基本信息:
- 专利标题： 基于主成分分析‑BP神经网络的包虫病患者血清的光谱识别方法
- 专利标题（英）：Echinococcosis patient serum spectral recognition method based on principal component analysis and BP neural network
- 申请号：CN201611178745.2 申请日：2016-12-19
- 公开(公告)号：CN106596507A 公开(公告)日：2017-04-26
- 发明人： 温浩 , 吕国栋 , 程金盈 , 吕小毅 , 莫家庆 , 刘辉 , 林仁勇 , 卢晓梅 , 李亮 , 毕晓娟 , 张传山 , 杨宁
- 申请人： 新疆医科大学第一附属医院
- 申请人地址： 新疆维吾尔自治区乌鲁木齐市新市区鲤鱼山南路137号新疆医科大学第一附属医院科研科
- 专利权人： 新疆医科大学第一附属医院
- 当前专利权人： 新疆医科大学第一附属医院
- 当前专利权人地址： 新疆维吾尔自治区乌鲁木齐市新市区鲤鱼山南路137号新疆医科大学第一附属医院科研科
- 代理机构： 乌鲁木齐合纵专利商标事务所
- 代理人： 汤建武; 杨涵
- 主分类号： G01N21/65
- IPC分类号： G01N21/65
The invention relates to the technical field of spectral recognition, and provides an echinococcosis patient serum spectral recognition method based on principal component analysis and a BP neural network. The method is implemented according to the steps that 1, serum of at least 20 healthy persons and serum of at least 20 echinococcosis patients are sucked separately and placed in a raman spectrometer for full-wavelength scanning and data collecting; 2, collected data is subjected to normalization processing; 3, the data obtained after normalization is subjected to principle component analysis, and scores of all principle components of which the accumulated contribution rates reach 80% are taken as input layer nodes of the BP neural network. According to the method, an echinococcosis spectral diagnosis technical scheme with the high accuracy is established by adopting the method of combining principle component analysis (PCA) with the BP neural network, the diagnosis accuracy rate is high, and operation and implementation are convenient.
IPC结构图谱:
| G | 物理 |
| --G01 | 测量；测试 |
| ----G01N | 借助于测定材料的化学或物理性质来测试或分析材料 |
| ------G01N21/00 | 利用光学手段，即利用红外光、可见光或紫外光来测试或分析材料 |
| --------G01N21/01 | .便于进行光学测试的装置或仪器 |
| ----------G01N21/63 | ..光学激发的 |
| ------------G01N21/65 | ...喇曼散射 |