基于PSOFS和TSK模糊系统的不平衡心电数据分类算法

doi:10.11959/j.issn.2096-0271.2022039

大数据 ›› 2022, Vol. 8 ›› Issue (5): 139-152.doi: 10.11959/j.issn.2096-0271.2022039

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^,², 申情²^,³, 张雄涛¹^,²

¹ 湖州师范学院信息工程学院，浙江湖州 313000
² 浙江省现代农业资源智慧管理与应用研究重点实验室，浙江湖州 313000
³ 湖州学院理工学院，浙江湖州 313000

出版日期:2022-09-15 发布日期:2022-09-01
作者简介:李鑫辉（1997- ），男，湖州师范学院信息工程学院硕士生，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，湖州学院理工学院讲师，主要研究方向为人工智能等
张雄涛（1984- ），男，博士，湖州师范学院信息工程学院讲师，主要研究方向为模式识别和模糊系统等
基金资助:
国家自然科学基金资助项目(61771193);国家自然科学基金资助项目(61802123);浙江省教育厅一般科研项目(Y202146028)

Classification algorithm for imbalance data of ECG based on PSOFS and TSK fuzzy system

Xinhui LI¹^,², Qing SHEN²^,³, Xiongtao ZHANG¹^,²

¹ School of Information Engineering, Huzhou University, Huzhou 313000, China
² Zhejiang Province Key Laboratory of Smart Management ＆Application of Modern Agricultural Resources, Huzhou 313000, China
³ School of Science and Engineering, Huzhou College, Huzhou 313000, China

Online:2022-09-15 Published:2022-09-01
Supported by:
The National Natural Science Foundation of China(61771193);The National Natural Science Foundation of China(61802123);General Research Program of Zhejiang Educational Committee(Y202146028)

摘要/Abstract

摘要：

提出基于粒子群优化特征选择（PSOFS）算法和TSK（Takagi-Sugeno-Kang）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。首先对训练集中的各类样本进行随机放回抽样，然后将抽样得到的样本合并在一起，再独立且并行地通过PSOFS算法进行特征选择。PSOFS算法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-FNN）。模糊系统的可解释性和PSOFS算法挑选出来的特征子集能有效地帮助医学研究者找出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，能将预测结果的宏召回率提升至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:

A new classification model of electrocardiogram (ECG) signal based on particle swarm optimization feature selection (PSOFS) and TSK (Takagi-Sugeno-Kang) fuzzy system was proposed, i.e., parallel ensemble fuzzy neural network based on PSOFS and TSK (PE-PT-FN), which was used for ECG prediction.Each class sample in the training set was randomly sampled, and the samples obtained by randomly sampled were added.Then, the feature selection method PSOFS was carried out independently and parallelly.In PSOFS, particles that were random initial positions represent different feature subsets and converge to the optimal positions after many iterations.Each subset had a corresponding feature subset.Several groups of TSK fuzzy neural network (TSK-FNN) were trained by each feature subset in parallel.Medical researchers could 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

中图分类号:

TP301

李鑫辉, 申情, 张雄涛. 基于PSOFS和TSK模糊系统的不平衡心电数据分类算法[J]. 大数据, 2022, 8(5): 139-152.

Xinhui LI, Qing SHEN, Xiongtao ZHANG. Classification algorithm for imbalance data of ECG based on PSOFS and TSK fuzzy system[J]. Big Data Research, 2022, 8(5): 139-152.

