| dc.coverage.temporal | 計畫年度：91 起迄日期：20020801～20030731 | en_US |
| dc.creator (作者) | 翁久幸 | zh_TW |
| dc.date (日期) | 2002 | en_US |
| dc.date.accessioned | 18-Apr-2007 16:36:42 (UTC+8) | en_US |
| dc.date.accessioned | 8-Sep-2008 16:05:42 (UTC+8) | - |
| dc.date.available | 18-Apr-2007 16:36:42 (UTC+8) | en_US |
| dc.date.available | 8-Sep-2008 16:05:42 (UTC+8) | - |
| dc.date.issued (上傳時間) | 18-Apr-2007 16:36:42 (UTC+8) | en_US |
| dc.identifier (Other Identifiers) | 912118M004003.pdf | en_US |
| dc.identifier.uri (URI) | http://tair.lib.ntu.edu.tw:8000/123456789/3840 | en_US |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/3840 | - |
| dc.description (描述) | 核定金額：406200元 | en_US |
| dc.description.abstract (摘要) | 時間序列分析所討論的課題很多，這裡我們考慮關於時間序列的分段與確認(Segmentation and identification)之問題。也就是說，若一時間序列由若干個未知 模型分別在不同的時間區間內生成，我們要找出其分段點及其生成之模型。我們的解決辦法是結合支撐向量法(Support vector machines)與統計的叢聚分析 (Clustering analysis)。該方法可以應用於許多複雜的時間序列，例如 Mackey-Glass, EEG。本論文創新處包括提出一個支撐向量法的新形式，與一個調整控制模型間競爭程度之參數的新方法。前者主要是對支撐向量法模型的誤差項給予不同的權重，以配合該時間序列是由若干個未知模型分別生成的特質；後者則是利用最大概似估計法調整參數。此研究成果已發表於研討會 (Chang, Lin, and Weng [2])，而此研討會論文經過重新 整理後，已經投稿於IEEE Transactions on Neural Networks，目前已被接受，即將刊登[3]。上述之方法也被應用在 Traveling salesman problems, 並且發表於研討會(Chang, Lin, and Weng [3])。 | - |
| dc.description.abstract (摘要) | We present a framework for the unsupervised segmentation of switching dynamics using support vector machines. Following the architecture by Pawelzik et al. [8] where annealed competing neural networks were used to segment a non-stationary time series, in this article we exploit the use of support vector machines, a well-known learning technique. First, a new formulation of support vector regression is proposed. Second, an expectation-maximization (EM) step is suggested to adaptively adjust the annealing parameter. Experimental results using chaotic time series indicate that the proposed approach is promising. | - |
| dc.format | applicaiton/pdf | en_US |
| dc.format.extent | bytes | en_US |
| dc.format.extent | 90009 bytes | en_US |
| dc.format.extent | 90009 bytes | - |
| dc.format.extent | 4961 bytes | - |
| dc.format.mimetype | application/pdf | en_US |
| dc.format.mimetype | application/pdf | en_US |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | text/plain | - |
| dc.language | zh-TW | en_US |
| dc.language.iso | zh-TW | en_US |
| dc.publisher (Publisher) | 臺北市：國立政治大學統計學系 | en_US |
| dc.rights (Rights) | 行政院國家科學委員會 | en_US |
| dc.subject (關鍵詞) | 時間序列;混合模型;支撐向量法;期望值-最大化 | - |
| dc.subject (關鍵詞) | Time series;Mixture models;Support vector machines;Expectation-maximization | - |
| dc.title (題名) | 混合型時間序列模型之分析 | zh_TW |
| dc.title.alternative (其他題名) | Analysis of Mixtures of Time Series Models | - |
| dc.type (資料類型) | report | en |
