Signal Transformation for Effective Multi-Channel Signal Processing

TL;DR

A signal transformation is proposed, using basic signal processing, to combine the individual channels of a low-bandwidth signal, like the EEG, into a single-channel high-bandwidth signal, like audio.

Abstract

Electroencephalography (EEG) is an non-invasive method to record the electrical activity of the brain. The EEG signals are low bandwidth and recorded from multiple electrodes simultaneously in a time synchronized manner. Typical EEG signal processing involves extracting features from all the individual channels separately and then fusing these features for downstream applications. In this paper, we propose a signal transformation, using basic signal processing, to combine the individual channels of a low-bandwidth signal, like the EEG into a single-channel high-bandwidth signal, like audio. Further this signal transformation is bi-directional, namely the high-bandwidth single-channel can be transformed to generate the individual low-bandwidth signals without any loss of information. Such a transformation when applied to EEG signals overcomes the need to process multiple signals and allows for a single-channel processing. The advantage of this signal transformation is that it allows the use of pre-trained single-channel pre-trained models, for multi-channel signal processing and analysis. We further show the utility of the signal transformation on publicly available EEG dataset.

Figures (4)

• Figure 1: Sample of a single-channel EEG signal of bandwidth $(f_s/2)$ (Top, $e_i$), spectral representation of $e_i$ (Middle, $E_i$), and stretched spectral representation with bandwidth $(F_s/2p)$ (Bottom, $E^{stretch}_i$).
• Figure 2: $p=6$ channel EEG with each channel having a bandwidth of $(f_s/2$) is stretched to $E^{stretch}_i$ having a bandwidth $((f_s/2)*6$) and stacked into a single-channel signal ($s$) with bandwidth $(F_s/2)$. Implementation details in Algorithm \ref{['algo:eeg2audio']}.
• Figure 3: Odour, Subject Classification. Train, Validation plots. For 2D-CNN architecture (Table \ref{['tab:cnn_model']}) using spectrogram of the transformed signal as the input features.
• Figure 4: Odour and Subject classification train and validation accuracy plots for 2D-CNN architecture (Table \ref{['tab:cnn_model']}(a)) using VGGish embeddings.