基于改进快速搜索和发现密度峰值算法的男童体型分类及判别

doi:10.13475/j.fzxb.20190802707

摘要/Abstract

摘要：

针对男童肥胖人群增加导致体型特征发生较大变化的问题,为优化男童的体型判别,以7~10岁学龄男童为研究对象,通过灰关联度计算男童8个体型特征的权重。采用加权快速搜索和发现密度峰值(CFSFDP)算法对男童体型进行分类与分析。再应用极限学习机建立男童体型判别模型。结果表明:加权CFSFDP算法对于男童体型分类的解释性较强,男童的8个体型特征值随着年龄的增长,近似呈现公差为一种特定方式的等差数列变化;7岁男童的体型差异性最小,10岁男童身体发育出现多样化,其体型差异较大;普通CFSFDP聚类结果的体型判别准确率为70%,加权CFSFDP聚类结果的体型判别准确率为90%;改进后的CFSFDP算法可有效提高男童体型判别的准确性与鲁棒性。

关键词: 童装设计, 男童体型分类, 男童体型判别, 体型特征权重, 聚类算法

Abstract:

In view of the notable changes in body type caused by the obesity among young boys and in order to optimize the body type recognition of young boys, the study was carried out on school age boys of 7 to 10 years old. To start with, the weights of 8 body type features were calculated through grey correlation. Then, the study used weighted clustering by fast search and finding of density peaks (CFSFDP)algorithm to classify and analyze the body types of boys. Finally, the research established the model of body type recognition for boys with the extreme learning machine. The results show that the weighted CFSFDP algorithm has a strong interpretation for the classification of body type in boys. The 8 body type features of young boys approximately form an arithmetic sequence with the tolerance with age; the 7-year-old boys has the smallest body type difference while the body types of 10-year-old boys show diversity. The accuracy of body type recognition for CFSFDP clustering is 70%, and that for weighted CFSFDP clustering increase to 90%. The improved CFSFDP algorithm therefore is recognized as effective to improve the accuracy and robustness of body type recognition for young boys.

Key words: children's wear design, body type classification for young boys, body type recognition for young boys, feature weight of body type, clustering algorithm

中图分类号:

TS941.17

周捷, 毛倩. 基于改进快速搜索和发现密度峰值算法的男童体型分类及判别[J]. 纺织学报, 2020, 41(05): 146-152.

ZHOU Jie, MAO Qian. Classification and recognition of body type for young boys based on improved fast search and finding of density peak algorithms[J]. Journal of Textile Research, 2020, 41(05): 146-152.

