SBIR Phase I: Brain Wave Adaptive Learning for Accelerated Adaptive Learning for STEM Education

这个SBIR第一阶段项目将为STEM教育开发一个用于加速适应性学习的脑机接口(BCI)。首次将使用脑电头带的脑机接口应用于基于学习策略的自适应学习。脑电是一种非侵入性的测量脑波模式的方法，用于识别大脑中的电活动。所提出的学习系统将提供五种学习策略--学徒策略、偶发策略、归纳策略、演绎策略和发现策略，并提供实时学习者分析。基于脑电头带的脑机接口自适应学习将为学习者提供实时的神经反馈，以确定最优的学习策略。预计使用多通道脑电头带直接采集脑波数据将导致更快地收敛到最优学习策略，使学习者达到最大学习结果。这种方法将允许我们将脑波分析与实时统计推理相结合，以提高学习者的表现。结合脑电波数据和学习者表现的多变量相关分析，将使所提出的用于加速自适应学习的BCI方法得到验证。随着EEG头带技术和低能量蓝牙接口的发展，提出的STEM教育方法将有可能在学校和大学商业化。使用EEG头带加速自适应学习的脑机接口将打破许多新的技术基础。第一次，个体学习者的脑波数据将被用来确定个人的学习偏好和学习策略。Alfa、Beta和Gamma脑波的分布将提供关于接受差异化学习策略的学习者的大脑状态的丰富信息。BCI方法将基于个体学习者的实时脑波分析，加速识别最佳学习结果的学习策略。拟议的项目还将提供前所未有的机会来评估神经反馈对STEM学生学习结果的影响。该项目将引发脑波自适应学习的新技术趋势，将产生许多用于高堆栈学习和培训的新应用和产品。基于脑机接口的适应性学习也将帮助认知障碍(自闭症谱系)、ADD和ADHD的学生，作为教育项目的学习辅助。数据驱动反馈的脑波自适应学习将对提高STEM教育的完成率和毕业率非常有用。

This SBIR Phase I project will develop a Brain Computer Interface (BCI) for Accelerated Adaptive Learning for STEM education. For the first time, the brain computer interface using Electroencephalogram (EEG) headband will be applied to the learning strategies based adaptive learning. Electroencephalogram is a none-invasive method for measuring brain wave pattern for identification of electrical activities in the brain. The proposed learning system will provide five learning strategies - apprentice, incidental, inductive, deductive and discovery with real-time learner analytics. The EEG headband based BCI for adaptive learning will provide real time neuro feedback to learners for identification of optimum learning strategy. It is expected that the direct collection of brain wave data using multi-channel EEG headband will lead to faster convergence to optimum learning strategy for learners to reach the maximum learning outcome. This approach will allow us to combine brain wave analytics with the real-time statistical inference to improve performance of the learner. The combination of brain wave data and multivariate correlation analysis of the learner performance will enable validation of the proposed BCI approach for accelerated adaptive learning. With the growth of EEG headband technology and low energy blue tooth interface it will be possible to commercialize proposed approach for STEM education in schools and colleges.Brain Computer Interface for accelerate adaptive learning using EEG headbands will break numerous new technical grounds. For the first time the brain wave data of the individual learner will be used to identify personal learning preferences and learning strategy. The distribution of Alfa, Beta and Gamma brain waves will provide wealth of information on the brain state of the learner exposed to the differentiated learning strategies. The BCI approach will lead to accelerated identification of learning strategy for the best learning outcome based on the real- time brain wave analysis for individual learners. The proposed project will also provide unprecedented opportunity to assess effect of neuro feedback on the learning outcome of the STEM students. This project will spark a new technology trend of brain wave adaptive learning that will yield numerous new applications and products for high-stack learning and training. The brain computer interface based adaptive learning will also help students with cognitive disability (autism spectrum), ADD and ADHD as study aid for educational programs. The brain wave adaptive learning with data-driven feedback will be extremely useful for improving completion and graduation rates for STEM education.