|
|||||
|
|
| 并行计算在动态模式识别中的实现和应用* | |
| 引用本文： | 周龙沙,王聪,耿彤. 并行计算在动态模式识别中的实现和应用*[J]. 计算机应用研究, 2011, 28(3): 1012-1013. DOI: 10.3969/j.issn.1001-3695.2011.03.061 |
| 作者姓名： | 周龙沙 王聪 耿彤 |
| 作者单位： | 华南理工大学自动化科学与工程学院,广州,510641 |
| 基金项目： | 国家自然科学基金重大研究计划重点项目(90816028, 60934001) |
| 摘 要： | 研究一种针对最近提出的动态环境下的机器学习理论——确定学习理论的算法实现，提出一种采用并行计算实现确定学习理论中的动态模式识别的方法。利用并行计算中的OpenMP多核编程环境，采用曙光16核服务器为硬件平台，实现对动态模式识别算法的快速性。同时，以压气机Mansoux模型为应用背景，把确定学习理论的动态模式识别方法应用到压气机旋转失速/喘振的快速检测中，利用多核并行计算实现了从包含多种旋转失速/喘振模式的模式库中快速识别当前模式的方法，为文章中方法提供了一个有效的验证。 |
| 关 键 词： | 多核并行计算，模式识别，确定性学习 |
| 收稿时间： | 2010-08-27 |
| 修稿时间： | 2011-02-12 |
Realization and application of parallel computing in identification of dynamic model |
|
| ZHOU Long-sh,WANG Cong,GENG Tong. Realization and application of parallel computing in identification of dynamic model[J]. Application Research of Computers, 2011, 28(3): 1012-1013. DOI: 10.3969/j.issn.1001-3695.2011.03.061 | |
| Authors: | ZHOU Long-sh WANG Cong GENG Tong |
| Affiliation: | ZHOU Long-sha,WANG Cong,GENG Tong (School of Automation Science & Engineering,South China University of Technology,Guangzhou 510641,China) |
| Abstract: | The paper introduce a neural network-based learning theory, which is called the deterministic learning theory, and demonstrate the application of the theory in the dynamic pattern recognition. Based on the classical Mansoux compressor model, the deterministic learning theory is applied to the model and the parallel computing for the rapid recognition of compressor model under multi-dynamic patterns is achieved, by using the OpenMP multi-core programming environment and taking the DAWNING server as the hardware platform. It provides an excellent application for the parallel computing in rapid pattern recognition. |
| Keywords: | multi-core parallel computing OpenMP pattern recognition deterministic learning |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 | |
| 点击此处可从《计算机应用研究》下载全文 | |