基于主动重心的青年高血压患者心肺运动时序数据增强

doi:10.11896/jsjkx.211200233

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 211200233-11.doi: 10.11896/jsjkx.211200233

基于主动重心的青年高血压患者心肺运动时序数据增强

黄昉菀^1,2, 卢举鸿¹, 於志勇^1,2

1 福州大学计算机与大数据学院福州 350116;
2 福建省网络计算与智能信息处理重点实验室福州 350116

出版日期:2023-06-10 发布日期:2023-06-12
通讯作者: 於志勇(yuzhiyong@fzu.edu.cn)
作者简介:(hfw@fzu.edu.cn)
基金资助:
国家自然科学基金(61772136);福建省中青年教育科研项目(JAT210007)

Data Augmentation for Cardiopulmonary Exercise Time Series of Young HypertensivePatients Based on Active Barycenter

HUANG Fangwan^1,2, LU Juhong¹, YU Zhiyong^1,2

1 College of Computer and Data Science,Fuzhou University,Fuzhou 350116,China;
2 Fujian Key Laboratory of Network Computing and Intelligent Information Processing,Fuzhou 350116,China

Online:2023-06-10 Published:2023-06-12
About author:HUANG Fangwan,born in 1980,Ph.D,senior lecturer,is a member of China Computer Federation.Her main research interests include computational intelligence,machine learning and big data analysis. YU Zhiyong,born in 1982,Ph.D,professor,is a member of China Computer Federation.His main research interests include pervasive computing,mobile social networks,and crowd sensing.
Supported by:
National Natural Science Foundation of China(61772136) and Fujian Province Young and Middle-aged Teachers Education Research Project(JAT210007).

摘要/Abstract

摘要： 精准医疗的逐步兴起,如挖掘青年高血压患者的心肺运动时序数据,可以了解不同个体对有氧运动训练的响应性,有助于提高患者高血压管理计划的制定效率,更有效地实现有氧运动干预的治疗。开展该研究的瓶颈之一在于难以获取充足的样本数据。为了解决获取数据难度大、成本高等问题,利用加权动态时间规整重心平均算法来进行时间序列数据增强,重点针对重心选择和权重分配进行了研究。针对重心选择问题,首次引入了主动重心的概念,提出了代表性重心与多样性重心选择策略,改善了数据增强的效果。此外,针对现有权重分配策略的不足,提出了随机权重距离递减分配策略,避免了合成重复样本,进一步提升了模型的泛化能力。实验结果表明,在该研究背景下同时考虑重心选择与权重分配进行数据增强,可以进一步提升青年高血压患者有氧运动干预疗效预测的准确性。

关键词: 高血压, 心肺运动实验, 时序数据增强, 动态时间规整重心平均, 重心选择策略, 权重分配策略

Abstract: The gradual rise of precision medicine,such as mining cardiopulmonary exercise time series of young hypertensive patients,can understand the response of different individuals to aerobic exercise training.This helps to improve the efficiency of hypertension management plan and achieve aerobic exercise intervention more effectively.One of the bottlenecks in this study is that it is difficult to obtain sufficient sample data.To solve the above problem,this paper adopts the weighted dynamic-time-warping barycenter averaging algorithm(WDBA) to realize data augmentation of time series,focusing on the barycenter selection and the weight assignment.In this paper,the concept of active barycenter is introduced for the first time,and the selection strategies of representative barycenter and diversity barycenter are proposed to improve the effect of data augmentation.Furthermore,aiming at the shortcomings of the existing weight assignment strategies,a random strategy with decreasing distance is proposed to further improve the generalization ability of the model by avoiding the synthesis of duplicate samples.Experimental results show that the accuracy of predicting the efficacy of aerobic exercise intervention in young hypertensive patients can be further improved by considering both the barycenter selection and the weight assignment for data augmentation in the background of this study.

