Spectrum Decision in Wireless Sensor Networks Employing Machine Learning

Wireless Sensor Networks (WSNs) employ 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 to coexist with other networks. This study evaluates the use of Supervised Machine Learning (ML) for channel selection in WSNs, considering the channel quality and communication metrics. The methods were evaluated experimentally and compared with energy-based methods. The results show that ML-based methods increase the communication performance by reducing the number of transmission attempts and therefore also reducing the delivery delay.