Machine learning-based spectrum decision algorithms for Wireless Sensor Networks

Wireless Sensor Networks (WSNs) employ Industrial, Scientific and Medical (ISM) spectrum bands for communication, which are overloaded due to various technologies such as WLANs and other WSNs. Therefore, such networks must employ intelligent methods such as Cognitive Radio (CR) to coexist with other networks. This study investigates the use of supervised Machine Learning (ML) for channel selection in WSNs. The proposed models were analyzed using ML tools and techniques, and the best algorithms were evaluated on real sensor nodes. The experiments show performance improvements on the delivery rate and delivery delay when the proposed cognitive solutions are employed.

[1]  Cheng-Xiang Wang,et al.  Reinforcement learning approaches and evaluation criteria for opportunistic spectrum access , 2014, 2014 IEEE International Conference on Communications (ICC).

[2]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[3]  Moshe T. Masonta,et al.  Spectrum Decision in Cognitive Radio Networks: A Survey , 2013, IEEE Communications Surveys & Tutorials.

[4]  Panagiotis Demestichas,et al.  Self-Organizing Maps for advanced learning in cognitive radio systems , 2012, Comput. Electr. Eng..

[5]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[6]  Chiara Petrioli,et al.  Energy Efficient COGnitive-MAC for Sensor Networks Under WLAN Co-existence , 2015, IEEE Transactions on Wireless Communications.

[7]  T. Charles Clancy,et al.  A machine learning approach for dynamic spectrum access radio identification , 2014, 2014 IEEE Global Communications Conference.

[8]  Apurva N. Mody,et al.  IEEE Standards Supporting Cognitive Radio and Networks, Dynamic Spectrum Access, and Coexistence , 2008, IEEE Communications Magazine.

[9]  Hüseyin Arslan,et al.  A survey of spectrum sensing algorithms for cognitive radio applications , 2009, IEEE Communications Surveys & Tutorials.

[10]  Tao Liu,et al.  Data-driven link quality prediction using link features , 2014, TOSN.

[11]  Antonio Alfredo Ferreira Loureiro,et al.  A framework for cognitive radio wireless sensor networks , 2012, 2012 IEEE Symposium on Computers and Communications (ISCC).

[12]  Jorge Sá Silva,et al.  Characteristics of Channels of IEEE 802.15.4 Compliant Sensor Networks , 2012, Wirel. Pers. Commun..

[13]  Klaus Wehrle,et al.  Intelligent Channel Assignment in Cognitive Wireless Sensor Networks: Learning from Virtual Channel Environment , 2014, 2014 International Conference on Information Science & Applications (ICISA).

[14]  Muhammad Umar Javed,et al.  Experimental Comparison of Dynamic Spectrum Access Techniques for Wireless Sensor Networks , 2010, 2010 IEEE 71st Vehicular Technology Conference.

[15]  Klaus Moessner,et al.  An overview of learning mechanisms for cognitive systems , 2012, EURASIP J. Wirel. Commun. Netw..

[16]  Ian F. Akyildiz,et al.  NeXt generation/dynamic spectrum access/cognitive radio wireless networks: A survey , 2006, Comput. Networks.