An Event-Related Potential (ERP)-based Brain-Computer Interface (BCI) Speller System assists people with disabilities communicate by decoding electroencephalogram (EEG) signals. A P300-ERP embedded in EEG signals arises in response to a rare, but relevant event (target) among a series of irrelevant events (non-target). Different machine learning methods have constructed binary classifiers to detect target events, known as calibration. Existing calibration strategy only uses data from participants themselves with lengthy training time, causing biased P300 estimation and decreasing prediction accuracy. To resolve this issue, we propose a Bayesian signal matching (BSM) framework for calibrating the EEG signals from a new participant using data from source participants. BSM specifies the joint distribution of stimulus-specific EEG signals among source participants via a Bayesian hierarchical mixture model. We apply the inference strategy: if source and new participants are similar, they share the same set of model parameters, otherwise, they keep their own sets of model parameters; we predict on the testing data using parameters of the baseline cluster directly. Our hierarchical framework can be generalized to other base classifiers with clear likelihood specifications. We demonstrate the advantages of BSM using simulations and focus on the real data analysis among participants with neuro-degenerative diseases.

翻译：基于事件相关电位（ERP）的脑机接口（BCI）拼写系统通过解码脑电图（EEG）信号帮助残障人士进行交流。P300-ERP嵌入在EEG信号中，是对一系列无关事件（非目标）中出现的罕见但相关事件（目标）的响应。不同的机器学习方法构建了二元分类器来检测目标事件，这被称为校准。现有的校准策略仅使用参与者自身的数据，且训练时间较长，导致P300估计产生偏差并降低预测准确性。为解决此问题，我们提出了一种贝叶斯信号匹配（BSM）框架，用于利用源参与者的数据对新参与者的EEG信号进行校准。BSM通过贝叶斯层次混合模型指定源参与者之间刺激特异性EEG信号的联合分布。我们采用如下推理策略：若源参与者与新参与者相似，则共享同一组模型参数；否则，各自保留其模型参数集。我们直接使用基线聚类的参数对测试数据进行预测。我们的层次框架可推广至其他具有明确似然规范的基础分类器。我们通过模拟实验展示了BSM的优势，并重点分析了患有神经退行性疾病的参与者的真实数据。