| dc.contributor | 統計系 | |
| dc.creator (作者) | 周珮婷 | |
| dc.date (日期) | 2016-12 | |
| dc.date.accessioned | 4-Jun-2026 09:08:13 (UTC+8) | - |
| dc.date.available | 4-Jun-2026 09:08:13 (UTC+8) | - |
| dc.date.issued (上傳時間) | 4-Jun-2026 09:08:13 (UTC+8) | - |
| dc.identifier.uri (URI) | https://ah.lib.nccu.edu.tw/item?item_id=182732 | - |
| dc.description.abstract (摘要) | 我們提出了一個雙向的DCG分群方法，從功能性磁振造影資料成像數據中，提取腦部活 動的特殊模式。透過結合兩個DCG分類樹，其中一個為建給觀測對象，另一個為建給變數， 用來確定對象群和變數群之間的許多的交互模式。這些交互模式可進一步計算成“雙關係"。 我們透過分析一個真正的功能性磁振造影資料成像數據來說明此方法，我們可因此對於不同 的疾病找出雙關係，這種雙關係的發現就像發現一個生物標誌。這些計算出的生物標誌的整 個集合構成了整體性特徵整合矩陣，這是一個非常有效的機器學習算法。此外，我們談到了 如何進化一個簡單的經驗距離，以提高整體性特徵整合矩陣學習的效率。我們也對功能性磁 振造影如何做特徵萃取提供不同的演算法。此研究提出了功能性磁振造影成像數據分析和大 腦狀態解碼的一個創新方法。 | |
| dc.description.abstract (摘要) | We propose a two-way clustering procedure through a DCG clustering method to extract the special patterns of brain activities from fMRI data. By coupling the two DCG trees, one for the subject space and the other for the covariate space, many partial interaction patterns between subject-clusters and covariate-clusters can be determined. These interaction patterns are further distilled computationally into dual-relationships. We illustrate with real fMRI dataset, where we demonstrate that such dual-relationships are indeed class specific, each precisely representing the discovery of a biomarker. The whole collection of computed biomarkers constitutes a global feature-matrix, which is then shown to give rise to a very effective learning algorithm. Also, we talked about how to adaptively evolve a simple empirical distance into an effective one in order to facilitate an efficient global feature-matrix for learning purposes. Furthermore, we provide different methods for feature extraction. This project provides an innovative method for fMRI data classification and brain states decoding. | |
| dc.format.extent | 116 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | 科技部, MOST104-2118-M004-007, 104.08-105.07 | |
| dc.title (題名) | 功能性磁振造影資料解碼 | |
| dc.title (題名) | Decoding Brain States from Fmri Data with Machine Learning Methods | |
| dc.type (資料類型) | report | |
