一种基于降噪自动编码器和宽度学习的增量式疾病预测模型

漆华妹; 胡宇轩; 袁正一

doi:10.12263/DZXB.20211320

您当前的位置：

首页 >

文章列表页 >

一种基于降噪自动编码器和宽度学习的增量式疾病预测模型

学术论文 | 更新时间：2025-12-08

- 一种基于降噪自动编码器和宽度学习的增量式疾病预测模型
- An Incremental Disease Prediction Model Based on Denoising Autoencoder with Broad Learning System
- 电子学报 2023年51卷第6期页码：1474-1485
- 作者机构：
  
  中南大学计算机学院，湖南长沙 410075
- 作者简介：
  
  [ "漆华妹女，1978年出生，江西南昌人.中南大学计算机学院副教授，硕士生导师.主要研究方向为机器学习、边缘计算、云计算、物联网、5G通信等.E-mail: qhm@csu.edu.cn" ]
  [ "胡宇轩男，1999年出生，湖南娄底人.中南大学计算机学院硕士研究生.主要研究方向为机器学习与智慧医疗.E-mail: 204712249@csu.edu.cn" ]
  [ "袁正一男，2001年出生，江西南昌人.中南大学计算机学院本科生.主要研究方向为机器学习与智能算法.E-mail: 2250100280@qq.com" ]
- 基金信息：
- DOI：10.12263/DZXB.20211320
  中图分类号： TP183;
- 收稿：2021-09-23，
  
  修回：2022-05-30，
  
  纸质出版：2023-06-25
- 稿件说明：
移动端阅览
漆华妹,胡宇轩,袁正一.一种基于降噪自动编码器和宽度学习的增量式疾病预测模型[J].电子学报,2023,51(06):1474-1485.

QI Hua-mei,HU Yu-xuan,YUAN Zheng-yi.An Incremental Disease Prediction Model Based on Denoising Autoencoder with Broad Learning System[J].ACTA ELECTRONICA SINICA,2023,51(06):1474-1485.
漆华妹,胡宇轩,袁正一.一种基于降噪自动编码器和宽度学习的增量式疾病预测模型[J].电子学报,2023,51(06):1474-1485. DOI： 10.12263/DZXB.20211320.

QI Hua-mei,HU Yu-xuan,YUAN Zheng-yi.An Incremental Disease Prediction Model Based on Denoising Autoencoder with Broad Learning System[J].ACTA ELECTRONICA SINICA,2023,51(06):1474-1485. DOI： 10.12263/DZXB.20211320.

摘要

疾病预测模型通过利用收集到的医疗数据，能够在患者疾病发作前准确地进行疾病预测.目前在疾病预测方面深受欢迎的深度神经网络，它依靠增加网络层数来提升模型的准确率，利用梯度下降来进行权重的更新，而这导致了模型梯度爆炸、训练速度慢等问题.一旦数据更新，深度神经网络需要重新训练，进而导致模型更新困难.宽度学习（Broad Learning System，BLS）无须梯度下降的特性与其可通过增量学习快速重构的优势为有效解决上述问题提供了技术方案，但是BLS无法提取到隐藏在医疗数据中深层次的特征，其在复杂的医疗环境下仍然表现不佳.针对该问题，本文提出一种基于降噪自动编码器（Denoising AutoEncoder，DAE）与宽度学习的增量式疾病预测模型——DAE-BLS.所提模型将DAE引入BLS的架构设计中，结合了DAE在混乱环境下的降噪能力与BLS的简洁快速的特点，既保证了高效的运算能力又增强了特征提取能力，因而更适用于复杂医疗环境.将DAE-BLS在包含不同格式以及不同数据量的糖尿病、心力衰竭、心电异常和乳腺癌数据集上进行模拟预测实验，实验结果表明，DAE-BLS能够在保留宽度结构的神经网络快速高效特点的同时，在不同格式的数据上表现出很好的性能，分别达到96.62%，94.53%，98.50%与83.64%的准确率，并能在需要更改模型结构时通过增量学习技术快速重构以适应用户不断变化的疾病数据.

