Project

AttentivU - Brain Switch

Copyright

MIT Media Lab

Sophia Rim 

The Brain Switch is a real-time, closed-loop brain-computer system allowing for real-time correspondence of simple user needs to a caretaker non-verbally. The Brain Switch is a lightweight, wearable and wireless system which aims on helping to restore and support communication to those with physical challenges (ALS, CP, SCI).

Brain Switch is a part  of AttentivU system. Its architecture consists of wearable, wireless electroencephalography system, which is comfortable to the user and can be worn over extended periods of time (no sticky electrodes, 8hours+ of active use; 2 hours of charging time). It supports different needs of the users, for example, those who require or wish to remain in bed, have limited neck muscle support, etc.  No need for any muscle activity or even eye activity is needed. In addition, two mobile applications are being provided to the family. They connect to a server, one being a notification app used by the caretaker for remote insights (e.g., what the user is in need now) and the other, used by or near the patient. The patient's app streams packets of raw … View full description

The Brain Switch is a real-time, closed-loop brain-computer system allowing for real-time correspondence of simple user needs to a caretaker non-verbally. The Brain Switch is a lightweight, wearable and wireless system which aims on helping to restore and support communication to those with physical challenges (ALS, CP, SCI).

Brain Switch is a part  of AttentivU system. Its architecture consists of wearable, wireless electroencephalography system, which is comfortable to the user and can be worn over extended periods of time (no sticky electrodes, 8hours+ of active use; 2 hours of charging time). It supports different needs of the users, for example, those who require or wish to remain in bed, have limited neck muscle support, etc.  No need for any muscle activity or even eye activity is needed. In addition, two mobile applications are being provided to the family. They connect to a server, one being a notification app used by the caretaker for remote insights (e.g., what the user is in need now) and the other, used by or near the patient. The patient's app streams packets of raw electroencephalography data from a  brain computer interface back to the server. With this information, a convolutional neural network is trained and used to classify mental states like imagery as well as attention of the user in real-time. Enabled by the cloud platform, the system is able to work anywhere and on a multitude of devices, computationally unlimited. 

Using Brain Switch, the caretaker can be notified remotely if the user needs something like eye drops or to be turned, can ask questions ("Do you want the music on?" and see a response in the app in real-time), and monitor the overall well-being of the patient in real-time, all without a muscle being moved. 

Collaborators in this project:  Arnav Balyan, Noah Pacik-Nelson