Geometric methods for covariance-based neural decoding
Neuroimaging tasks present significant challenges in signal processing and analysis due to factors such as low signal-to-noise ratios, high non-stationarity, and limited dataset sizes. Furthermore, understanding brain dynamics is complicated by the coupling mechanisms across various neuroimaging mod...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Doctor of Philosophy |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/179776 |
| _version_ | 1811684769143980032 |
|---|---|
| author | Ju, Ce |
| author2 | Guan Cuntai |
| author_facet | Guan Cuntai Ju, Ce |
| author_sort | Ju, Ce |
| collection | NTU |
| description | Neuroimaging tasks present significant challenges in signal processing and analysis due to factors such as low signal-to-noise ratios, high non-stationarity, and limited dataset sizes. Furthermore, understanding brain dynamics is complicated by the coupling mechanisms across various neuroimaging modalities. To address these challenges, my study introduces an alternative approach by formulating covariance-based neuroimaging data on symmetric positive definite manifolds. I integrate various geometric methods to model this data and develop geometric deep learning frameworks for multiple neuroimaging tasks, including EEG-based motor imagery classification and the multimodal fusion of simultaneous EEG-fMRI data. |
| first_indexed | 2024-10-01T04:33:53Z |
| format | Thesis-Doctor of Philosophy |
| id | ntu-10356/179776 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:33:53Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1797762024-09-04T07:56:36Z Geometric methods for covariance-based neural decoding Ju, Ce Guan Cuntai College of Computing and Data Science CTGuan@ntu.edu.sg Computer and Information Science Geometric methods Brain-computer interfaces Geometric deep learning Riemannian geometry Neuroimaging tasks present significant challenges in signal processing and analysis due to factors such as low signal-to-noise ratios, high non-stationarity, and limited dataset sizes. Furthermore, understanding brain dynamics is complicated by the coupling mechanisms across various neuroimaging modalities. To address these challenges, my study introduces an alternative approach by formulating covariance-based neuroimaging data on symmetric positive definite manifolds. I integrate various geometric methods to model this data and develop geometric deep learning frameworks for multiple neuroimaging tasks, including EEG-based motor imagery classification and the multimodal fusion of simultaneous EEG-fMRI data. Doctor of Philosophy 2024-08-23T00:09:36Z 2024-08-23T00:09:36Z 2024 Thesis-Doctor of Philosophy Ju, C. (2024). Geometric methods for covariance-based neural decoding. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/179776 https://hdl.handle.net/10356/179776 10.32657/10356/179776 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Geometric methods Brain-computer interfaces Geometric deep learning Riemannian geometry Ju, Ce Geometric methods for covariance-based neural decoding |
| title | Geometric methods for covariance-based neural decoding |
| title_full | Geometric methods for covariance-based neural decoding |
| title_fullStr | Geometric methods for covariance-based neural decoding |
| title_full_unstemmed | Geometric methods for covariance-based neural decoding |
| title_short | Geometric methods for covariance-based neural decoding |
| title_sort | geometric methods for covariance based neural decoding |
| topic | Computer and Information Science Geometric methods Brain-computer interfaces Geometric deep learning Riemannian geometry |
| url | https://hdl.handle.net/10356/179776 |
| work_keys_str_mv | AT juce geometricmethodsforcovariancebasedneuraldecoding |