图/表 8

图1

图2

图3

表1

图4

表2

图5

图6

参考文献 21

[1]	HE H B , GARCIA E A . Learning from imbalanced data[J]. IEEE Transactions on Knowledge and Data Engineering, 2009,21(9): 1263-1284.
[2]	HUANG G B , ZHU Q Y , SIEW C K . Extreme learning machine:theory and applications[J]. Neurocomputing, 2006,70(1/2/3): 489-501.
[3]	HSU C F , LIN C M , YEH R G . Supervisory adaptive dynamic RBFbased neural-fuzzy control system design for unknown nonlinear systems[J]. Applied Soft Computing, 2013,13(4): 1620-1626.
[4]	LIU H , CHEN S M . Multi-level fusion of classifiers through fuzzy ensemble learning[C]// Proceedings of 2018 11th International Symposium on Computational Intelligence and Design. Piscataway:IEEE Press, 2018: 19-22.
[5]	GU X W . Multilayer ensemble evolving fuzzy inference system[J]. IEEE Transactions on Fuzzy Systems, 2021,29(8): 2425-2431.
[6]	KORYTKOWSKI M , NOWICKI R , RUTKOWSKI L ,et al. AdaBoost ensemble of DCOG rough-neuro-fuzzy systems[C]// Proceedings of the 3rd International Conference on Computational Collective Intelligence:Technologies and Applications. Heidelberg:Springer, 2011: 62-71.
[7]	LIU H , CHEN S M . Multi-level creation of fuzzy ensembles through diversified settings of parameters[C]// Proceedings of 2019 12th International Symposium on Computational Intelligence and Design. Piscataway:IEEE Press, 2019: 185-188.
[8]	LIAW A , WIENER M . Classification and regression by randomForest[J]. R News, 2002,23(2/3): 18-22.
[9]	LESKI J M . TSK-fuzzy modeling based on ε-insensitive learning[J]. IEEE Transactions on Fuzzy Systems, 2005,13(2): 181-193.
[10]	TAKAGI T , SUGENO M . Fuzzy identification of systems and its applications to modeling and control[J]. Readings in Fuzzy Sets for Intelligent Systems, 1993,15(1): 387-403.
[11]	DENG Z H , JIANG Y Z , CHOI K S ,et al. Knowledge-leverage-based TSK fuzzy system modeling[J]. IEEE Transactions on Neural Networks and Learning Systems, 2013,24(8): 1200-1212.
[12]	SULAIMAN M A , LABADIN J . Feature selection based on mutual information[C]// Proceedings of 2015 9th International Conference on IT in Asia. Piscataway:IEEE Press, 2015: 1-6.
[13]	ZHENG L , CHAO F , PARTHALáIN N M , ,et al. Feature grouping and selection:a graph-based approach[J]. Information Sciences, 2021,546: 1256-1272.
[14]	周文桦, 刘华文, 李恩慧 . 基于特征选择的局部敏感哈希位选择算法[J]. 大数据, 2021,7(6): 67-77.
	ZHOU W H , LIU H W , LI E H . Algorithm of locality sensitive hashing bit selection based on feature selection[J]. Big Data Research, 2021,7(6): 67-77.
[15]	ZHAO J , LIN C M . Wavelet-TSK-type fuzzy cerebellar model neural network for uncertain nonlinear systems[J]. IEEE Transactions on Fuzzy Systems, 2019,27(3): 549-558.
[16]	RUBIO-SOLIS A , PANOUTSOS G . Fuzzy uncertainty assessment in RBF neural networks using neutrosophic sets for multiclass classification[C]// Proceedings of 2014 IEEE International Conference on Fuzzy Systems. Piscataway:IEEE Press, 2014: 1591-1598.
[17]	HUANG W , OH S K , PEDRYCZ W . Hybrid fuzzy wavelet neural networks architecture based on polynomial neural networks and fuzzy set/relation inference-based wavelet neurons[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018,29(8): 3452-3462.
[18]	ARSLAN H , TOZ M . Hybrid FCMWOA data clustering algorithm[C]// Proceedings of 2018 26th Signal Processing and Communications Applications Conference. Piscataway:IEEE Press, 2018: 1-4.
[19]	CATAL?O J P S , POUSINHO H M I , MENDES V M F . Hybrid wavelet-PSOANFIS approach for short-term wind power forecasting in Portugal[J]. IEEE Transactions on Sustainable Energy, 2011,2(1): 50-59.
[20]	ZHU Y J , WANG Z , GAO D Q . Gravitational fixed radius nearest neighbor for imbalanced problem[J]. Knowledge-Based Systems, 2015,90: 224-238.
[21]	GRAA O , REKIK I . Multi-view learningbased data proliferator for boosting classification using highly imbalanced classes[J]. Journal of Neuroscience Methods, 2019,327:108344.

模型	r	C	δ	penalty parameter	hidden layer
PE-PT-FN	50	60	2.3	—	—
RBF	—	—	3.5	—	—
ELM	—	—	—	—	1 000
ANFIS	—	—	—	—	—
GFRNN	—	—	—	—	—
SMOTE+SVM	—	—	1	1 000	—

模型	macro-P	macro-R	macro-F1
PE-PT-FN	0.877805
RBF	0.704845	0.685438	0.695006
ELM		0.860886	0.781939
ANFIS	0.481846	0.435967	0.45776
GFRNN	0.519663	0.852065	0.586005
SMOTE+SVM	0.848847	0.894739	0.871189

基于PSOFS和TSK模糊系统的不平衡心电数据分类算法

Classification algorithm for imbalance data of ECG based on PSOFS and TSK fuzzy system

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 21

相关文章 7

Metrics

推荐阅读 0

[1]	蔡莉, 朱扬勇. 从数据质量到数据产品质量[J]. 大数据, 2022, 8(3): 26-39.
[2]	尹传儒, 金涛, 张鹏, 王建民, 陈嘉一. 数据资产价值评估与定价：研究综述和展望[J]. 大数据, 2021, 7(4): 14-27.
[3]	赵明, 董大治. 基于区块链技术的数据资产管理机制研究[J]. 大数据, 2021, 7(4): 49-60.
[4]	臧根林, 王亚强, 吴庆蓉, 占春丽, 李熠. 智慧城市知识图谱模型与本体构建方法[J]. 大数据, 2020, 6(2): 96-106.
[5]	李望月, 刘瑾, 陈娜. 大数据技术在乡村画像中的应用研究[J]. 大数据, 2020, 6(1): 99-118.
[6]	徐优俊, 裴剑锋. 深度学习在化学信息学中的应用[J]. 大数据, 2017, 3(2): 45-66.
[7]	. 聚焦政企联动——构建大数据产业生态环境[J]. 大数据, 2016, 2(2): 108-116.