Georgia Institute of Technology
Study of soft materials, flexible electronics, and machine learning for fully portable and wireless brain-machine interfaces
Abstract
dc:description.abstractOver 300,000 individuals in the United States are afflicted with some form of limited motor function from brainstem or spinal-cord related injury resulting in quadriplegia or some form of locked-in syndrome. Conventional brain-machine interfaces used to allow for communication or movement require heavy, rigid components, uncomfortable headgear, excessive numbers of electrodes, and bulky electronics with long wires that result in greater data artifacts and generally inadequate performance. Wireless, wearable electroencephalograms, along with dry non-invasive electrodes can be utilized to allow recording of brain activity on a mobile subject to allow for unrestricted movement. Additionally, multilayer microfabricated flexible circuits, when combined with a soft materials platform allows for imperceptible wearable data acquisition electronics for long term recording. This dissertation aims to introduce new electronics and training paradigms for brain-machine interfaces to provide remedies in the form of communication and movement for these individuals. Here, training is optimized by generating a virtual environment from which a subject can achieve immersion using a VR headset in order to train and familiarize with the system. Advances in hardware and implementation of convolutional neural networks allow for rapid classification and low-latency target control. Integration of materials, mechanics, circuit and electrode design results in an optimized brain-machine interface allowing for rehabilitation and overall improved quality of life.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Mechanical Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Mahmood, Musa
- Advisor dc:contributor.advisor
-
- Yeo, Woon-Hong
- Committee members dc:contributor.committeemember
-
- Hammond, Frank
- Sulchek, Todd
- Shinohara, Minoru
- Duarte, Audrey
Subjects
dc:subject × 2Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/70058