Improving Motor Imagery Based Brain Computer Interfaces Using A Novel Physical Feedback Technique

TL;DR

This paper introduces a novel physical feedback method for motor imagery BCI using electromagnetically manipulated ferrofluid droplets, enhancing user training accuracy and system applicability.

Contribution

The study presents a new physical feedback mechanism in BCI that physically reconstructs commands via ferrofluid movement, improving training and performance.

Findings

Average droplet speed of 0.469 cm/s

Average target hitting accuracy of 81.6%

Demonstrated potential for more real-world BCI applications

Abstract

In this project, and through an understanding of neuronal system communication, A novel model serves as an assistive technology for locked-in people suffering from Motor neuronal disease (MND) is proposed. Work was done upon the potential of brain wave activity patterns to be detected as electrical signals, classified and translated into commands following Brain Computer Interfaces (BCI) constructing paradigm. However, the interface constructed was for the first time a device which can reconstruct this command physically. The project novelty is in the feedback step, where an electromagnets magnetic field is used to showcase the command in ferrofluid droplets movement- these moved to assigned targets due to rotation of a glass surface desk according to the data received from the brain. The goal of this project is to address the challenges of the inaccurate performance in user-training which is yet the main issues preventing BCI from being upgraded into more applicable technology. Tests were performed based on Open ViBE software after uploading recorded files of Motor Imagery MI tasks and the design requirements tested were the motion speed of the droplet and accuracy of hitting fixed targets. An average speed of 0.469 cm/s and average accuracy of 81.6% were obtained from the best volume for the droplet. A conclusion to be drawn was that the promise of this other point of view on BCI systems to be more Brain-Real World Systems