Data Set Construction Method for Intelligent Health Care and Its Application

doi:10.3778/j.issn.1673-9418.2101028

Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (7): 1543-1551.DOI: 10.3778/j.issn.1673-9418.2101028

• Service Computing • Previous Articles Next Articles

Data Set Construction Method for Intelligent Health Care and Its Application

ZHANG Linyu, TU Zhiying⁺(), HANG Shaoshi, ZHANG Bolin, CHU Dianhui

School of Computer Science and Technology, Harbin Institute of Technology, Weihai, Shandong 264209, China

Received:2021-01-07 Revised:2021-05-17 Online:2022-07-01 Published:2021-06-29
Supported by:
the National Key Research and Development Program of China(2018YFB1004800);the National Natural Science Foundation of China(61772159);the Natural Science Foundation of Shandong Province(ZR2017MF026)

面向智慧康养的数据集构建方法及其应用

张麟宇, 涂志莹⁺(), 杭少石, 张柏林, 初佃辉

哈尔滨工业大学计算机科学与技术学院,山东威海 264209

作者简介:张麟宇（1997—）,男,硕士研究生,主要研究方向为服务计算、知识图谱。
ZHANG Linyu, born in 1997, M.S. candidate. His research interests include service computing and knowledge graph.
涂志莹（1983—）,男,博士,副教授,CCF会员,主要研究方向为服务计算、知识工程。
TU Zhiying, born in 1983, Ph.D., associate professor, member of CCF. His research interests include service computing and knowledge engineering.
杭少石（1996—）,男,硕士研究生,主要研究方向为服务计算、知识图谱。
HANG Shaoshi, born in 1996, M.S. candidate. His research interests include service computing and knowledge graph.
张柏林（1997—）,男,硕士研究生,主要研究方向为机器学习、服务计算。
ZHANG Bolin, born in 1997, M.S. candidate. His research interests include machine learning and service computing.
初佃辉（1970—）,男,博士,教授,CCF会员,主要研究方向为服务计算、知识工程。
CHU Dianhui, born in 1970, Ph.D., professor, member of CCF. His research interests include service computing and knowledge engineering.
基金资助:
国家重点研发计划(2018YFB1004800);国家自然科学基金(61772159);山东省自然科学基金(ZR2017MF026)

Abstract

Abstract:

The rapid development of Internet and computer technology makes it possible to improve smart health care services in today’s aging population. However, there are some data problems that seriously restrict the process of intelligence in the field of elderly care, such as the lack of real data, the interference of dirty data, and too few standard samples. To solve the problem of lacking data set, this paper proposes a three-stage data set construction method based on machine learning on the basis of small sample data which are collected from the community health care in a city. In the first stage, this paper designs a tree structure-based generation strategy to generate the basic attributes of the data set according to the distribution of the original data. In the second stage, this paper obtains the basic behavioral ability evaluation index of the samples with naive Bayesian algorithm. In the third stage, this paper constructs a variety of multiple linear regression equations to get high-order behavioral ability index and evaluation stage on the basis of the first two stages. In order to verify the effectiveness of the data set generated by the model for downstream tasks, this paper designs multiple rehabilitation training plan recommendation models based on the generated data with neural network, and achieves 5 multi-classification tasks and 2 multi-label classification tasks. This paper verifies the authenticity and validity of generated data through analysis of experimental results and expert knowledge.

Key words: smart health care service, small sample data, naive Bayes, multiple linear regression

摘要：

互联网和计算机技术的快速发展,使得在人口老龄化的今天发展智慧康养服务成为可能。然而,养老领域的数据问题严重地制约着该领域的智慧化进程。真实数据的缺失、脏数据的干扰以及标准样本过少等问题层出不穷。针对数据集缺失问题,在收集了某市社区康养的小样本数据基础上,提出了一种基于机器学习的三阶段数据生成模型：第一阶段,使用基于树形结构的生成策略,按照原始数据的分布生成了数据集的基础属性;第二阶段,使用朴素贝叶斯算法生成样本的基础行为能力评估指标;第三阶段,在前两个阶段的基础上采用多元线性回归的方法生成高阶行为能力指标以及评估阶段。此外,为验证该模型生成的数据集对下游任务的有效性,在生成数据基础上,利用神经网络设计多个康复训练计划推荐模型,实现5个多分类任务和2个多标签分类任务。通过对实验结果的分析以及专家知识的注入,验证了生成数据的真实性和有效性。

关键词: 智慧康养服务, 小样本数据, 朴素贝叶斯, 多元线性回归

CLC Number:

TP301.6

ZHANG Linyu, TU Zhiying, HANG Shaoshi, ZHANG Bolin, CHU Dianhui. Data Set Construction Method for Intelligent Health Care and Its Application[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(7): 1543-1551.

张麟宇, 涂志莹, 杭少石, 张柏林, 初佃辉. 面向智慧康养的数据集构建方法及其应用[J]. 计算机科学与探索, 2022, 16(7): 1543-1551.

