基于BP神经网络的运动文胸肩带属性与乳房振幅的函数关系

doi:10.13475/j.fzxb.20181001406

摘要/Abstract

摘要：

为确定运动文胸肩带的3种属性在人体跑步时对胸部振幅的影响,选取8名被测人员,在其左胸上标记6个测量点,更换不同的肩带进行人体运动测试,记录这些测量点动态的三维坐标,进而得到乳房运动的振幅;利用BP神经网络模型,通过更换不同的网络模型参数,确定运动文胸肩带的3种属性与乳房振幅之间的权值关系。结果表明,选取BP神经网络的传输函数为tansig函数,隐含层神经元个数为21个,训练函数为traingdm作为网络参数时,网络拟合出的乳房振幅值达到了真实值的99.44%;在该网络参数下,分别求得网络输入层到隐含层和隐含层到输出层的权值和阈值,最终得到肩带的3种属性与胸部振幅的正向推理关系式。

关键词: 运动文胸, 文胸肩带, BP神经网络, 胸部振幅

Abstract:

In order to determine the influence of 3 properties of the sports bras shoulder straps on breast amplitudes during running, the motions of breast markers were attached in 6 different left breast positions of 8 subjects, and different shoulder straps were replaced for the human motion testing. The 3-D coordinates of the breast markers were recorded, and the amplitudes of the breast motion were obtained. The weight relationship between the 3 properties of the shoulder straps and the breast amplitude was determined by using the BP neural network model to replace different model parameters. The results show that when the transmission function of BP neural network is tansig function, the number of implicit layer neurons is 21, and the training function is traingdm as the network parameters, the breast amplitude values of the network fitting is close to the true values of the breast motion to 99.44%. The weights and thresholds of the network input to the hidden layer and the hidden to the output layer are respectively obtained under the network parameters. The positive inference relationship between 3 kinds of properties of the shoulder straps and the breast amplitudes can be obtained.

Key words: sports bra, bra shoulder strap, BP neural network, breast amplitude

中图分类号:

TS941.763.5

周捷, 马秋瑞. 基于BP神经网络的运动文胸肩带属性与乳房振幅的函数关系[J]. 纺织学报, 2019, 40(09): 186-191.

ZHOU Jie, MA Qiurui. Prediction of relationship between shoulder strap attribute and breast amplitude of sports bra by BP neural network[J]. Journal of Textile Research, 2019, 40(09): 186-191.

