Objectives
An invasive brain‐computer interface (BCI) is a promising neurorehabilitation device for severely disabled patients. Although some systems have been shown to work well in restricted laboratory settings, their utility must be tested in less controlled, real‐time environments. Our objective was to investigate whether a specific motor task could be reliably detected from multiunit intracortical signals from freely moving animals in a simulated, real‐time setting.
Materials and Methods
Intracortical signals were first obtained from electrodes placed in the primary motor cortex of four rats that were trained to hit a retractable paddle (defined as a “Hit”). In the simulated real‐time setting, the signal‐to‐noise‐ratio was first increased by wavelet denoising. Action potentials were detected, and features were extracted (spike count, mean absolute values, entropy, and combination of these features) within pre‐defined time windows (200 ms, 300 ms, and 400 ms) to classify the occurrence of a “Hit.”
Results
We found higher detection accuracy of a “Hit” (73.1%, 73.4%, and 67.9% for the three window sizes, respectively) when the decision was made based on a combination of features rather than on a single feature. However, the duration of the window length was not statistically significant (p = 0.5).
Conclusion
Our results showed the feasibility of detecting a motor task in real time in a less restricted environment compared to environments commonly applied within invasive BCI research, and they showed the feasibility of using information extracted from multiunit recordings, thereby avoiding the time‐consuming and complex task of extracting and sorting single units.