Update on

Since my previous update, I’ve progressed on my project. I am trying to build a connection between a brain and a computer, and perhaps eventually the body. I define the problem below

There are 15.4 million people with spinal cord injury, which disrupts the connection between their brain and muscles. Current technology does not reliably restore intuitive voluntary movement. A system that would be able to understand what the user wants to do and stimulate their muscles would restore voluntary movement.

Since the last update, I’ve done research to better understand the potential target market to allow me to focus my project more specifically.

There are two main parts of paralysis I’m looking at: paraplegia and tetraplegia. Paraplegia is the paralysis of the legs while tetraplegia is the paralysis of all 4 limbs and the torso.

I have decided I will start as simple as possible. My procedure is as follows: Use the BCI CV 2a Dataset to train a classification model that gets a minimum 95% accuracy score. Then, I will purchase an affordable EEG headset. I will need to make a new model based off the previous one for the specifications of the new headset.

The main part of the definition statement this focuses on is “understand what the user wants to do.” That part is much safer to focus on because once the human body gets involved, I am at risk of harming someone, for example if I tested it on myself(which I probably would), I might damage something in my body.

The biggest challenge I foresee is coding the classification model because it has been some time since I’ve done any big coding projects, so it might take some time for me to remember.

As of right now, my next step is to create the classifier model.

I have used AI to assist me in my project to help me unpack such a complex topic. The transcripts are listed below:

https://docs.google.com/document/d/1CoE7TABSEuxQ2X2NbVKCYMHyMqrHT-zPR7hzq_gNGlI/edit?usp=sharing