Brain Control of an External Device by Extracting the Highest Force-Related Contents of Local Field Potentials in Freely Moving Rats

Abstract

A local field potential (LFP) signal is an alternative source to neural action potentials for decoding kinematic and kinetic information from the brain. Here, we demonstrate that the better extraction of force-related features from multichannel LFPs improves the accuracy of force decoding. We propose that applying canonical correlation analysis (CCA) filter on the envelopes of separate frequency bands (band-specific CCA) separates non-task related information from the LFPs. The decoding accuracy of the continuous force signal based on the proposed method were compared with three feature reduction methods: 1) band-specific principal component analysis (band-specific PCA) method that extract the components which leads to maximum variance from the envelopes of different frequency bands; 2) correlation coefficient-based (CC-based) feature reduction that selects the best features from the envelopes sorted based on the absolute correlation coefficient between each envelope and the target force signal; and 3) mutual information-based (MI-based) feature reduction that selects the best features from the envelopes sorted based on the mutual information between each envelope and output force signal. The band-specific CCA method outperformed band-specific PCA with 11% improvement, CC-based feature reduction with 16% improvement, and MI-based feature reduction with 18% improvement. In the online brain control experiments, the real-time decoded force signal from the 16-channel LFPs based on the proposed method was used to move a mechanical arm. Two rats performed 88 trials in seven sessions to control the mechanical arm based on the 16-channel LFPs.

Brain-Computer-Spinal Interface Restores Upper Limb Function After Spinal Cord Injury

“…LFP decoders have also shown sufficient stability for motor intention decoding without recalibration over several months in human subjects [39]. In prior work, the CCA decoder used here maintained high performance with a lower computational complexity compared to principal component analysis or correlation coefficient-based methods [33].…”

“…The offline study was performed in MATLAB using custom scripts. We used the decoding paradigm presented in [33] to continuously decode forelimb movements from the multichannel LFPs. Several preprocessing steps were implemented to remove artifacts/noise and improve decoding performance.…”

Adaptive Artifact Removal From Intracortical Channels for Accurate Decoding of a Force Signal in Freely Moving Rats

“…In this step, the extracted features were normalized by subtracting the mean values and dividing by standard deviation of each feature (Khorasani et al, 2018). PLS regression model was used to model the relationship between the input feature vector and the output force signal (Figure 1).…”

This preprint has been taken down.

“…LFP decoders have also shown sufficient stability for motor intention decoding without recalibration over several months in human 37 . In prior work, the CCA decoder used here maintained high performance with a lower computational complexity compared to principal component analysis or correlation coefficient-based methods 38 .…”

“…The envelope of each channel was a continuous signal that represented the changes in spectral power of LFPs in response to output movement. To obtain the highest movement related spectral components, a canonical correlation coefficient (CCA) filter was applied on the multi-channel envelopes during the lever task 38 . Offline analysis was performed using the signal processing method demonstrated in the previous study 38 .…”