Direct information transfer rate optimisation for SSVEP-based BCI

TL;DR

This paper introduces a novel method for optimizing classification thresholds in SSVEP-based BCI systems by maximizing a generalized information transfer rate, leading to improved accuracy and efficiency without manual parameter tuning.

Contribution

The paper presents a new threshold optimization technique that maximizes ITR using a generalized formula, eliminating manual tuning and grid searches, and significantly improving classification performance.

Findings

Achieved an ITR of 62 bit/min on the dataset.

Outperformed previous methods by a factor of 2 in ITR.

Reduced false classifications in BCI target classification.

Abstract

In this work, a classification method for SSVEP-based BCI is proposed. The classification method uses features extracted by traditional SSVEP-based BCI methods and finds optimal discrimination thresholds for each feature to classify the targets. Optimising the thresholds is formalised as a maximisation task of a performance measure of BCIs called information transfer rate (ITR). However, instead of the standard method of calculating ITR, which makes certain assumptions about the data, a more general formula is derived to avoid incorrect ITR calculation when the standard assumptions are not met. This allows the optimal discrimination thresholds to be automatically calculated and thus eliminates the need for manual parameter selection or performing computationally expensive grid searches. The proposed method shows good performance in classifying targets of a BCI, outperforming previously reported results on the same dataset by a factor of 2 in terms of ITR. The highest achieved ITR on the used dataset was 62 bit/min. The proposed method also provides a way to reduce false classifications, which is important in real-world applications.