Nonlinear Manifold Alignment Decoding (NoMAD) for Robust Brain-Machine Interfaces

­ Application Nonlinear Manifold Alignment Decoding for Brain-Machine Interface (BMI). Key Benefits Accurate, non-invasive prediction of gallstones in the bile duct. Based on readily available patient information. Market Summary The inven…

Application
Nonlinear Manifold Alignment Decoding for Brain-Machine Interface (BMI).

Key Benefits

  • Accurate, non-invasive prediction of gallstones in the bile duct.
  • Based on readily available patient information.


Market Summary
The invention described in this disclosure could contribute to the global neuroprosthetics market which is expected to reach $14.6 billion by 2024 (Grand View Research). Furthermore, global hardware sales revenue from brain-machine interfaces (BMIs) is expected to reach $19 billion per annum from $2.4 billion in 2018 (Juniper Research, March 2018). There has been an increasing prevalence of neurological disorders, thus, there is a need for more cost-effective and efficient technologies and methods to address the issue. Additionally, there is an increasing interest in BMIs for healthy subjects to have more efficient and fluid interactions with computers, particularly in augmented or virtual reality environments. NoMAD addresses a critical robustness challenge with all previous BMIs, by enabling extended uninterrupted device use through lack of frequent recalibration.

Technical Summary
Researchers developed an AI algorithm that demonstrates significant improvement in stability and performance in neural prosthetic devices over state-of-the-art alternatives. The algorithm, NoMAD (Nonlinear Manifold Alignment Decoding) attains accurate alignment between complex neural signals arising from co-activation across neural populations over a period over time, thus creating an invariant signal from which to predict the intended motor control accurately for a longer period of time without recalibration. Researchers were able to demonstrate that with unsupervised alignment NoMAD was able to stabilize the accuracy of predictions from neural activity over a more than three-month duration.

Developmental Stage
Prototype tested.

Website

https://emoryott.technologypublisher.com/techcase/20056

Contact Information

TTO Home Page: https://emoryott.technologypublisher.com

Name: Hyeon (Sean) Kim

Title: Licensing Associate

Email: hkim70@emory.edu

Phone: 404-727-7218