图/表 11

图1

图2

表1

图3

表2

图4

表3

表4

图5

图6

图7

参考文献 21

[1]	王付曼, 姚屹, 杨琦. 中国七个城市学龄前儿童消瘦、超重和肥胖状况的队列研究[J]. 中华疾病控制杂志, 2019,23(5):522-526.
	WANG Fuman, YAO Qi, YANG Qi. Cohort study on thin, overweight and obesity of preschool children among 7 cities in China[J]. Chinese Journal of Disease Control & Prevention, 2019,23(5):522-526.
[2]	SINGH L D. Somatotypes of the affluent and non-affluent meitei boys of manipur, India[J]. The Anthropologist, 2011,13(1):9-16.
[3]	黄大元, 张惠娟, 吴国运, 等. 湖南白族少年儿童体型特征[J]. 解剖学报, 2014,45(5):715-718.
	HUANG Dayuan, ZHANG Huijuan, WU Guoyun, et al. Somatotype characteristics of Bai ethnicity children and adolescents in Hu'nan[J]. Acta Anatomica Sinica, 2014,45(5):715-718.
[4]	PARK B K, LUMENG J C, LUMENG C N, et al. Child body shape measurement using depth cameras and a statistical body shape model[J]. Ergonomics, 2015,58(2):301-309. pmid: 25323820
[5]	PARK B K, REED M P. Parametric body shape model of standing children aged 3-11 years[J]. Ergonomics, 2015,58(10):1714-1725. pmid: 25933223
[6]	梁亚林, 张欣, 何素恒, 等. 6~12岁学龄儿童体型的数据测量与分析[J]. 西安工程科技学院学报, 2004(2):115-120.
	ZHANG Yalin, ZHANG Xin, HE Suheng, et al. Measurements and analyses on the body date of 6~12 school-age children[J]. Journal of Xi'an Polytechnic University, 2004(2):115-120.
[7]	景晓宁, 李晓久. 朴素贝叶斯算法在女童体型判别中的应用[J]. 纺织学报, 2017,38(12):124-128.
	JING Xiaoning, LI Xiaojiu. Application of Naive Bayesian method in girl's figure discrimination[J]. Journal of Textile Research, 2017,38(12):124-128.
[8]	叶清珠, 张欣. 4~6岁学龄前儿童体型分类研究[J]. 西安工程大学学报, 2009,23(6):58-62.
	YE Qingzhu, ZHANG Xin. Study of body shape classification for 4~6 years old children[J]. Journal of Xi'an Polytechnic University, 2009,23(6):58-62.
[9]	吴世刚, 邹平. 辽宁地区学龄女童体型分类分析[J]. 纺织学报, 2011,32(9):104-108.
	WU Shigang, ZOU Ping. Classification and analysis of forms of school-age girls from Liaoning province[J]. Journal of Textile Research, 2011,32(9):104-108.
[10]	YI Xiaoqing, YIN Chunyan, CHANG Ming, et al. Prevalence and risk factors of obesity among school-aged children in Xi'an, China[J]. European Journal of Pediatrics, 2012,171(2):389-394.
[11]	吴世刚. 辽宁地区6~9岁男童体型特征分析[J]. 纺织学报, 2007,28(7):91-93.
	WU Shigang. Analysis of the body figure features of boys aged 6-9 in Liaoning province[J]. Journal of Textile Research, 2007,28(7):91-93.
[12]	陈明艳. 成年女性体型特征及其服装样板设计[J]. 纺织学报, 2005,28(3):121-124.
	CHEN Mingyan. Body characteristics of the mature female and the design of template for suit-dress[J]. Journal of Textile Research, 2005,26(3):121-124.
[13]	刘宝宝, 周捷. 西安地区大胸中老年女性体型特征与分类研究[J]. 西安工程大学学报, 2019,33(4):364-368.
	LIU Baobao, ZHOU Jie. Study on body characteristics and classification of middle aged and old women with large breasts in Xi'an[J]. Journal of Xi'an Polytechnic University, 2019,33(4):364-368.
[14]	RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014,344(6191):1492-1496. doi: 10.1126/science.1242072 pmid: 24970081
[15]	李克清, 葛柳飞, 戴欢. 基于CFSFDP与ELM相结合的半监督室内定位算法[J]. 武汉大学学报(理学版), 2016,62(05):451-455.
	LI Keqing, GE Liufei, DAI Huan. A semi-supervised indoor location algorithm based on CFSFDP and ELM[J]. Journal of Wuhan University(Natural Science Edition), 2016,62(05):451-455.
[16]	徐睿, 梁循, 齐金山, 等. 极限学习机前沿进展与趋势[J]. 计算机学报, 2019,42(7):1640-1670.
	XU Rui, LIANG Xun, QI Jinshan, et al. Advances and trends in extreme learning machine[J]. Chinese Journal of Computers, 2019,42(7):1640-1670.
[17]	张英莉, 周捷, 毛倩. 基于灰色层次关联分析的微博营销评估[J]. 西安工程大学学报, 2019,33(3):262-267.
	ZHANG Yingli, ZHOU Jie, MAO Qian. A micro-blog marketing evaluation based on grey hierarchical correlation analysis[J]. Journal of Xi'an Polytechnic University, 2019,33(3):262-267.
[18]	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006,70(1):489-501.
[19]	HUANG G B, SONG S J, GUPTA J N D, et al. Semi-supervised and unsupervised extreme learning machines[J]. IEEE Transactions on Cybernetics, 2004,44(12):2405-2417. pmid: 25415946
[20]	陆俊, 陈志敏, 龚钢军, 等. 基于极限学习机的居民用电行为分类分析方法[J]. 电力系统自动化, 2019,43(2):97-104.
	LU Jun, CHEN Zhimin, GONG Gangjun, et al. Classification analysis method for electricity consumption behavior based on extreme learning machine algorithm[J]. Automation of Electric Power Systems, 2019,43(2):97-104.
[21]	杨乐, 杨磊. 基于核函数的在线序列ELM模型[J]. 纺织高校基础科学学报, 2013,26(4):516-520.
	YANG Le, YANG Lei. Online sequence ELM model based on the kernel function[J]. Basic Sciences Journal of Textile Universities, 2013,26(4):516-520.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

人体特征	权重	人体特征	权重
F₁	0.142 9	F₅	0.110 7
F₂	0.142 7	F₆	0.114 1
F₃	0.141 7	F₇	0.116 2
F₄	0.115 9	F₈	0.115 8

类簇中心	F₁	F₂	F₃	F₄	F₅	F₆	F₇	F₈
1	125	58	33	55	46	66	75	50
2	135	61	35	55	49	69	80	54
3	140	65	36	61	49	73	84	56
4	145	68	37	64	52	77	90	59

类簇差值统计量	F₁	F₂	F₃	F₄	F₅	F₆	F₇	F₈
3-2差值	5.0	4.0	1.0	6.0	0.0	4.0	4.0	2.0
4-3差值	5.0	3.0	1.0	3.0	3.0	4.0	6.0	3.0
均值	5.0	3.5	1.0	4.5	1.5	4.0	5.0	2.5
标准差	0.0	0.5	0.0	1.5	1.5	0.0	1.0	0.5

类簇中心	F₁	F₂	F₃	F₄	F₅	F₆	F₇	F₈
1	126	59	32	56	46	66	75	51
2	133	64	33	59	48	73	80	54
3	140	68	35	63	50	74	83	55
4	149	73	37	69	52	81	89	60