Analogue Evolutionary Brain Computer Interfaces

键盘是一块带有许多开关的塑料，它为我们提供了一种可靠但非常不自然的输入形式。鼠标就没那么原始了。然而，它只是一个肌肉骨骼运动的机电换能器。这两款产品已经使用多年，目前仍是我们拥有的最好的计算机接口，但它们无法用于患有严重肌肉骨骼疾病的人，而且它们本身也是与工作相关的上肢和背部疾病的已知原因：这两种疾病在英国的劳动力中都非常普遍。如果有一天能够处理掉它们，取而代之的是能够直接解释计算机用户的欲望和意图的脑机接口（bci），这不是很好吗？这一大胆的提议旨在在计算机科学，生物医学工程，神经科学和心理学的边缘开展一项创新和雄心勃勃的跨学科研究计划，旨在利用申请人最近开发的新颖强大的脑机接口方法开发这些设备。多年来，脑机接口一直是研究人员的梦想，但发展缓慢，除了极少数例外，脑机接口实际上仍然是一种只能在实验室中使用的好奇心。那么，这个项目有什么不同？在最近的研究中，我们能够开发出一种原型BCI鼠标，能够完全进行2-D运动控制（这在BCI领域是罕见的），任何人都可以在几分钟内使用，无需任何事先培训。这要归功于我们对脑机接口采用了完全创新的方法。以前的脑机接口设计是基于观察脑电图信号寻找特定的特征或波，操纵它们，然后对这些特征或波是否存在做出是或否的决定。与这种设计智慧相反，我们完全抛弃了决策步骤，允许脑电波通过简单的模拟转换直接控制计算机。此外，我们只对系统进行了部分设计，将每个特定用户的设计完成和定制留给了进化算法。这要感谢计算机内部的一种人工形式的达尔文进化，它完成了选择最佳脑电图通道、波和模拟操作的艰巨任务。使用同样的两种成分（模拟方法和进化设计），并从我们成功的实验BCI鼠标开始，该项目特别致力于开发足够强大，灵活和廉价的脑机接口，可以离开实验室，并开始在现实世界中产生重大影响。为了最大限度地提高性能，初步工作将确定最佳的视觉呈现条件，以最大限度地减少认知负荷、感知错误和目标干扰。

The keyboard is a piece of plastic with lots of switches, which provides us with a reliable, but very unnatural form of input. The mouse is slightly less primitive. Still, it is only an electro-mechanical transducer of musculoskeletal movement. Both have been with us for many years and are still the best computer interfaces we have at the moment, yet they are unusable for people with severe musculoskeletal disorders and are themselves known causes of work-related upper-limb and back disorders: both hugely widespread problems for the UK's workforce.Wouldn't it be nice some day to be able to dispose of them and replace them with Brain-Computer Interfaces (BCIs) capable of directly interpreting the desires and intentions of computer users?This adventurous proposal aims to carry out an innovative and ambitious interdisciplinary research programme at the edge of Computer Science, Biomedical Engineering, Neuroscience and Psychology aimed at developing precisely these devices with a novel powerful BCI approach recently developed by the applicants.BCI has been a dream of researchers for many years, but developments have been slow and, with rare exceptions, BCI is still effectively a curiosity that can be used only in the lab. So, what's different about this project?In very recent research, we were able to develop a prototype BCI mouse capable of full 2-D motion control (a rarity in the BCI world), which uniquely can be used by any person without any prior training within minutes. This was possible thanks to our taking a completely innovative approach to BCI. Previous BCI designs were based on the paradigm of observing EEG signals looking for specific features or waves, manipulating them and then making a yes-or-no decision as to whether such features or waves were present. Contrary to this design wisdom, we completely dispose of the decision step and allow brain waves to directly control the computer via simple analogue transformations. Furthermore, we only partially design the system, leaving the completion and customisation of the design for each specific user to an evolutionary algorithm. This, thanks to an artificial form of Darwinian evolution inside the computer, performs the difficult tasks of selecting the best EEG channels, waves and analogue manipulations. Using these same two ingredients (analogue approach and evolutionary design) and starting from our successful experimental BCI mouse, this project specifically aims at developing brain-computer interfaces which are sufficiently robust, flexible and cheap to leave the lab and that can start making a serious impact in the real world.To maximise performance, preliminary work will determine the optimal visual presentation conditions that minimise cognitive load, perceptual errors and target-distractors interference.