Investigating Data Cleaning Methods to Improve Performance of Brain–Computer Interfaces Based on Stereo-Electroencephalography

Abstract

Stereo-electroencephalography (SEEG) utilizes localized and penetrating depth electrodes to directly measure electrophysiological brain activity. The implanted electrodes generally provide a sparse sampling of multiple brain regions, including both cortical and subcortical structures, making the SEEG neural recordings a potential source for the brain–computer interface (BCI) purpose in recent years. For SEEG signals, data cleaning is an essential preprocessing step in removing excessive noises for further analysis. However, little is known about what kinds of effect that different data cleaning methods may exert on BCI decoding performance and, moreover, what are the reasons causing the differentiated effects. To address these questions, we adopted five different data cleaning methods, including common average reference, gray–white matter reference, electrode shaft reference, bipolar reference, and Laplacian reference, to process the SEEG data and evaluated the effect of these methods on improving BCI decoding performance. Additionally, we also comparatively investigated the changes of SEEG signals induced by these different methods from multiple-domain (e.g., spatial, spectral, and temporal domain). The results showed that data cleaning methods could improve the accuracy of gesture decoding, where the Laplacian reference produced the best performance. Further analysis revealed that the superiority of the data cleaning method with excellent performance might be attributed to the increased distinguishability in the low-frequency band. The findings of this work highlighted the importance of applying proper data clean methods for SEEG signals and proposed the application of Laplacian reference for SEEG-based BCI.

Deep Learning With Convolutional Neural Networks for Motor Brain-Computer Interfaces Based on Stereo-Electroencephalography (SEEG)

“…It is obvious from these two subplots that the correlation between two different classes decreased after the first spatial layer. This enhancement brought by the spatial layer was similar to that obtained by a spatial filter (Laplacian reference) methods [14], [26]. Next, to find out if the network extracted band-specific features like a filter, the testing data set was fed into the trained network to obtain the intermediate feature map of Conv spatial 2.…”

“…Frequency representation is another commonly used feature [13]. For example, the power of the bands 1-4 Hz, 4-8 Hz, 8-13 Hz, 13-30 Hz, and 60-195 Hz was extracted and concatenated as input to an SVM classifier [14]. Other commonly used features are statistical features, such as mean, median, standard deviation, etc.…”

Neuromorphic applications in medicine

“…Advance technologies now allow us to combine machine learning algorithms with traditional neuromodulation techniques to enhance biomedical interfaces, which aim to modulate and decode biological signals to achieve immunotherapeutic or prosthetic outcomes [136]. Intensive real-time data processing is often necessary for these interfaces, which may require the transmission of data to an external computer with the computational power needed for processing [137,138].…”

Research on Oil Well Data Cleaning System

“…In deep learning, the quality of data sets In the final analysis, data cleaning is to conduct in-depth analysis on the main causes of dirty data, find out the form in which these dirty data exist in a large number of data to affect the analysis results, use the current existing technology and optimize its processing to find dirty data, and change these detected data into values that meet normal needs after processing. The idea of data cleaning mainly uses the backtracking method [17], which takes the detected data as the starting point, makes a systematic analysis of each detail of the data flow direction, and summarizes a widely used data cleaning algorithm and related rules, which can be applied to various types of data cleaning systems [18].…”