Saa Jaime F Delgado, Pesters Adriana de, McFarland Dennis, Çetin Müjdat
Signal Proc. Info. Syst. Lab, Sabanci University, Istanbul, Turkey. Robotics & Intelligent Syst. Lab, Universidad del Norte, Barranquilla, Colombia.
J Neural Eng. 2015 Apr;12(2):026007. doi: 10.1088/1741-2560/12/2/026007. Epub 2015 Feb 16.
In this work we propose a probabilistic graphical model framework that uses language priors at the level of words as a mechanism to increase the performance of P300-based spellers.
This paper is concerned with brain-computer interfaces based on P300 spellers. Motivated by P300 spelling scenarios involving communication based on a limited vocabulary, we propose a probabilistic graphical model framework and an associated classification algorithm that uses learned statistical models of language at the level of words. Exploiting such high-level contextual information helps reduce the error rate of the speller.
Our experimental results demonstrate that the proposed approach offers several advantages over existing methods. Most importantly, it increases the classification accuracy while reducing the number of times the letters need to be flashed, increasing the communication rate of the system.
The proposed approach models all the variables in the P300 speller in a unified framework and has the capability to correct errors in previous letters in a word, given the data for the current one. The structure of the model we propose allows the use of efficient inference algorithms, which in turn makes it possible to use this approach in real-time applications.
在这项工作中，我们提出了一种概率图形模型框架，该框架在单词层面使用语言先验作为提高基于P300的拼写器性能的一种机制。
本文关注基于P300拼写器的脑机接口。受涉及基于有限词汇进行通信的P300拼写场景的启发，我们提出了一种概率图形模型框架和一种相关的分类算法，该算法在单词层面使用学习到的语言统计模型。利用这种高级上下文信息有助于降低拼写器的错误率。
我们的实验结果表明，所提出的方法相对于现有方法具有多个优势。最重要的是，它提高了分类准确率，同时减少了字母需要闪烁的次数，提高了系统的通信速率。
所提出的方法在一个统一框架中对P300拼写器中的所有变量进行建模，并且在给定当前字母数据的情况下，有能力纠正单词中先前字母的错误。我们提出的模型结构允许使用高效的推理算法，这反过来又使得在实时应用中使用这种方法成为可能。
