A Bayesian dynamic stopping method for evoked response brain-computer interfacing

TL;DR

A model-based approach that takes advantage of the analytical knowledge that the author has about the underlying classification model and allows precise control over the types of errors and the balance between precision and speed is proposed.

Abstract

As brain-computer interfacing (BCI) systems transition from assistive technology to more diverse applications, their speed, reliability, and user experience become increasingly important. Dynamic stopping methods enhance BCI system speed by deciding at any moment whether to output a result or wait for more information. Such approach leverages trial variance, allowing good trials to be detected earlier, thereby speeding up the process without significantly compromising accuracy. Existing dynamic stopping algorithms typically optimize measures such as symbols per minute (SPM) and information transfer rate (ITR). However, these metrics may not accurately reflect system performance for specific applications or user types. Moreover, many methods depend on arbitrary thresholds or parameters that require extensive training data. We propose a model-based approach that takes advantage of the analytical knowledge that we have about the underlying classification model. By using a risk minimisation approach, our model allows precise control over the types of errors and the balance between precision and speed. This adaptability makes it ideal for customizing BCI systems to meet the diverse needs of various applications. We validate our proposed method on a publicly available dataset, comparing it with established static and dynamic stopping methods. Our results demonstrate that our approach offers a broad range of accuracy-speed trade-offs and achieves higher precision than baseline stopping methods.

Figures (4)

• Figure 1: An example of the score distribution of target (blue) and non-target (pink) classes and how they change over stimulation time. Solid lines indicate the mean ($\alpha b_1$ and $\alpha b_0$) of the Gaussian distributions and dashed lines indicate the standard deviation ($\sigma_1$ and $\sigma_0$). The black solid line is the decision boundary $\eta$ resulting from Equation \ref{['eq:decision_boundary']} with $\zeta=1$.
• Figure 2: The performance of the Bayesian dynamic stopping averaged over the 108 trials for each participant, as the cost ratio $\zeta$ changes between 1e-10 and 1e10. The performance is measured in terms of accuracy and average stopping time as well as the relevance-based metrics precision, recall, F-score and specificity.
• Figure 3: Accuracy versus stopping time averaged over 12 participants for BDS and static and dynamic stopping methods from the literature as the hyper-parameter of each method changes. For BDS (blue), the hyper-parameter is the cost ratio $\zeta$ ranging from $1*10^{-10}$ to $1*10^{10}$. For the static stopping methods with optimized accuracy (red), the margin (green), and beta (purple) dynamic stopping, the targeted accuracy varied between $10\%$ and $98\%$. The static methods that maximize accuracy (grey $\times$) or ITR (gray $+$) do not have a hyper-parameter and therefore appear as one point in the figure. The performance of a fixed trial length from 0.5 s to 4.2 s is also included for reference (yellow). All but one of the baseline methods are implemented using both correlation (dashed) and inner product (solid) as the similarity score. The shaded areas indicate the 95% confidence interval.
• Figure 4: Precision versus stopping time averaged over 12 participants for the BDS, margin and beta dynamic stopping methods as the hyper-parameter of each method changes. For BDS (blue), the hyper-parameter is the cost ratio $\zeta$ which ranges from $1*10^{-10}$ to $1*10^{10}$. For the margin (green) and beta (purple) methods, the targeted accuracy ranges between $10\%$ and $98\%$. The margin method is implemented using both correlation (dashed) and inner product (solid) as the similarity score. The 95% confidence interval is visualized using a shaded area, but they are in the range of 0.005 and therefore barely visible.