Sensor Reduction and Generalization

Machine-learning pipelines often begin with a simple assumption: if more measurements are available, more measurements should be used. That assumption is especially expensive in sensor-based systems. Every additional EEG channel adds another electrode, another signal stream, another source of setup complexity, and another feature block that must be processed at inference time.

The present work builds on the methodology used in the previous work by myself , where the effects on the performance of the EEG classifier when entire participants are held out from the training data and used only for testing. This revealed the great importance of the validation method on the performance results. Now that the methodology has been established, the next step will have a more applied approach, as the model must be able to generalize on completely unknown participants.…