首页 | 本学科首页   官方微博 | 高级检索  
     

基于血液光谱的物种检测技术
引用本文:李宏霄,孙美秀,王振南,赵晓萌,向志光,汪毅,李迎新. 基于血液光谱的物种检测技术[J]. 北京理工大学学报, 2017, 37(S1): 1-4
作者姓名:李宏霄  孙美秀  王振南  赵晓萌  向志光  汪毅  李迎新
作者单位:中国医学科学院 北京协和医学院生物医学工程研究所, 天津 300092;天津大学 光电信息技术教育部重点实验室, 天津 300072,中国医学科学院 北京协和医学院生物医学工程研究所, 天津 300092,中国医学科学院 北京协和医学院生物医学工程研究所, 天津 300092,中国医学科学院 北京协和医学院生物医学工程研究所, 天津 300092,中国医学科学院 北京协和医学院医学实验动物研究所, 北京 100021,天津大学 光电信息技术教育部重点实验室, 天津 300072,中国医学科学院 北京协和医学院生物医学工程研究所, 天津 300092
基金项目:国家"八六三"计划项目(2015AA021105);中央级公益性科研院所基本科研业务费项目(2016ZX310104);天津大学光电信息技术教育部重点实验室开放课题项目资助(2015KFKT015)
摘    要:提出一种基于血液光谱数据识别血液来源物种的光谱检测技术.设计制作了一套可以采集抗凝管血样光谱的检测设备,使用该设备采集了649个血样的光谱数据,建立了一个小型的血液光谱数据集.为了满足物种识别的需求,建立了一种基于数据驱动的建模方法.使用该方法对样本数据集进行交叉验证,可以达到95%的识别准确率,并发现该准确率随着样本数量增加而升高.

关 键 词:血液光谱  物种识别  数据驱动模型  模式识别
收稿时间:2016-11-19

Species Detection Based on Blood Spectrum
LI Hong-xiao,SUN Mei-xiu,WANG Zhen-nan,ZHAO Xiao-meng,XIANG Zhi-guang,WANG Yi and LI Ying-xin. Species Detection Based on Blood Spectrum[J]. Journal of Beijing Institute of Technology(Natural Science Edition), 2017, 37(S1): 1-4
Authors:LI Hong-xiao  SUN Mei-xiu  WANG Zhen-nan  ZHAO Xiao-meng  XIANG Zhi-guang  WANG Yi  LI Ying-xin
Affiliation:Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin 300092, China;Tianjin University Key Laboratory of Optoelectronic Information Technology of Ministry of Education, Tianjin 300072, China,Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin 300092, China,Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin 300092, China,Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin 300092, China,Institute of Laboratory Animal Sciences, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100021, China,Tianjin University Key Laboratory of Optoelectronic Information Technology of Ministry of Education, Tianjin 300072, China and Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin 300092, China
Abstract:A spectrum detection technique based on blood spectrum data to identify blood source species was proposed.A device which can collect the spectrum of the blood sample in the anticoagulant tube was designed,and the spectrum data of 649 blood samples were collected by the equipment.In order to meet the needs of species identification,a data driven modeling method was established.Use this method to cross-validate the sample dataset,the recognition accuracy rate can reach 95%,and the accuracy was found to increase with the increasing of sample size.
Keywords:blood spectrum  species identification  data driven model  pattern recognition
点击此处可从《北京理工大学学报》浏览原始摘要信息
点击此处可从《北京理工大学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号