大数据

• •    

基于PSOFS和TSK模糊系统的不平衡心电数据分类算法

李鑫辉1,3 申情2,3 张雄涛1,3   

  1. 1湖州师范学院信息工程学院,湖州313000
    2湖州学院理工学院,湖州313000
    3浙江省现代农业资源智慧管理与应用研究重点实验室,湖州313000
  • 作者简介:李鑫辉(1997-),男,硕士研究生,湖州师范学院学生,主要研究方向为智能信息处理和模糊系统等。 申情(1982-),女,博士,湖州师范学院讲师,主要研究方向为人工智能等。 张雄涛(1984-),男,博士,湖州师范学院讲师,主要研究方向为模式识别和模糊系统等。

Classification Algorithm for Imbalance Data of ECG Based on PSOFS and TSK Fuzzy System

LI Xinhui1,3, SHEN Qing2,3 and ZHANG Xiongtao1,3   

  1. School of Information Engineering, Huzhou University, Huzhou, 313000, China
    School of Science and Engineering, Huzhou College, Huzhou, 313000, China Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou, 313000, China

摘要: 心梗和心律不齐是危害我国人民身体健康的疾病,心电图是最重要的监测措施。对于医学研究者而言,预测模型可以作为预测的工具,预测过程中产生的多组特征子集可以用作评估不同特征重要程度的研究数据。本文提出基于粒子群优化特征选择算法(Particle Swarm Optimization Feature Selection,PSOFS) 和Takagi-Sugeno-Kang(TSK)模糊系统的心电信号分类模型,即基于PSOFS和TSK的并行集成模糊神经网络(PE-PT-FN),用于心电图预测。首先对训练集中各类样本都进行随机放回抽样,然后将抽样得到的样本并在一起,再独立并行的通过PSOFS算法进行特征选择。PSOFS中不同的位置表示不同的特征子集,初始位置随机的粒子经过多次迭代收敛至最佳位置。每个子集得到一个特征子集用于并行训练多组独立的小型TSK模糊神经网络 (TSK-FN)。模糊系统的可解释性和PSOFS挑选出来的特征子集能有效地帮助医学研究者找出心电图心电信号数据与不同类型病例之间的关联。实验证明PE-PT-FN在保留可解释性的前提下,能提升预测结果的宏查全率至92.35%。

关键词: TSK模糊神经网络, 粒子群优化特征选择, 集成学习, 心电信号分类, 不平衡数据

Abstract: Myocardial infarction and arrhythmia are endangered diseases in China, and electrocardiogram (ECG) is the most important monitoring measure. For medical researchers, predictive models can be used as predictive tools, and the multiple feature subsets generated during the prediction process can be used as research data to assess the importance of different features. A new classification model of ECG signal based on Particle Swarm Optimization Feature Selection (PSOFS) and Takagi-Sugeno-Kang (TSK) fuzzy system is proposed, i.e., parallel ensemble fuzzy neural network based on PSOFS and TSK (PE-PT-FN), is used for ECG prediction. Each class samples in the training set are randomly sampled, and the samples obtained by randomly sampled are added. Then, the feature selection method PSOFS is carried out independently and parallelly. In PSOFS, particles which are random initial positions represent different feature subsets and converge to the optimal positions after many iterations. Each subset has a corresponding feature subset. Several groups of TSK fuzzy neural networks (TSK-FN) are trained by each feature subset in parallel. Medical researchers can effectively find the correlation between ECG signal data and different types of disease through the interpretability of the fuzzy system and the feature subsets by the PSOFS algorithm. Experiments prove that PE-PT-FN greatly improves the macro-R to 92.35% while retaining interpretability.

Key words: TSK fuzzy neural network, Particle swarm optimization feature selection, Ensemble learning, classification of ECG signal, Imbalance data

No Suggested Reading articles found!