Key words: Hypertension, Cardiopulmonary exercise test, Time series data augmentation, Dynamic-time-warping barycenter ave-raging, Barycenter selection strategy, Weight assignment strategy

中图分类号:

TP391

黄昉菀, 卢举鸿, 於志勇. 基于主动重心的青年高血压患者心肺运动时序数据增强[J]. 计算机科学, 2023, 50(6A): 211200233-11. https://doi.org/10.11896/jsjkx.211200233

HUANG Fangwan, LU Juhong, YU Zhiyong. Data Augmentation for Cardiopulmonary Exercise Time Series of Young HypertensivePatients Based on Active Barycenter[J]. Computer Science, 2023, 50(6A): 211200233-11. https://doi.org/10.11896/jsjkx.211200233

参考文献

[1]YANO Y,REIS J P,COLANGELO L A,et al.Association of blood pressure classification in young adults using the 2017 American College of Cardiology/American Heart Association blood pressure guideline with cardiovascular events later in life[J].Jama,2018,320(17):1774-1782.
[2]WU S,SONG Y,CHEN S,et al.Blood pressure classification of 2017 associated with cardiovascular disease and mortality in young Chinese adults[J].Hypertension,2020,76(1):251-258.
[3]BROOK R D,APPEL L J,RUBENFIRE M,et al.Beyond medications and diet:alternative approaches to lowering blood pressure:a scientific statement from the American Heart Association[J].Hypertension,2013,61(6):1360-1383.
[4]WEN H,WANG L.Reducing effect of aerobic exercise on blood pressure of essential hypertensive patients:A meta-analysis[J].Medicine,2017,96(11)e6150.
[5]CAO L,LI X,YAN P,et al.The effectiveness of aerobic exercise for hypertensive population:a systematic review and meta-analysis[J].The Journal of Clinical Hypertension,2019,21(7):868-876.
[6]PEDRALLI M L,EIBEL B,WACLAWOVSKY G,et al.Effects of exercise training on endothelial function in individuals with hypertension:a systematic review with meta-analysis[J].Journal of the American Society of Hypertension,2018,12(12):e65-e75.
[7]GOROSTEGI-ANDUAGA I,CORRES P,MARTINEZAGU-IRRE-BETOLAZA A,et al.Effects of different aerobic exercise programmes with nutritional intervention in sedentary adults with overweight/obesity and hypertension:EXERDIET-HTA study[J].European Journal of Preventive Cardiology,2018,25(4):343-353.
[8]PEDERSEN B K,SALTIN B.Exercise as medicine-evidence for prescribing exercise as therapy in 26 different chronic diseases[J].Scandinavian Journal of Medicine & Science in Sports,2015,25:1-72.
[9]LOPES S,MESQUITA-BASTOS J,ALVES A J,et al.Exercise as a tool for hypertension and resistant hypertension management:current insights[J].Integrated Blood Pressure Control,2018,11:65-71.
[10]HACKE C,NUNAN D,WEISSER B.Do exercise trials for hy-pertension adequately report interventions? A reporting quality study[J].International Journal of Sports Medicine,2018,39(12):902-908.
[11]OZEMEK C,ARENA R.Precision in promoting physical activity and exercise with the overarching goal of moving more[J].Progress in Cardiovascular Diseases,2019,62(1):3-8.
[12]ROSS R,GOODPASTER B H,KOCH L G,et al.Precision exercise medicine:understanding exercise response variability[J].British journal of sports medicine,2019,53(18):1141-1153.
[13]YANG G,LENG X,HUANG F,et al.Use CPET data to predict the intervention effect of aerobic exercise on young hypertensive patients[C]//2019 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).IEEE,2019:1699-1702.
[14]ALBOUAINI K,EGRED M,ALAHMAR A,et al.Cardiopulmonary exercise testing and its application[J].Postgraduate medical journal,2007,83(985):675-682.
[15]BALADY G J,ARENA R,SIETSEMA K,et al.Clinician’sguide to cardiopulmonary exercise testing in adults:a scientific statement from the American Heart Association[J].Circulation,2010,122(2):191-225.