Abstract

Disease prediction models use collected medical data to accurately predict a patient's disease before its onset. At present

deep neural network

which is popular in disease prediction

relies on increasing the number of network layers to improve the accuracy of the model

and uses gradient descent to update the weight

which leads to problems such as model gradient explosion and slow training speed. At the same time

once the data is updated

the deep neural network needs to be retrained

which makes it difficult to update the model. Broad learning system (BLS)

which does not need gradient descent and has the advantage of rapid reconstruction through incremental Learning

provides a technical solution to solve the above problems effectively. However

BLS cannot extract the deep features hidden in medical data

and still performs poor in complex medical environment. To solve this problem

we propose an incremental disease prediction model based on denoising autoencoder (DAE) and BLS

called DAE-BLS. In the proposed model

DAE is introduced into the architecture design of BLS. The model combines the denoising ability of DAE in chaotic environment with the simplicity and speed of BLS

which not only ensures the efficient computing capability of the model but also enhances the feature extraction capability of the model

making it more suitable for complex medical environment. Applying DAE-BLS to prediction experiments on diabetes

heart failure

ECG abnormalities and breast cancer datasets with different formats and data volumes

experimental results show that DAE-BLS can retain the fast and efficient characteristics of BLS

and show good performance in different data formats

reaching 96.62%

94.53%

98.50% and 83.64% accuracy respectively

and can be rapidly reconstructed to adapt to users' changing disease data through incremental learning techniques when the model structure needs to be changed.

关键词

Keywords

references

李静 , 吴美玲 . 中国城乡人口老龄化发展质量: 差异和预测 [J]. 宏观质量研究 , 2020 , 8 ( 5 ): 1 - 13 .

LI J , WU M L . The quality of the urban and rural population aging in China: Differences and forecasts [J]. Journal of Macro-Quality Research , 2020 , 8 ( 5 ): 1 - 13 . (in Chinese)

DIMITROV D V . Medical Internet of Things and big data in healthcare [J]. Healthcare Informatics Research , 2016 , 22 ( 3 ): 156 - 163 .

LI W , CHAI Y B , KHAN F , et al . A comprehensive survey on machine learning-based big data analytics for IoT-enabled smart healthcare system [J]. Mobile Networks and Applications , 2021 , 26 ( 1 ): 234 - 252 .

张学军 , 景鹏 , 何涛 , 等 . 基于变分模态分解的癫痫脑电信号分类方法 [J]. 电子学报 , 2020 , 48 ( 12 ): 2469 - 2475 .

ZHANG X J , JING P , HE T , et al . An epileptic electroencephalogram signal classification method based on variational mode decomposition [J]. Acta Electronica Sinica , 2020 , 48 ( 12 ): 2469 - 2475 . (in Chinese)

成娟 , 陈勋 , 彭虎 . 基于样本熵的肌电信号起始点检测研究 [J]. 电子学报 , 2016 , 44 ( 2 ): 479 - 484 .

CHENG J , CHEN X , PENG H . An onset detection method for action surface electromyography based on sample entropy [J]. Acta Electronica Sinica , 2016 , 44 ( 2 ): 479 - 484 . (in Chinese)

李婧 , 张红 , 薛万刚 , 等 . 医院与社区协同的远程心电诊断服务模式设计与实现 [J]. 中国数字医学 , 2020 , 15 ( 1 ): 47 - 49 .

LI J , ZHANG H , XUE W G , et al . Design and implementation of remote ECG diagnosis service model based on cooperation between hospital and communities [J]. China Digital Medicine , 2020 , 15 ( 1 ): 47 - 49 . (in Chinese)

POPLIN R , VARADARAJAN A V , BLUMER K , et al . Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning [J]. Nature Biomedical Engineering , 2018 , 2 ( 3 ): 158 - 164 .

RAJENDRA ACHARYA U , FUJITA H , OH S L , et al . Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals [J]. Information Sciences , 2017 , 415/416 : 190 - 198 .

