Machine learning plug-ins for GNU Radio Companion

This paper gives an insight about how to create classifier plug-ins (signal processing blocks) using hard-code input for GNU Radio Companion (GRC). GNU Radio Companion is an open source Visual programming language for any real time signal processing applications. At present there is no classifier block available inside this GRC tool. Here we are introducing a low cost classifier which utilizes the basic machine learning algorithms:linear regression and logistic regression. The creation of classifier plug-ins in an open source software enables easy manipulation of real time classification problems during the transmission and reception of signals in Software Defined Radios. So this workdescribes the development of signal processing block that can be done by changing the Python code and C++ codes of the `gr-modtool´ package. It is highly cost effective and with great potential since GNU Radio software is open source and free.