Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/18226
題名: | Analysis of Switching Dynamics with Competing Support Vector Machine | 作者: | 張洺偉;林智仁;翁久幸 Chang, Ming-Wei;Lin, Chih-Jen;Weng, Ruby C. |
日期: | May-2004 | 上傳時間: | 19-Dec-2008 | 摘要: | We present a framework for the unsupervised segmentation\r\nof switching dynamics using support vector machines.\r\nFollowing the architecture by Pawelzik et al., where annealed competing\r\nneural networks were used to segment a nonstationary time\r\nseries, in this paper, we exploit the use of support vector machines,\r\na well-known learning technique. First, a new formulation of support\r\nvector regression is proposed. Second, an expectation-maximization\r\nstep is suggested to adaptively adjust the annealing parameter.\r\nResults indicate that the proposed approach is promising. | 關聯: | IEEE Transactions on Neural Networks 15(3),720-727 | 資料類型: | article | DOI: | http://dx.doi.org/10.1109/IJCNN.2002.1007515 |
Appears in Collections: | 期刊論文 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
720727.pdf | 666.14 kB | Adobe PDF2 | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.