TULI S , BASUMATARY N , GILL S S , et al . HealthFog: An ensemble deep learning based Smart Healthcare System for Automatic Diagnosis of Heart Diseases in integrated IoT and fog computing environments [J]. Future Generation Computer Systems , 2020 , 104 : 187 - 200 .

XIAN Y Q , HU H F . Enhanced multi-dataset transfer learning method for unsupervised person re-identification using co-training strategy [J]. IET Computer Vision , 2018 , 12 ( 8 ): 1219 - 1227 .

CHEN C L P , LIU Z L . Broad learning system: An effective and efficient incremental learning system without the need for deep architecture [J]. IEEE Transactions on Neural Networks and Learning Systems , 2018 , 29 ( 1 ): 10 - 24 .

赵慧敏 , 郑建杰 , 郭晨 , 等 . 基于流形正则化框架和MMD的域自适应BLS模型 [J/OL]. 自动化学报 , ( 2021-06-28 )[ 2021-07-23 ]. http://www.aas.net.cn/article/doi/10.16383/j.aas.c210009 http://www.aas.net.cn/article/doi/10.16383/j.aas.c210009 .

ZHAO H M , HENG J J , GUO C , et al . Domain adaptive BLS model based on manifold regularization framework and MMD [J/OL]. Acta Automatica Sinica , ( 2021-06-28 )[ 2021-07-23 ]. http://www.aas.net.cn/article/doi/10.16383/j.aas.c210009. http://www.aas.net.cn/article/doi/10.16383/j.aas.c210009. (in Chinese)

XU M L , HAN M , CHEN C L P , et al . Recurrent broad learning systems for time series prediction [J]. IEEE Transactions on Cybernetics , 2020 , 50 ( 4 ): 1405 - 1417 .

BELOUADAH E , POPESCU A , KANELLOS I . A comprehensive study of class incremental learning algorithms for visual tasks [J]. Neural Networks , 2021 , 135 : 38 - 54 .

LEE J , SUN S , YANG S M , et al . Bidirectional recurrent auto-encoder for photoplethysmogram denoising [J]. IEEE Journal of Biomedical and Health Informatics , 2019 , 23 ( 6 ): 2375 - 2385 .

VINCENT P , LAROCHELLE H , BENGIO Y , et al . Extracting and composing robust features with denoising autoencoders [C]// Proceedings of the 25th International Conference on Machine Learning . Helsinki : ACM , 2008 : 1096 - 1103 .

RUMELHART D E , HINTON G E , WILLIAMS R J . Learning representations by back-propagating errors [J]. Nature , 1986 , 323 ( 6088 ): 533 - 536 .

BOURLARD H , KAMP Y . Auto-association by multilayer perceptrons and singular value decomposition [J]. Biological Cybernetics , 1988 , 59 ( 4 ): 291 - 294 .

IJJINA E P , KRISHNA M C . Classification of human actions using pose-based features and stacked auto encoder [J]. Pattern Recognition Letters , 2016 , 83 ( 3 ): 268 - 277 .

TIAN S W , YAN Y L , YU L , et al . Prediction of anti-HIV activity on the basis of stacked auto-encoder [J]. Journal of Chemometrics , 2017 , 31 ( 10 ): 2970 - 2987 .

WANG L , WANG Z W , ZHAO G Y , et al . Automatic voice quality evaluation method of IVR service in call center based on Stacked Auto Encoder [J]. IOP Conference Series: Earth and Environmental Science , 2021 , 827 ( 1 ): 012021 .

MASCI J , MEIER U , CIREŞAN D , et al . Stacked convolutional auto-encoders for hierarchical feature extraction [C]// Artificial Neural Networks and Machine Learning . Berlin : Springer , 2011 : 52 - 59 .

LIU J S , ZHANG Z , RAZAVIAN N . Deep EHR: Chronic disease prediction using medical notes [EB/OL]. ( 2018 )[2021]. https://arxiv.org/abs/1808.04928 https://arxiv.org/abs/1808.04928 .

