基于自适应噪声完整聚合经验模态分解-极限学习机的短期血糖预测

doi:10.3969/j.issn.0258-8021.2017.06.010

Abstract
Figure/Table
References
Related Citation (5)

Download: PDF (1189 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract A short-term prediction model of blood glucose based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and extreme learning machine (ELM) was proposed to improve the forecasting accuracy of blood glucose, which is timing-varying, nonlinear and non-stationary in diabetics. Firstly, by means of CEEMDAN, time sequence of blood glucose was decomposed into several intrinsic mode function (IMF) with different frequencies and a residual to reduce the non-stationary. Next, ELMs were built for each IMF and residual component to improve the forecasting accuracy, and the all forecasts of ELMs were fused to produce the prediction of blood glucose. Finally, an early alarm algorithm of hypoglycemia was proposed based on the short-term prediction model. The model was verified by 56 cases of diabetic in Department of Endocrinology of Henan Province People's Hospital. The experimental results showed that comparing to ELM model and EMD-ELM model, the proposed prediction model of blood glucose based on CEEMDAN-ELM could achieve 45 min prediction in advance, the RMSE was 0.2051 and the MAPE was 2.1164%. The false alarm rate and missing alarm rate of early alarm algorithm of hypoglycemia were 0.97% and 7.55% respectively. The 45 min prediction ahead provided sufficient time for doctors and diabetics to control the blood glucose concentration, especially for diabetics with hypoglycemia.

Key words： glucose prediction hypoglycemia alarm CEEMDAN extreme learning machine

Received: 25 October 2016

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Wang Yannian
	Guo Zhanli
	Yuan Jinlei
	Li Quanzhong

Cite this article:

Wang Yannian,Guo Zhanli,Yuan Jinlei, et al. Short-term Prediction of Blood Glucose Based on CEEMDAN and ELM[J]. Chinese Journal of Biomedical Engineering, 2017, 36(6): 702-710.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2017.06.010 OR http://cjbme.csbme.org/EN/Y2017/V36/I6/702

[1] 李鹏.人工胰脏中血糖预测模型的关键问题研究[D]. 长春:中国科学院大学, 2015.
[2] Ceriello A, Novials A, Ortega E, et al. Evidence that hyperglycemia after recovery from hypoglycemia worsens endothelial function and increases oxidative stress and inflammation in healthy control subjects and subjects with type 1 diabetes[J]. Diabetes, 2012, 61(11): 2993-2997.
[3] 陈松景,罗森林,潘丽敏等.2型糖尿病患病因素对血糖影响的定量分析[J].北京理工大学学报, 2014, 34(2):201-206.
[4] Wang YN, Wei FF, Sun CQ, et al. The research of improved grey GM (1, 1) model to predict the postprandial glucose in type 2 diabetes [J]. Bio Med Research International, 2016, 2016(4): 1-6.
[5] Mo X, Wang YQ, Wu XW. Hypoglycemia prediction using extreme learning machine (ELM) and regularized ELM [C] //25th Chinese Control and Decision Conference (CCDC). Guiyang: IEEE, 2013:4405-4409.
[6] 王延年, 申艳蕊, 张旭,等.自适应血糖预测模型在低血糖预警中的应用[J].中国卫生统计, 2014, 6, 31(3):421-424.
[7] Georga EI, Protopappas VC, Polyzos D, et al. Evaluation of short-term predictors of glucose concentration in type 1 diabetes combining feature ranking with regression models.[J] Med Biol Eng Comput, 2015,53(12): 1305-1318.
[8] Georga EI, Vasilios CP, Diego A, et al. Multivariate prediction of subcutaneous glucose concentration in type 1 diabetes patients based on support vector regression [J]. Journal of Biomedical and Health Informatics, 2013, 17:71-81.
[9] Chiara Z, Andrea F, Giovanni S, et al. Neural network incorporating meal information improves accuracy of short-time prediction of glucose concentration [J]. IEEE Transactions on Biomedical Engineering, 2012, 59: 1550-1560.
[10] Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society A-Mathematical Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[11] 谢平, 陈晓玲, 苏玉萍,等. 基于EMD-多尺度熵和ELM的运动想象脑电特征提取和模式识别[J]. 中国生物医学工程学报, 2013, 32:641-648.
[12] 庞春颖,王小甜,孙晓琳. 一种基于改进经验模态分解的癫痫脑电识别新方法[J]. 中国生物医学工程学报, 2013, 32:663-669.
[13] Wu ZH, Huang NE. Ensemble empirical mode decomposition: A noise-assisted data analysis method [J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
[14] Yeh JR, Shieh JS, Huang NE, Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method[J]. Advances in Adaptive Data Analysis, 2010,02:1000042.
[15] Torres ME, Colominas MA, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C] // 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Prague:IEEE, 2011: 4144-4147.
[16] Huang GB, Zhu QY, Siew CK. Extreme learning machine: Theory and applications [J]. Neurocomputing, 2006, 70(1/2/3):489-501.
[17] 李军, 李大超.基于CEEMDAN-FE-KELM 方法的短期风电功率预测[J]. 信息与控制, 2016, 45(2): 135-141.
[18] Ståhl F, Johansson R, Olsson ML. Predicting nocturnal hypoglycemia using a non-parametric insulin action model [C] //IEEE International Conference on Systems. Kowloon: IEEE, 2015: 1583-1588.
[19] Dassau E, Cameron F, Bequette BW, et al. Real-time hypoglycemia prediction suite using continuous glucosemonitoring [J]. Diabetes Care, 2010, 33: 1249-1254.
[20] Clarke WL,Cox D,Gonder-Frederick LA,et al. Evaluating clinical accuracy of systems for self-monitoring of blood glucose [J]. Diabetes Care, 1987, (5):622-628.