雨生红球藻生长阶段分类研究  

Classification of growth stages of Haematococcus pluvialis

作　　者：杨梦玉 崔世钢[1,2] 王永亮[1] YANG Mengyu;CUI Shigang;WANG Yongliang(School of Automation and Electrical Engineering,Tianjin University of Technology and Education,Tianjin 300222,China;Tianjin Key Laboratory of Information Sensing and Intelligent Control,Tianjin University of Technology and Education,Tianjin 300222,China)

机构地区：[1]天津职业技术师范大学自动化与电气工程学院,天津300222 [2]天津职业技术师范大学天津市信息传感与智能控制重点实验室,天津300222

出　　处：《天津职业技术师范大学学报》2021年第4期58-63,共6页Journal of Tianjin University of Technology and Education

基　　金：国家重点研发计划项目(2017YFB0403904);天津职业技术师范大学科研发展基金资助项目(KJ2007).

摘　　要：针对雨生红球藻细胞在不同生长阶段呈现不同特征的问题,采用C4.5决策树算法,对雨生红球藻细胞在生长过程中的细胞属性进行选取并对细胞数据进行采集,以雨生红球藻的细胞半径、细胞个数、吸光度值、颜色作为划分属性,对处于细胞增殖阶段与虾青素积累阶段的藻细胞进行分类。实验结果表明:利用训练集对决策树模型进行训练,通过对前期实验数据的学习,该模型对未见示例进行预测,准确率较高,可以生成一棵泛化能力较强的决策树,实现了对雨生红球藻所处的2个生长阶段进行分类的目标。Haematococcus pluvialis shows different characteristics in different growth stages.In order to classify algal cells in the phase of the cells in cell proliferation stage and astaxanthin accumulation stage,the C4.5 decision tree algorithm was adopted to classify the cells in two different growth stages by selecting the cell attributes and collecting the cell data and taking the cell radius,number,absorbency value(OD value)and color of the cells as the dividing attributes.The experimental results showed that the training set was used to train the decision tree model,and by learning the experimental data in the early stage,the model could predict the unknown examples with high accuracy and generate a decision tree with strong generalization ability,so as to realize the classification of the two growth stages of the hygrophyta.

关 键 词：C4.5决策树算法 雨生红球藻 虾青素 细胞分类 

分 类 号：Q945.3[生物学—植物学]