JIN M Q , BAHADORI M T , COLAK A , et al . Improving hospital mortality prediction with medical named entities and multimodal learning [EB/OL]. ( 2018 )[2021]. https://arxiv.org/abs/1811.12276 https://arxiv.org/abs/1811.12276 .

LIANG Z , ZHANG G , HUANG J X , et al . Deep learning for healthcare decision making with EMRs [C]// 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) . Belfast : IEEE , 2015 : 556 - 559 .

HANNUN A Y , RAJPURKAR P , HAGHPANAHI M , et al . Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network [J]. Nature Medicine , 2019 , 25 ( 1 ): 65 - 69 .

CHEN C L P , LIU Z L . Broad learning system: A new learning paradigm and system without going deep [C]// 2017 32nd Youth Academic Annual Conference of Chinese Association of Automation (YAC) . Hefei : IEEE , 2017 : 1271 - 1276 .

BEN-ISRAEL A , GREVILLE T N E . Generalized Inverses: Theory and Applications [M]. 2nd ed . New York : Springer , 2003 .

LIU Z L , ZHOU J , CHEN C L P . Broad learning system: Feature extraction based on K-means clustering algorithm [C]// 2017 4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS) . Dalian : IEEE , 2017 : 683 - 687 .

JIN J W , PHILIP CHEN C L . Regularized robust Broad Learning System for uncertain data modeling [J]. Neurocomputing , 2018 , 322 : 58 - 69 .

ZHOU Q M , HE X P . Broad learning model based on enhanced features learning [J]. IEEE Access , 2019 , 7 : 42536 - 42550 .

LIN J T . Three-domain fuzzy wavelet broad learning system for tremor estimation [J]. Knowledge-Based Systems , 2020 , 192 : 105295 .

LEI M , RAO Z Y , LI M , et al . Identification of coal geographical origin using near infrared sensor based on broad learning [J]. Applied Sciences , 2019 , 9 ( 6 ): 1111 .

滕菲 , 单麒赫 , 李铁山 . 智能船舶综合能源系统及其分布式优化调度方法 [J]. 自动化学报 , 2020 , 46 ( 9 ): 1809 - 1817 .

TENG F , SHAN Q H , LI T S . Intelligent ship integrated energy system and its distributed optimal scheduling algorithm [J]. Acta Automatica Sinica , 2020 , 46 ( 9 ): 1809 - 1817 . (in Chinese)

LIU Y Z , GOPALAKRISHNAN V . An overview and evaluation of recent machine learning imputation methods using cardiac imaging data [J]. Data , 2017 , 2 ( 1 ): 8 .

CHAWLA N V , BOWYER K W , HALL L O , et al . SMOTE: Synthetic minority over-sampling technique [J]. Journal of Artificial Intelligence Research , 2002 , 16 : 321 - 357 .

STRACK B , DESHAZO J P , GENNINGS C , et al . Impact of HbA1c measurement on hospital readmission rates: Analysis of 70, 000 clinical database patient records [J]. BioMed Research International , 2014 , 2014 : 781670 .

ZHANG Z , CAO L , ZHAO Y , et al . Hospitalized patients with heart failure: integrating electronic healthcare records and external outcome data (version 1.2) [EB/OL]. ( 2020 )[2021]. https://doi.org/10.13026/8a9e-w734 https://doi.org/10.13026/8a9e-w734 .

MOODY G B , MARK R G . The impact of the MIT-BIH arrhythmia database [J]. IEEE Engineering in Medicine and Biology Magazine , 2001 , 20 ( 3 ): 45 - 50 .

SPANHOL F A , OLIVEIRA L S , PETITJEAN C , et al . A dataset for breast cancer histopathological image classification [J]. IEEE Transactions on Bio-Medical Engineering , 2016 , 63 ( 7 ): 1455 - 1462 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

背景感知机制的图像分类网络

一种基于双层模型和指标分布的恶意网络流持续检测和分类方法

基于神经网络的图像风格迁移算法综述

基于自适应空间映射多可信度模型的网状天线形态机电集成优化设计