摘要
A neural network ensemble algorithm used in automatic target recognition (ATR) was designed based on multi-DSP mixture structure. It is formed a same type classifier under different size and initial condition by BP neural networks, and map every output of neural network into posteriori probability, then make weighted summation and judge. Real-time recognition was run by the neural networks ensemble system. The result showed that statistic recognition rate was up to 97 percent for 8 type object. The processing was finished in 30 ms. The recognition rate was better than single neural networks obviously.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | Proceedings - Third International Conference on Natural Computation, ICNC 2007 |
| 页 | 162-166 |
| 页数 | 5 |
| DOI | |
| 出版状态 | 已出版 - 2007 |
| 活动 | 3rd International Conference on Natural Computation, ICNC 2007 - Haikou, Hainan, 中国 期限: 24 8月 2007 → 27 8月 2007 |
出版系列
| 姓名 | Proceedings - Third International Conference on Natural Computation, ICNC 2007 |
|---|---|
| 卷 | 5 |
会议
| 会议 | 3rd International Conference on Natural Computation, ICNC 2007 |
|---|---|
| 国家/地区 | 中国 |
| 市 | Haikou, Hainan |
| 时期 | 24/08/07 → 27/08/07 |
指纹
探究 'Research on algorithms of neural network ensemble with multi-dsp mixture structure' 的科研主题。它们共同构成独一无二的指纹。引用此
Xu, T., & Ni, G. (2007). Research on algorithms of neural network ensemble with multi-dsp mixture structure. 在 Proceedings - Third International Conference on Natural Computation, ICNC 2007 (页码 162-166). 文章 4305035 (Proceedings - Third International Conference on Natural Computation, ICNC 2007; 卷 5). https://doi.org/10.1109/ICNC.2007.614