首页> 外文期刊>Journal of Scientific & Industrial Research >Incapable of identifying suspicious records in CTG data using ANN based machine learning techniques
【24h】

Incapable of identifying suspicious records in CTG data using ANN based machine learning techniques

机译:使用基于ANN的机器学习技术无法识别CTG数据中的可疑记录

获取原文
获取原文并翻译 | 示例
       

摘要

Cardiotocography (CTG) is a simultaneous recording of fetal heart rate (FHR) and uterine contractions (UC). It is one of the most common diagnostic techniques to evaluate maternal and fetal well-being during pregnancy and before delivery. By observing the Cardiotocography trace patterns doctors can understand the state of the fetus. We implement a model based CTG data classification system using a supervised artificial neural network (ANN) and support vector machine (SVM) which can classify the CTG data based on its training data. The performance neural network based classification model has been compared with the most commonly used unsupervised clustering methods Fuzzy C-mean and k-mean clustering and supervised clustering method SVM classification. According to the arrived results, the performance of the supervised machine learning based classification (ANN) approach provided significant performance than other compared unsupervised clustering methods and supervised SVM classification method. We used Precision, Recall, F-Measure and Rand Index as the metric to evaluate the performance. Even though the traditional clustering methods can identify the Normal CTG patterns, they were incapable of finding Suspicious and Pathologic patterns and the SVM based classifier provided good performance, it was absolutely incapable of identifying a single suspicious record. It was found that, the ANN based classifier was capable of identifying Normal, Suspicious and Pathologic condition, from the nature of CTG data with very good accuracy. The important finding in this paper is Even though SVM is a well proven technique for classification, it was incapable of identifying Suspicious Records in Cardiotocogram Data - but ANN did considerably good classification of Suspicious Records.
机译:心动描记法(CTG)是同时记录胎儿心率(FHR)和子宫收缩(UC)的信息。它是评估怀孕期间和分娩前母婴健康状况的最常见诊断技术之一。通过观察心动描记线的痕迹,医生可以了解胎儿的状态。我们使用监督人工神经网络(ANN)和支持向量机(SVM)实现了基于模型的CTG数据分类系统,该系统可以根据其训练数据对CTG数据进行分类。将基于性能神经网络的分类模型与最常用的无监督聚类方法模糊C均值和k均值聚类以及监督聚类方法SVM分类进行了比较。根据得出的结果,基于监督机器学习的分类(ANN)方法的性能提供了比其他比较的非监督聚类方法和监督SVM分类方法显着的性能。我们使用Precision,Recall,F-Measure和Rand Index作为评估性能的指标。尽管传统的聚类方法可以识别正常的CTG模式,但它们无法找到可疑和病理模式,并且基于SVM的分类器提供了良好的性能,但绝对无法识别单个可疑记录。结果发现,基于ANN的分类器能够从CTG数据的性质中非常准确地识别正常,可疑和病理状态。本文的重要发现是,即使SVM是一种行之有效的分类技术,也无法识别心电图数据中的可疑记录-但是ANN对可疑记录进行了很好的分类。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号