Classification of Magnetoencephalography Signals by Multilayer and Radial Based Artificial Neural Networks

Magnetoencephalography (MEG) is a neuroimaging technique for recording brain activity, using very sensitive magnetometers. MEG signals are obtained from neuronal electrical activity and are capable of providing important information for decoding brain activity. In the case of visual stimulation, the relationship between the stimuli and the signal due to the generated mental activity is important for the development of machine learning algorithms. MEG signals have a complex structure due to environmental factors and functional differences arising from brain structures of individuals. It is difficult to get meaningful information from these complex signals. For this reason it is necessary to utilize advanced signal processing techniques. In this study, the successes of multilayer neural network (MLNN) and radial basis neural network (RBNN) have been demonstrated by classifying magnetoencephalography signals through MLNN and RBNN. The performances of proposed classifiers are compared with the results of the previous studies using same dataset.