EEG Data Visualization Platform that Enables Machine Learning Based Analysis for Fast BCI Experimentation
There are multiple EEG streaming and analyzation interfaces that utilize machine-learning and data filtering algorithms to classify brain activity. They have three major limitations: they employ slow algorithms, data feedback systems, and visualizations; they are unable to support real-time data streaming and rely on external files for static data; and they require complex integrations to numerous external analysis tools. This limits experimentation time and requires researchers and students, who are users of such platforms, to have a deep technical expertise in computational neuroscience.
The proposed solution, Brainee, is an EEG analyzation platform that uses a Muse consumer-grade EEG headset and a web-based application to run simple and fast motor imagery and emotional classification experiments. Brainee contains real-time data streaming, powerful integrated machine-learning algorithms that provide high accuracy classifications, and interactive visualizations in a user-friendly interface. This makes it easy and fast to run experiments without the need for deep technical expertise, expands the scope and size of the neuroscience research that can be conducted, lowers the total cost of experimentation.