Systematic Comparison of Neural Networks for Raw EEG Analysis

In general, analyzing EEG data is a challenging task with many difficulties (Vallabhaneni et al., 2021 (link)). Due to typically low amplitude signals in the μV range (cp. Figure 1A), small interferences can distort a signal making it unusable (cp. Figure 1B red section compared to ordinary EEG recordings). We denote an interference as any part of a signal that is not directly generated by brain activity or brain activity that is not directly produced as result of an experimental stimulus. It is hard to remove interferences from a signal since these often show similar characteristics as the actual signal. To remove transient interferences before analyzing an EEG signal, various methods have been proposed, e.g., linear regression or blind source separation (Urigüen and Garcia-Zapirain, 2015 (link)). Nevertheless, none of them is supposed to work perfectly and remaining interferences may cause erroneous analysis results (Hagmann et al., 2006 (link)).
Another problem can be the placement and number of electrodes that capture brain activity. Not all regions of the brain are equally active during experiments and some regions are more dominant than others. When less electrodes are used, activation could be missed during the recording which results in no features.
To avoid such errors it is advisable to use a higher number of electrodes and to cover all areas of the head. When the number of electrodes used increases, the time and effort required to preprocess the data increases as well. This can be critical for time-frequency transforms which typically process signals channel- or window-wise (Li et al., 2016 ; Tabar and Halici, 2016 (link)).
In recent years, deep learning neural network approaches have been applied to a wide range of neuroscientific problems like feedback on motor imagery tasks (MI) (Tabar and Halici, 2016 (link)), emotion recognition (Ng et al., 2015 ), seizure detection (Thodoroff et al., 2016 ) and many other tasks (Gong et al., 2021 (link)) (see Table 4). These studies typically apply standard convolutional and recurrent neural networks (Craik et al., 2019 (link)). Many studies use handcrafted features as input for deep neural networks. However, extracting features can be time-consuming and often requires expert domain knowledge to extract features which represent the signal correctly. To avoid loss of information during the preprocessing phase, the aim of neurobiological analysis should be an analysis of raw data. If more information is provided to the neural network, better results can be expected. To the best of our knowledge, no study exists that systematically compares feed-forward and recurrent neural networks in all their flavors for raw signal EEG data analysis.