| 基于遗传算法和BP神经网络的CTG识别研究 |
| |
| 引用本文： | 周红标,张宇林,胡金平.基于遗传算法和BP神经网络的CTG识别研究[J].重庆医科大学学报,2011,36(7). |
| |
| 作者姓名： | 周红标 张宇林 胡金平 |
| |
| 作者单位： | 淮阴工学院电子与电气工程学院电气教研室;兰州理工大学电信学院电子信息教研室; |
| |
| 基金项目： | 淮安市2010年度科技支撑资助项目(编号:SN1045); 淮阴工学院科研基金资助项目(编号:HGG1009) |
| |
| 摘 要： | 目的:针对正常类、非典型类和异常类3类胎心宫缩监护图(Cardiotocography,CTG),利用BP神经网络建立分类识别模型。方法:根据遗传算法(Genetic algorithm,GA)具有全局寻优的特点,引入遗传算法对神经网络权值和阈值进行优化,形成一种训练神经网络的混合算法(GA-BP算法),以克服BP算法易陷入局部最优解的缺陷,并以UCI数据库中的CTG数据集为例进行测试。结论:仿真结果表明,对于正常类、非典型类和异常类3类样本,BP算法的分类准确率分别为97.32%、71.97%和95.45%,而GA-BP算法的分类准确率分别提高到98.24%、82.67%和95.65%。可见GA-BP分类模型具有较强的学习能力和泛化能力,分类准确度更令人满意,所提出的方法是可行的。
|
| 关 键 词： | 胎心宫缩监护 BP神经网络 遗传算法 优化 |
CTG recognition based on genetic algorithm and BP neural network |
| |
| ZHOU Hong-biao,ZHANG Yu-lin,HU Jin-ping.CTG recognition based on genetic algorithm and BP neural network[J].Journal of Chongqing Medical University,2011,36(7). |
| |
| Authors: | ZHOU Hong-biao ZHANG Yu-lin HU Jin-ping |
| |
| Institution: | ZHOU Hong-biao1,ZHANG Yu-lin1,HU Jin-ping2(1.Department of Electrical,Faculty of Electronic and Electrical Engineering,Huaiyin Institute of Technology,2.Department of Electronic Information,College of Telecom,Lanzhou Technology University) |
| |
| Abstract: | Objective:To establish BP neural network(NN)classification model for normal,atypical and abnormal cardiotocography(CTG).Methods:Genetic algorithm(GA)was used to optimize the initial weights and threshold value of the neural network based on the inherent local minimum problem of NN and the good global convergence and global search ability of GA.The UCI's CTG set was used to test the algorithm.Results:The simulative results indicated that the recognition rates of the normal,atypical and abnormal CTG reached 9... |
| |
| Keywords: | cardiotocography BP neural network genetic algorithm optimization |
| 本文献已被 CNKI 等数据库收录！ |
|
