BACKGROUND Even though the BCI field has quickly grown in the last few years, it is still mainly investigated as a research area. Increased practicality and usability are required to move BCIs to the real-world. Self-paced (SP) systems would reduce the problem but there is still the big challenge of what is known as the 'onset detection problem'. METHODS Our previous studies showed how a new sound-imagery (SI) task, high-tone covert sound production, is very effective for onset detection scenarios and we expect there are several advantages over most common asynchronous approaches used thus far, i.e., motor-imagery (MI): 1) Intuitiveness; 2) benefits to people with motor disabilities and, especially, those with lesions on cortical motor areas; and 3) no significant overlap with other common, spontaneous cognitive states, making it easier to use in daily-life situations. The approach was compared with MI tasks in online real-life scenarios, i.e., during activities such as watching videos and reading text. In our scenario, when a new message prompt from a messenger program appeared on the screen, participants watching a video (or reading text, browsing images) were asked to open the message by executing the SI or MI tasks, respectively, for each experimental condition. RESULTS The results showed the SI task performed statistically significantly better than the MI approach: 84.04% (SI) vs 66.79 (MI) True-False positive rate for the sliding image scenario, 80.84% vs 61.07% for watching video. The classification performance difference between SI and MI was found not to be significant in the text-reading scenario. Furthermore, the onset response speed showed SI (4.08 s) being significantly faster than MI (5.46 s). In terms of basic usability, 75% of subjects found SI easier to use. CONCLUSIONS Our novel SI task outperforms typical MI for SP onset detection BCIs, therefore it would be more easily used in daily-life situations. This could be a significant step forward for the BCI field which has so far been mainly restricted to research-oriented indoor laboratory settings.

中文翻译：

---

现实在线在线自定节奏BCI中隐性声音产生任务（声音图像）与运动图像之间的比较，以进行发病检测。

背景技术尽管BCI领域在最近几年中发展迅速，但仍主要作为研究领域对其进行研究。为了使BCI进入现实世界，需要提高实用性和可用性。自定步调（SP）系统可以减少该问题，但是仍然存在着巨大的挑战，即所谓的“发作检测问题”。方法我们以前的研究表明，新的声音图像（SI）任务，即高音隐蔽声音的产生，对于发作检测场景非常有效，并且我们期望与目前使用的最常见的异步方法相比，它具有多个优点，例如，意象（MI）：1）直观；2）对运动障碍者，特别是在皮质运动区域有损伤的人的利益；和3）与其他常见的自发认知状态没有明显的重叠，使其更易于在日常生活中使用。在在线现实场景中，即在观看视频和阅读文字等活动中，将该方法与MI任务进行了比较。在我们的场景中，当屏幕上出现来自Messenger程序的新消息提示时，要求观看视频（或阅读文本，浏览图像）的参与者通过针对每种实验条件分别执行SI或MI任务来打开消息。结果结果表明，SI任务在统计上比MI方法明显更好：滑动图像场景的真假阳性率分别为84.04％（SI）和66.79（MI），观看视频的真假率为80.84％vs 61.07％。发现在文本阅读方案中，SI和MI之间的分类性能差异不明显。此外，起搏反应速度显示为SI（4。08 s）比MI（5.46 s）快得多。在基本可用性方面，有75％的受试者发现SI更易于使用。结论我们新颖的SI任务在SP发作检测BCI方面胜过典型的MI，因此在日常生活中更容易使用。对于迄今为止主要限于研究型室内实验室环境的BCI领域，这可能是向前迈出的重要一步。