and decision making on the constructed CR communication scenario based on the least-squares support vector machine is demonstrated in detail. Some results of two simulation experiments show that the system performance can be remarkably improved as the CR system learns more reliable knowledge from more communication instances experienced, and that the generalisation capability of the model is quite good.

[1]  Safwan El Assad,et al.  Efficient classification algorithm and a new training mode for the adaptive radial basis function neural network equaliser , 2012, IET Commun..

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Dimitris Kanellopoulos,et al.  Data Preprocessing for Supervised Leaning , 2007 .

[4]  Timothy J. O'Shea,et al.  Applications of Machine Learning to Cognitive Radio Networks , 2007, IEEE Wireless Communications.

[5]  Venugopal V. Veeravalli,et al.  Algorithms for Dynamic Spectrum Access With Learning for Cognitive Radio , 2008, IEEE Transactions on Signal Processing.

[6]  Joseph Mitola,et al.  Cognitive radio: making software radios more personal , 1999, IEEE Wirel. Commun..

[7]  Panagiotis Demestichas,et al.  Neural network-based learning schemes for cognitive radio systems , 2008, Comput. Commun..

[8]  Johan A. K. Suykens,et al.  Benchmarking Least Squares Support Vector Machine Classifiers , 2004, Machine Learning.

[9]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[10]  Jae Hoon Lee,et al.  Analysis of space–time adaptive processing performance using K-means clustering algorithm for normalisation method in non-homogeneity detector process , 2011 .

[11]  S. Baskar,et al.  Application of NSGA-II Algorithm to Single-Objective Transmission Constrained Generation Expansion Planning , 2009, IEEE Transactions on Power Systems.

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.