Figures/Tables 12

Fig.1 Data generation model

Table 1 Basic attribute statistical distribution

基础属性	数据包含项	分布比例
性别	（男、女）	[48∶32]
年龄	（按照年龄段划分）[0,44],[45,59],60以上	[15∶37∶28]
残疾类型	（偏瘫、截瘫、脑瘫等）	[59∶6∶3∶3 $⋯$ ]
残疾原因	（疾病、感染、产伤等）	[40∶10∶8∶5 $⋯$ ]
残疾等级	（一级、二级、三级等）	[10∶10∶20∶40]

Table 1 Basic attribute statistical distribution

基础属性	数据包含项	分布比例
性别	（男、女）	[48∶32]
年龄	（按照年龄段划分）[0,44],[45,59],60以上	[15∶37∶28]
残疾类型	（偏瘫、截瘫、脑瘫等）	[59∶6∶3∶3 $⋯$ ]
残疾原因	（疾病、感染、产伤等）	[40∶10∶8∶5 $⋯$ ]
残疾等级	（一级、二级、三级等）	[10∶10∶20∶40]

Table 2 Spearman correlation coefficient matrix of sample basic attributes

基础属性	性别	年龄	类型	原因	等级
性别	1.000	0.127	-0.013	-0.073	0.073
年龄	0.127	1.000	-0.087	0.050	-0.029
类型	-0.013	-0.087	1.000	0.545	0.105
原因	-0.073	0.050	0.545	1.000	0.157
等级	0.073	-0.029	0.105	0.157	1.000

Table 3 Sample data presentation of recommended model

样本属性	样本属性名称	解释
基本信息	性别	男、女
	年龄	样本的年龄
	残疾类型	偏瘫、截瘫等
	残疾原因	疾病、产伤等
	残疾等级	中国残疾人等级划分
	行为能力评估指标	翻身、坐等13项
	行为能力评估阶段	分为三个阶段
康复计划	运动康复目标	如能进行身体锻炼
	生活自理能力康复	如能独立吃饭
	生活适应能力康复	如能独立参加活动
	康复训练项目	如翻身、坐、站等
	康复疗法	如理疗、运动疗法
	康复训练强度	如每次训练15 min
	康复训练组数	如每周做3组

Fig.2 Sample feature extraction model

Table 4 Matrix of correctness degree evaluation

指标得分	0	1	2	3
0	1.00	0.75	0.50	0.25
1	0.75	1.00	0.75	0.50
2	0.50	0.75	1.00	0.75
3	0.25	0.50	0.75	1.00

Fig.3 Experimental results of ability index of turning over

Table 5 Each regression equation R2 and F value

回归方程	自变量	R²	F值
1	$X 1, X 2, X 3, X 4$	0.579	29.190
2	$X 1, X 2, X 3, X 4$	0.612	32.140
3	$X 1, X 2, X 3, X 4$	0.376	1.820
4	$X 1, X 2, X 3, X 4$	0.078	1.788
5	$X 1, X 2, X 3, X 4$	0.280	8.260
6	$X 1, X 2, X 3, X 4$	0.301	9.136
7	$X 1, X 2, X 3, X 4$	0.344	11.130
8	$X 1, X 2, X 3, X 4$	0.456	17.780
9	$X 1, X 2, X 3, X 4$	0.347	11.300

Table 5 Each regression equation R2 and F value

回归方程	自变量	R²	F值
1	$X 1, X 2, X 3, X 4$	0.579	29.190
2	$X 1, X 2, X 3, X 4$	0.612	32.140
3	$X 1, X 2, X 3, X 4$	0.376	1.820
4	$X 1, X 2, X 3, X 4$	0.078	1.788
5	$X 1, X 2, X 3, X 4$	0.280	8.260
6	$X 1, X 2, X 3, X 4$	0.301	9.136
7	$X 1, X 2, X 3, X 4$	0.344	11.130
8	$X 1, X 2, X 3, X 4$	0.456	17.780
9	$X 1, X 2, X 3, X 4$	0.347	11.300

Table 6 Experimental results of regression equation 1

参数	系数	标准差	t值	$p > \| t \|$
常量	-0.021 4	0.150	-0.142	0.887
$X 1$	0.266 3	0.081	3.290	0.001
$X 2$	0.118 3	0.091	-1.303	0.096
$X 3$	0.223 7	0.102	2.191	0.031
$X 4$	0.510 1	0.094	5.437	0.001

Table 6 Experimental results of regression equation 1

参数	系数	标准差	t值	$p > \| t \|$
常量	-0.021 4	0.150	-0.142	0.887
$X 1$	0.266 3	0.081	3.290	0.001
$X 2$	0.118 3	0.091	-1.303	0.096
$X 3$	0.223 7	0.102	2.191	0.031
$X 4$	0.510 1	0.094	5.437	0.001

