Improving Decoding of Electrocorticographic Signals using Deep Learning Public
Li, Kejun (Spring 2019)
Published
Abstract
Brain-machine Interfaces (BMIs) are technologies that aim to assist people who suffer from loss of motor function due to accidents or neurodegenerative diseases, by providing a pathway between brain and external assistive devices. Electrocorticography (ECoG) is one of the recording methodologies that could be used to infer people’s movement intention for BMI systems. ECoG covers large areas of the brain and has a demonstrated safety record. However, its low spatial resolution usually leads to worse accuracy in decoding movement intention than BMIs that use intracortical recordings. In this study, we found that ECoG decoding performance could be improved by modeling neural population dynamics using a deep learning technique: Latent Factor Analysis via Dynamical Systems (LFADS). LFADS attempts to uncover structure from neural population activity that is consistent with a low-dimensional dynamical system. In previous applications to intracortical recording from motor cortex, LFADS improved decoding accuracy by uncovering estimates of neural population dynamics on a single-trial, moment-by-moment basis. However, since LFADS was previously evaluated using intracortical recordings with high spatial resolution, it was unclear whether LFADS is appropriate for de-noising recordings with low spatial resolution, such as ECoG. To test this, we applied LFADS to ECoG recordings from seven human subjects who were being monitored as part of clinical treatment for epilepsy or glioma. Subjects performed a one-finger button-press task as their finger kinematics and kinetics were recorded. We compared our ability to decode behavioral states (i.e. pre-movement, movement or force) before and after application of LFADS. The accuracy of the discrete classifier was improved significantly by the application of LFADS. Our results represent a new avenue toward improving the performance of ECoG-based BMI systems.
Table of Contents
Terminology and Abbreviations …..………………………………………….…………… 1
Introduction …………………………………………….………………………….……… 2 - 5
Methods …………………………………………….………………………….………… 6 - 14
1. Subjects and Recording
2. Experimental Protocol
3. Spectral Feature Extraction
4. Spectral Feature Extraction and Power Amplitude (PA) Matrix
5. LFADS Structure
6. Hyperparameter Tuning with Population-based Training
7. Principal Component Analysis
8. Decoding Analysis
Results …………………………………………….………………………….………… 15 - 17
Figures …………………………………………….………………………….………… 18 - 25
1. Demonstration of PCA analysis
2. Decision tree diagram
3. Experimental protocols and recording ECOG array placement for the subjects.
4. Scheme for discrete states classifiers
5. Percent variance explained by the first three principal components from PCA for PA matrix and LFADS-denoised ECoG
6. Example trial for ECoG and PCA trajectories of PA matrix and LFADS-denoised ECoG
7. Bagged trees decoding performance
Discussions …………………………………………….………………………….…... 26 - 29
References …………………………………………….………………………….……. 30 - 33
About this Honors Thesis
| School | |
|---|---|
| Department | |
| Degree | |
| Submission | |
| Language |
|
| Research Field | |
| Mot-clé | |
| Committee Chair / Thesis Advisor | |
| Committee Members |
Primary PDF
| Thumbnail | Title | Date Uploaded | Actions |
|---|---|---|---|
|
|
Improving Decoding of Electrocorticographic Signals using Deep Learning () | 2019-04-09 11:28:26 -0400 |
|
Supplemental Files
| Thumbnail | Title | Date Uploaded | Actions |
|---|