Benda Mihaly, Stawicki Piotr, Gembler Felix, Grichnik Roland, Rezeika Aya, Saboor Abdul, Volosyak Ivan
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:1939-1943. doi: 10.1109/EMBC.2018.8512622.
In this paper we examined different ways to inform the user of the classification progress in our online SSVEPbased BCI speller. Different user feedback was given based on the distance from the classification threshold, separately calculated for each stimulus. We focused on the comparison of the accuracies and spelling times associated with each different feedback type. We tested eight different methods, one without feedback for comparison, and the two paradigms each (an increase and a decrease), for three varying parameters, during an online spelling task. The eighth method was a combination of the best performing feedback modalities. A 28 target speller was used for spelling the same word with different feedback methods. The level of comfort was assessed by the seven healthy participants, using a questionnaire. We found substantial decreases in spelling times; they were reduced to 12-77% of the no-feedback condition spelling times, for each of our subjects, with at least one of the parameters. However, this parameter, as expected, was different for each user. According to the personal fastest feedback methods, a combination of them was also used for spelling. These combined feedback methods usually resulted in a slower spelling than the individual best feedback, but still faster than without any feedback. Overall, the average spelling times with the different feedback methods were: no feedback, 95.09 s, increasing size, 62.94 s, decreasing size, 87.73 s, increasing contrast, 77.80 s, decreasing contrast, 124.37 s, increasing duty-cycle, 134.70 s, and decreasing dutycycle, 103.77 s.
在本文中，我们研究了在基于稳态视觉诱发电位（SSVEP）的在线脑机接口（BCI）拼写器中向用户告知分类进度的不同方式。根据与分类阈值的距离给出不同的用户反馈，针对每个刺激单独计算该距离。我们重点比较了与每种不同反馈类型相关的准确率和拼写时间。在在线拼写任务期间，我们测试了八种不同方法，一种无反馈方法用于比较，针对三个不同参数，每种参数各有两种模式（增加和减少）。第八种方法是表现最佳的反馈模式的组合。使用一个28个目标的拼写器，用不同反馈方法拼写同一个单词。七名健康参与者通过问卷调查评估舒适度。我们发现拼写时间大幅减少；对于我们的每个受试者，在至少一个参数的情况下，拼写时间减少到无反馈条件下拼写时间的12% - 77%。然而，正如预期的那样，每个用户的这个参数各不相同。根据个人最快的反馈方法，也将它们组合起来用于拼写。这些组合反馈方法通常导致拼写速度比单个最佳反馈慢，但仍比无任何反馈时快。总体而言，不同反馈方法的平均拼写时间分别为：无反馈，95.09秒；增大尺寸，62.94秒；减小尺寸，87.73秒；增大对比度，77.80秒；减小对比度，124.37秒；增大占空比，134.70秒；减小占空比，103.77秒。
