First steps towards quantum machine learning applied to the classification of event-related potentials

TL;DR

This paper explores the application of quantum machine learning, specifically a quantum-enhanced support vector classifier, to EEG-based brain-computer interfaces, aiming to improve classification accuracy for clinical use.

Contribution

It introduces the first application of quantum-enhanced support vector classification to EEG data for brain-computer interfaces, demonstrating initial feasibility.

Findings

Balanced accuracy of 83.17% for training

Prediction accuracy of 50.25%

Indicates potential but requires further optimization

Abstract

Low information transfer rate is a major bottleneck for brain-computer interfaces based on non-invasive electroencephalography (EEG) for clinical applications. This led to the development of more robust and accurate classifiers. In this study, we investigate the performance of quantum-enhanced support vector classifier (QSVC). Training (predicting) balanced accuracy of QSVC was 83.17 (50.25) %. This result shows that the classifier was able to learn from EEG data, but that more research is required to obtain higher predicting accuracy. This could be achieved by a better configuration of the classifier, such as increasing the number of shots.