Can The Analysis Of Large Open-Access Neuroimaging Data Inform The Development Of More Effective Neurofeedback Training Systems?

我的研究项目开发了新技术(硬件和软件)，以帮助人们更有效地训练他们的大脑。我们开发了创新的技术，当人们思考一项任务时，它可以引导他们。这项技术提供了关于他们大脑工作方式的反馈。这些反馈是通过电子设备提供的，每一秒都会给出一份关于大脑活动的报告，称为神经反馈。神经反馈可能会帮助人们以一种帮助他们更有效地学习的方式来使用他们的大脑。当我们在学习过程中思考一项任务时，神经反馈尤其重要，因为我们通常得不到反馈，这是学习的关键。我们的技术提供反馈，并帮助用户更好地改变他们的大脑活动。 问题是，我们的神经反馈技术并不像它应有的那样有效。我们的技术假设用户产生的大脑活动与你看到的模式相匹配，如果你将许多人的大脑活动平均在一起。这并不总是有效的，因为不同的人使用大脑的方式有很大的差异。我的研究计划将开发新的软件，以提供个性化的神经反馈，解释用户之间的差异。我将进行测试，看看个性化的神经反馈是否有助于人们更好地改变他们的大脑活动。 我的研究还将首次使用大数据来更好地理解我们在个性化神经反馈时将使用的信号。这将把我们开发的用于分析大脑成像数据的软件与使用一套称为机器学习(借用自计算机科学)的算法的大数据结合起来。这种新的组合有可能通过考虑个体变异性以及年龄和性别等人口统计因素来改善神经反馈系统。 神经反馈系统只有以人的大脑发出的正确信号为目标时才有效。我的研究重点是确保我们每次都能瞄准正确的信号。如果神经反馈更有效，那么它将被更多的研究人员和公司用来帮助人们改善大脑。这有可能帮助人们更好地学习，并帮助患者在中风或脑损伤后更好地恢复。我有一些合作者对我的技术的这些应用程序感兴趣。我的探索基金研究将帮助他们帮助人们。

My research program develops new technology (hardware and software) to aid people to train their brain more effectively. We have developed innovative technology that guides people when they are thinking about a task. The technology provides feedback about how their brain is working. The feedback - provided on an electronic device - gives a second-by-second report about brain activity, called neurofeedback. Neurofeedback might help people to use their brain in a way that will help them learn more effectively. Neurofeedback is particularly important when we are thinking about a task during the learning process because we don't usually get feedback, which is key to learning. Our technology provides that feedback, and helps users to change their brain activity for the better. The problem is that our neurofeedback technology is not as effective as it could be. Our technology assumes that the brain activity that a user generates matches to the pattern that you see if you average a lot of people's brain activity together. This doesn't always work because there is a lot of variability in how different people use their brains. My research program will develop new software to provide personalized neurofeedback that accounts for the variability between users. I will test to see if personalized neurofeedback helps people change their brain activity for the better. My research will also, for the first time, use big data to better understand the signals that we will use when we personalize neurofeedback. This will combine the software that we develop for analyzing brain imaging data with big data using a set of algorithms called machine learning (borrowed from Computer Science). This novel combination has the potential to improve neurofeedback systems by accounting for individual variability, as well as demographic factors like age and gender. A neurofeedback system is only effective if it targets the right signals from a person's brain. My research is focused on making sure that we target the right signals every time. If neurofeedback is more effective, then it will be used by more researchers and companies to help people improve their brains. This has the potential to help people learn better, and to help patients recover better after a stroke or brain injury. I have collaborators that are interested in these applications for my technology. My Discovery Grant research will help them to help people.