摘要
为了提高眼科疾病诊断的精度,将Multi-agent和分布式思想引入支持向量机(SVM),提出一种基于云计算MapReduce框架的SVM眼科疾病诊断模型。通过眼底图像分割提取计算神经视网膜边缘比率(NRR)、杯盘比(CDR)和视网膜血管比率(BVR)三个临床特征参数;这三个临床特征参数作为SVM的输入向量,眼科疾病类型作为SVM的输出向量,建立基于云计算MapReduce框架的SVM眼科疾病诊断模型。研究结果表明,与KNN、NBayes、BPNN、RBFNN和LDA相比,所提出的方法MR-SVM不但可以提高眼科疾病诊断的精度,而且能够降低计算资源的消耗,缩短训练时间,具有很好的并行性能。
In order to improve the accuracy of ophthalmic disease diagnosis,multi-agent and distributed ideas are introduced into support vector machine(SVM),and an SVM model for ophthalmic disease diagnosis based on cloud computing MapReduce framework is proposed.Three clinical characteristic parameters,namely neuroretinal margin ratio(NRR),cupping to plate ratio(CDR)and retinal vessel ratio(BVR),are extracted and calculated by fundus image segmentation.The three clinical characteristic parameters are used as the input of SVM,and types of ophthalmic disease are used as the output vector of SVM.An SVM ophthalmic disease diagnosis model based on cloud computing MapReduce framework is established.The results show that,compared with KNN,NBayes,BPNN,RBFNN and LDA,MR-SVM proposed in this paper can not only improve the accuracy of ophthalmic disease diagnosis,but also reduce the consumption of computing resources,shorten the training time and have good parallel performance.
作者
顾小霞
GU Xiaoxia(Haian City People’s Hospital,Hai’an 226600,China)
出处
《微型电脑应用》
2023年第4期131-134,共4页
Microcomputer Applications
关键词
眼科疾病
临床特征参数
云计算
支持向量机
人工神经网络
ophthalmic disease
clinical characteristic parameter
cloud computing
support vector machine
artificial neural network
