|
|||||
|
|
| 神经网络用于血清的初级癌症诊断 | |
| 引用本文： | 林雍静 朱尔一 等. 神经网络用于血清的初级癌症诊断[J]. 厦门大学学报(自然科学版), 1996, 35(5): 769-773 |
| 作者姓名： | 林雍静 朱尔一 等 |
| 作者单位： | 厦门大学化学系 |
| 基金项目： | 国家及福建省自然科学基金 |
| 摘 要： | 用电感耦合等离子体原子光谱及石墨炉原子吸收测定了正常人及癌症病人血清样品中的６个元素，将所得数据送入计算机．用人工神经元网络的反向传播（ＢＰ）算法综合分析血清中的微量金属元素，预报识别率达９０％以上． |
| 关 键 词： | 人工神经网络，癌症诊断，血清 |
The Studies of Artificial Neutral Networks Applied to Preliminary Cancer Diagnosis of Blood Serum |
|
| Lin Yongjing, Zhu Eryi, Yang Pengyuan. The Studies of Artificial Neutral Networks Applied to Preliminary Cancer Diagnosis of Blood Serum[J]. Journal of Xiamen University(Natural Science), 1996, 35(5): 769-773 | |
| Authors: | Lin Yongjing Zhu Eryi Yang Pengyuan |
| Affiliation: | Dept. of Chem. |
| Abstract: | The concentrations of 6 trace elements in serum samples including both normal People and cancer patient samples were determined with ICP-AES and GF-AAS. These concentration data were then sent to computer. Three-layer artificial neural networks (ANN) with back-propagation of error were used to synthetically analyse the elements compounds. The network's architecture and parameters were optimized, and an empirical rule for dynamically adjusting the learning rate of network was put forward. It was found that the network convergedquickly, and the recognition rate was over 90%. |
| Keywords: | Artificial neural networks Cancer diagnosis Blood serum |
| 本文献已被 CNKI 维普 等数据库收录！ | |