BOOST ENSEMBLE LEARNING FOR CLASSIFICATION OF CTG SIGNALS.

BOOST ENSEMBLE LEARNING FOR CLASSIFICATION OF CTG SIGNALS.
复制标题

DOI:
10.1109/icassp43922.2022.9746503
复制
发表时间:
2022-05
期刊:
Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)
影响因子:
--
通讯作者:
Djuric, Petar M.
Djuric, Petar M.
中科院分区:
其他
文献类型:
--
作者:
Ajirak, Marzieh;Heiselman, Cassandra;Quirk, J. Gerald;Djuric, Petar M.

文献摘要

参考文献

相似文献

在分娩过程中,缺氧造成的胎儿困扰会导致各种异常。心脏图(CTG)包括胎儿心率(FHR)和子宫收缩(UC)的连续记录,通常用于将胎儿分类为低氧或非催眠蛋白。实际上,我们面临高度不平衡的数据,在该数据中,缺氧胎儿的代表性不足。我们建议通过Boost Ensemble学习来解决这个问题,在此供学习中,我们在数据集上使用分类错误的分布。然后,我们根据此分布迭代选择最有用的多数数据样本。在我们的工作中,除了解决不平衡问题外,我们还尝试了妇产科不常用的功能。我们提取了胎儿心脏跟踪和子宫活动信号的大量统计特征,仅使用了最有用的统计特征。对于分类,我们实施了几种方法:随机森林,adaboost,k-nearest邻居,支持向量机和决策树。本文在公共数据库中提供了这些方法的性能上的性能进行比较。我们的结果表明,当使用Boost Ensemble时,大多数应用方法都大大提高了其性能。
During the process of childbirth, fetal distress caused by hypoxia can lead to various abnormalities. Cardiotocography (CTG), which consists of continuous recording of the fetal heart rate (FHR) and uterine contractions (UC), is routinely used for classifying the fetuses as hypoxic or non-hypoxic. In practice, we face highly imbalanced data, where the hypoxic fetuses are significantly underrepresented. We propose to address this problem by boost ensemble learning, where for learning, we use the distribution of classification error over the dataset. We then iteratively select the most informative majority data samples according to this distribution. In our work, in addition to addressing the imbalanced problem, we also experimented with features that are not commonly used in obstetrics. We extracted a large number of statistical features of fetal heart tracings and uterine activity signals and used only the most informative ones. For classification, we implemented several methods: Random Forest, AdaBoost, k-Nearest Neighbors, Support Vector Machine, and Decision Trees. The paper provides a comparison in the performance of these methods on fetal heart rate tracings available from a public database. Our results show that most applied methods improved their performances considerably when boost ensemble was used.
DOI: 10.1016/j.neucom.2018.03.067
发表时间: 2018-09-13
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Christ, Maximilian;Braun, Nils;Kempa-Liehr, Andreas W.
通讯作者: Kempa-Liehr, Andreas W.
DOI: 10.1016/j.siny.2010.09.004
发表时间: 2011-02-01
影响因子: 3
作者:
Amer-Wahlin, I.;Marsal, K.
通讯作者: Marsal, K.
DOI: 10.23919/eusipco54536.2021.9616264
发表时间: 2021-08
期刊: Proceedings of the ... European Signal Processing Conference (EUSIPCO). EUSIPCO (Conference)
影响因子: --
作者:
Yang L;Ajirak M;Heiselman C;Quirk JG;Djurić PM
通讯作者: Djurić PM
DOI: 10.1109/tkde.2014.2316504
发表时间: 2014-12-01
影响因子: 8.9
作者:
Fulcher, Ben D.;Jones, Nick S.
通讯作者: Jones, Nick S.
DOI: 10.1186/1471-2393-14-16
发表时间: 2014-01-13
影响因子: 3.1
作者:
Chudáček V;Spilka J;Burša M;Janků P;Hruban L;Huptych M;Lhotská L
通讯作者: Lhotská L