[16]YOUN J C,KANG S M.Cardiopulmonary exercise test in patients with hypertension:focused on hypertensive response to exercise[J].Pulse,2015,3(2):114-117.
[17]HUANG F,LENG X,KASUKURTHI M V,et al.UtilizingMachine Learning Techniques to Predict the Efficacy of Aerobic Exercise Intervention on Young Hypertensive Patients Based on Cardiopulmonary Exercise Testing[J].Journal of Healthcare Engineering,2021(1):6633832.
[18]SHORTEN C,KHOSHGOFTAAR T M.A survey on image data augmentation for deep learning[J].Journal of Big Data,2019,6(1):1-48.
[19]LE GUENNEC A,MALINOWSKI S,TAVENARD R.Dataaugmentation for time series classification using convolutional neural networks[C]//ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data.2016.
[20]WEN Q,GAO J,SONG X,et al.RobustSTL:A robust seasonal-trend decomposition algorithm for long time series[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:5409-5416.
[21]BERGMEIR C,HYNDMAN R J,BENITEZ J M.Bagging exponential smoothing methods using STL decomposition and Box-Cox transformation[J].International Journal of Forecasting,2016,32(2):303-312.
[22]KEGEL L,HAHMANN M,LEHNER W.Feature-based comparison and generation of time series[C]//Proceedings of the 30th International Conference on Scientific and Statistical Database Management.2018:1-12.
[23]GAO J,SONG X,WEN Q,et al.RobustTAD:Robust time series anomaly detection via decomposition and convolutional neural networks[J].arXiv:2002.09545,2020.
[24]WEN Q,SUN L,YANG F,et al.Time series data augmentation for deep learning:A survey[J].arXiv:2002.12478,2020.
[25]ESTEBAN C,HYLAND S L,RÄTSCH G.Real-valued(medical) time series generation with recurrent conditional gans[J].arXiv:1706.02633,2017.
[26]YOON J,JARRETT D,VAN DER SCHAAR M.Time-series generative adversarial networks[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems.2019:5508-5518.
[27]BAGNALL A,LINES J,BOSTROM A,et al.The great time series classification bake off:a review and experimental evaluation of recent algorithmic advances[J].Data Mining and Knowledge Discovery,2017,31(3):606-660.
[28]PETITJEAN F,FORESTIER G,WEBB G I,et al.Faster and more accurate classification of time series by exploiting a novel dynamic time warping averaging algorithm[J].Knowledge and Information Systems,2016,47(1):1-26.
[29]FORESTIER G,PETITJEAN F,DAU H A,et al.Generatingsynthetic time series to augment sparse datasets[C]//2017 IEEE International Conference on Data Mining(ICDM).IEEE,2017:865-870.
[30]PETITJEAN F,KETTERLIN A,GANÇARSKI P.A globalaveraging method for dynamic time warping,with applications to clustering[J].Pattern Recognition,2011,44(3):678-693.
[31]PETITJEAN F,GANÇARSKI P.Summarizing a set of time series by averaging:From Steiner sequence to compact multiple alignment[J].Theoretical Computer Science,2012,414(1):76-91.
[32]GILYAZEV R A,TURDAKOV D Y.Active learning and crow-dsourcing:A survey of optimization methods for data labeling[J].Programming and Computer Software,2018,44(6):476-491.
[33]VAN DER MAATEN L,HINTON G.Visualizing data using t-SNE[J].Journal of machine learning research,2008,9(11):2579-2605.
[34]DAU H A,BAGNALL A,KAMGAR K,et al.The UCR time series archive[J].IEEE/CAA Journal of Automatica Sinica,2019,6(6):1293-1305.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于主动重心的青年高血压患者心肺运动时序数据增强

Data Augmentation for Cardiopulmonary Exercise Time Series of Young HypertensivePatients Based on Active Barycenter

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0