Signal Classification

Using machine learning techniques and an extensive training data set, CRFS has created a highly accurate signal classifier.

The RFeye® Signal Classification module is able to identify a comprehensive range of modulation types, both analog and digital, covering military and civilian standards. The module identifies, and returns in string format, the modulation technique of a signal of interest. This gives you centre frequency along with modulation type ("QPSK" or "QAM" for example), the number of modulation levels, modulation index and baud rate. All of this helps to identify the type of transmission being detected and can allow causes of interference to be diagnosed and possible threats to be identified.

The RFeye Signal Classification module has been developed using the latest Machine Learning techniques and mathematical tools to train neural networks and CRFS’s very extensive training data sets of signals. Machine learning techniques are ideal for optimising signal classification performance and allows for very fast accurate signal classification whilst minimizing false alarms and easy update of signal classifier databases with new signal types.

How does it work?

During the training process, the performance of the neural net can be monitored using a confusion matrix as shown below. The input data for training neural nets is a large database of signal types collected from real world RF environments using CRFS distributed RF sensors located all over the world. The more signal types, with real world distortions such as multipath, the more effectively the neural net can be trained to perform in actual field deployments.

Confusion Matrix for signal recognition
Confusion matrix for signal recognition

The CRFS training database uses “tagged” signals with known classifications to train the neural net. The training process adjusts individual neurones in the net so that they can identify the known signals correctly i.e. the classifier’s calculation and the “tag” match.

To test the neural network, a separate set of known signals not used for the training process is input to the classifier. The confusion matrix shows the known input signal type against the classifier’s calculation for every test and increments the appropriate element of the matrix with the answer against the test input. In other words, a 100% correct classifier would produce a confusion matrix with non-zero elements only along the leading diagonal. Generally, test scores of >95% accuracy can be achieved. These test scores improve with more varied and deeper training data sets. CRFS is actively building massive tagged signal training databases for this purpose.

Typical signal classifier neural network
Typical signal classifier neural network

The input layer of a neural net has a series of weightings from features extracted from signal IQ data e.g. 20 feature weightings, 20 input neurons. The output layer has a neuron for each signal type to be classified e.g. 30 signal types, 30 output neurons. The neural net selects the output signal type to reflect the most probable signal given the input features.


Machine Learning and RF Spectrum Intelligence Gathering White Paper