Enhancement of SSVEPs Classification in BCI-Based Wearable Instrumentation Through Machine Learning Techniques

This work addresses the adoption of Machine Learning classifiers and Convolutional Neural Networks to improve the performance of highly wearable, single-channel instrumentation for Brain-Computer Interfaces. The proposed measurement system is based on the classification of Steady-State Visually Evoked Potentials (SSVEPs). In particular, Head-Mounted Displays for Augmented Reality are used to generate and display the flickering stimuli for the SSVEPs elicitation. Four experiments were conducted by employing, in turn, a different Head-Mounted Display. For each experiment, two different algorithms were applied and compared with the state-of-the-art-techniques. Furthermore, the impact of different Augmented Reality technologies in the elicitation and classification of SSVEPs was also explored. The experimental metrological characterization demonstrates (i) that the proposed Machine Learning-based processing strategies provide a significant enhancement of the SSVEP classification accuracy with respect to the state of the art, and (ii) that choosing an adequate Head-Mounted Display is crucial to obtain acceptable performance. Finally, it is also shown that the adoption of inter-subjective validation strategies such as the Leave-One-Subject-Out Cross Validation successfully leads to an increase in the inter-individual 1-sigma reproducibility: this, in turn, anticipates an easier development of ready-to-use systems.