Fig.4 Result of matrix similarity calculation

Table 7 Experimental results of multi-classification tasks %

评价指标	任务1	任务2	任务3	任务4	任务5
Acc	64	72	68	75	77

Table 8 Experimental results of multi-label classification tasks %

评价指标	康复训练项目	康复疗法
AUC	63	65

References 15

[1]	HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507. DOI URL
[2]	郭丽丽, 丁世飞. 深度学习研究进展[J]. 计算机科学, 2015, 42(5): 28-33.
	GUO L L, DING S F. Reaserch progress on deep learning[J]. Computer Science, 2015, 42(5): 28-33.
[3]	刘全, 翟建伟, 章宗长, 等. 深度强化学习综述[J]. 计算机学报, 2018, 41(1): 1-27.
	LIU Q, ZHAI J W, ZHANG Z Z, et al. A survey on deep reinforcement learning[J]. Chinese Journal of Computers, 2018, 41(1): 1-27.
[4]	刘尚希, 赵福昌, 侯海波. 中国人口老龄化、经济增长与社会化改革[J]. 发展研究, 2020(10): 4-9.
	LIU S X, ZHAO F C, HOU H B. Aging of Chinese population, economic growth and social reform[J]. Development Research, 2020(10): 4-9.
[5]	LI J, YANG S, WANG X, et al. Tree-structured data regeneration with network coding in distributed storage systems[C]// Proceedings of the 17th International Workshop on Quality of Service, Charleston, Jul 13-15, 2009. Piscataway: IEEE, 2010: 1-9.
[6]	HUAI M, HUANG L S, YANG W, et al. Privacy-preserving naïve Bayes classification[C]// LNCS 9403: Proceedings of the 8th International Conference on Knowledge Science, Engineering and Management, Chongqing, Oct 28-30, 2015. Cham: Springer, 2015: 627-638.
[7]	ISLAM M Q, TIKU M L. Multiple linear regression model under nonnormality[J]. Communications in Statistics, 2005, 33(10): 2443-2467.
[8]	HE H B, GARCIA E A. Learning from imbalanced data[J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 21(9): 1263-1284. DOI URL
[9]	BRANCO P, TORGO L, RIBEIRO R P. A survey of predictive modeling on imbalanced domains[J]. ACM Computing Surveys, 2017, 49(2): 1-50.
[10]	段萌, 王功鹏, 牛常勇. 基于卷积神经网络的小样本图像识别方法[J]. 计算机工程与设计, 2018, 39(1): 224-229.
	DUAN M, WANG G P, NIU C Y. Method of small sample size image recognition based on convolution neural network[J]. Computer Engineering and Design, 2018, 39(1): 224-229.
[11]	陈旭, 刘鹏鹤, 孙毓忠, 等. 面向不均衡医学数据集的疾病预测模型研究[J]. 计算机学报, 2019, 42(3): 596-609.
	CHEN X, LIU P H, SUN Y Z, et al. Research on disease prediction models based on imbalanced medical data sets[J]. Chinese Journal of Computers, 2019, 42(3): 596-609.
[12]	LIU X Y, WU J X, ZHOU Z H. Exploratory undersampling for class-imbalance learning[J]. IEEE Transactions on Systems, Man, and Cybernetics: Part B, 2009, 39(2): 539-550. DOI URL
[13]	LIANG G H, COHN A G. An effective approach for imbalanced classification: unevenly balanced Bagging[C]// Procee-dings of the 27th AAAI Conference on A.pngicial Intelligence, Bellevue, Jul 14-18, 2013. Menlo Park: AAAI, 2013: 1633-1634.
[14]	RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv:1511. 06434, 2015.
[15]	刘宇飞, 周源, 刘欣, 等. 基于Wasserstein GAN的新一代人工智能小样本数据增强方法——以生物领域癌症分期数据为例[J]. 工程, 2019, 5(1): 156-163.
	LIU Y F, ZHOU Y, LIU X, et al. Wasserstein GAN-based small-sample augmentation for new-generation a.pngicial intelligence: a case study of cancer-staging data in biological[J]. Engineering, 2019, 5(1): 156-163. DOI URL

Data Set Construction Method for Intelligent Health Care and Its Application

面向智慧康养的数据集构建方法及其应用

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 15

Related Articles 3

Recommended Articles

Metrics

[1]	YANG Zheng, DENG Zhaohong, LUO Xiaoqing, GU Xin, WANG Shitong. Target Tracking System Constructed by ELM-AE and Transfer Representation Learning [J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(7): 1633-1648.
[2]	SHANG Xianzhen, HAN Meng, SUN Yuzhong, SUN Yuning, CHEN Xu, HU Manman, MEI Yudong. Skin Diseases Diagnosis Method Based on Generative Adversarial Networks and Naive Bayes [J]. Journal of Frontiers of Computer Science and Technology, 2019, 13(6): 1005-1015.
[3]	TANG Huanling, LU Mingyu. Advanced SemiBoost-CR Categorization Model Utilizing Confidence-Based Resampling [J]. Journal of Frontiers of Computer Science and Technology, 2011, 5(11): 1048-1056.