图/表 7

图1

图2

表1

图3

表2

图4

表3

参考文献 23

[1]	马秋瑞, 周捷, 李健, 等. 基于小波变换的文胸底围压力数据分析[J]. 针织工业, 2018(9):57-60.
	MA Qiurui, ZHOU Jie, LI Jian, et al. Analysis of bra bottom circumference pressure data based on wavelet transform[J]. Knitting Industries, 2018(9):57-60.
[2]	于晓坤. 文胸肩带功能分析与设计研究[D]. 上海:东华大学, 2014: 2-3.
	YU Xiaokun. Function analyses and design of bra straps abstract[D]. Shanghai: Donghua University, 2014: 2-3.
[3]	马秋瑞, 周捷, 李健, 等. 运动文胸肩带数据分析[J]. 西安工程大学学报, 2018,32(3):249-253,271.
	MA Qiurui, ZHOU Jie, LI Jian, et al. Data analysis of sports bra strap[J]. Journal of Xi'an Polytechnic University, 2018,32(3):249-253,271.
[4]	YU Xiaokun, WANG Keyi, HE Jiazhen, et al. Factorial analysis on breast lifted and gathered effects caused by bra straps[J]. Advanced Materials Research, 2011, 332-334:1451-1456. doi: 10.4028/www.scientific.net/AMR.332-334
[5]	徐军, 王成荣, 李条条. 文胸肩带的选择依据分析[J]. 西安工程大学学报, 2011,25(2):193-197.
	XU Jun, WANG Chengrong, LI Tiaotiao. Analysis of the basis of straps choice[J]. Journal of Xi'an Polytechnic University, 2011,25(2):193-197.
[6]	甘应进, 陈东生, 孟爽, 等. 女胸衣肩带滑落的原因及改进[J]. 纺织学报, 2005,26(2):127-129.
	GAN Yingjin, CHEN Dongsheng, MENG Shuang, et al. Exploration and ameliorative method on brassiere girdle sliding[J]. Journal of Textile Research, 2005,26(2):127-129.
[7]	ZHOU Jie, YU Winnie. A study on biomechanical models of sports bra's shoulder straps[J]. Journal of Fiber Bioengineering and Informatics, 2013,6(4):441-451. doi: 10.3993/jfbi
[8]	李立新. 文胸的肩带设计研究[J]. 针织工业, 2008(5):35-38.
	LI Lixin. Study on the shoulder strap design of bra[J]. Knitting Industries, 2008(5):35-38.
[9]	ZHOU Jie, YU Winnie, NG Sunpui. Studies of three-dimensional trajectories of breast movement for better bra design[J]. Textile Research Journal, 2012,82(3):242-254. doi: 10.1177/0040517511435004
[10]	MENTZ H A, RUIZ-RAZURA A, MINIEL L A. Correction of the bra strap shoulder groove deformity in women[J]. Plastic and Reconstructive Surgery, 2007,120(7):2122-2123. doi: 10.1097/01.prs.0000264660.73371.14 pmid: 18090798
[11]	于晓坤, 肖平, 张音. 文胸肩带拉伸性能测试分析[J]. 纺织学报, 2013,34(7):100-105.
	YU Xiaokun, XIAO Ping, ZHANG Yin. Stretchability test of bra straps[J]. Journal of Textile Research, 2013,34(7):100-105.
[12]	BOWLES K A, STEELE J R. Effects of strap cushions and strap orientation on comfort and sports bra performance[J]. Medicine and Science in Sports and Exercise, 2013,45(6):1113-1119. pmid: 23274596
[13]	COLTMAN C E, MCGHEE D E, STEELE J R. Bra strap orientations and designs to minimise bra strap discomfort and pressure during sport and exercise in women with large breasts[J]. Sports Medicine-Open, 2015(1):5. doi: 10.1186/s40798-014-0005-5 pmid: 27747842
[14]	王丽卓, 陈东生, 林彬. 文胸肩带压强分布分析[J]. 纺织学报, 2009,30(9):102-105.
	WANG Lizhuo, CHEN Dongsheng, LIN Bin. Analysis of pressure distribution of bra's shoulder straps[J]. Journal of Textile Research, 2009,30(9):102-105.
[15]	ZHOU Jie. New methods of evaluating breast motion[D]. Hong Kong: The Hongkong Polytechnic University, 2011: 88-134.
[16]	ZHOU Jie, YU Winnie. Identifying effective design features of commercial sports bras[J]. Textile Research Journal, 2013,83(14):1500-1513. doi: 10.1177/0040517512464289
[17]	罗成汉. 基于MATLAB神经网络工具箱的BP网络实现[J]. 计算机仿真, 2004,21(5):109-111.
	LUO Chenghan. Realization of BP network based on neural network tool kit in MATLAB[J]. Computer Simulation, 2004,21(5):109-111.
[18]	HE Yong, LI Xiaoli, DENG Xunfei. Discrimination of varieties of tea using near infrared spectroscopy by principal component analysis and BP model[J]. Journal of Food Engineering, 2007,79(4):1238-1242. doi: 10.1016/j.jfoodeng.2006.04.042
[19]	WANG Zhiliang, LI Yongchi, SHEN R F. Correction of soil parameters in calculation of embankment settlement using a BP network back-analysis model[J]. Engineering Geology, 2007,91(2-4):168-177. doi: 10.1016/j.enggeo.2007.01.007
[20]	徐力平, 张炎华. 评价神经网络拟合精度的另一个指标[J]. 上海交通大学学报, 2002,36(7):980-983.
	XU Liping, ZHANG Yanhua. Another criterion to judge performance of neural networks[J]. Journal of Shanghai Jiaotong University, 2002,36(7):980-983.
[21]	柳松青. MATLAB神经网络BP网络研究与应用[J]. 计算机工程与设计, 2003,24(11):81-83.
	LIU Songqing. Research and application on MATLAB BP neural network[J]. Computer Engineering and Design, 2003,24(11):81-83.
[22]	杨宝华. 基于Matlab的BP神经网络应用[J]. 电脑知识与技术, 2008,3(7):124-125.
	YANG Baohua. Based on Matlab BP neural network application[J]. Computer Knowledge and Technology, 2008,3(7):124-125.
[23]	徐远芳, 周旸, 郑华. 基于MATLAB的BP神经网络实现研究[J]. 微型电脑应用, 2006,22(8):41-44.
	XU Yuanfang, ZHOU Yang, ZHENG Hua. The research on the realization of back propagation network based on MATLAB[J]. Microcomputer Applications, 2006,22(8):41-44.

相关文章 15

[1]	王建萍, 徐朔, 王竹君, 姚晓凤, 李永贵. 智能运动文胸电子监测系统设计方案与实施[J]. 纺织学报, 2020, 41(06): 105-111.
[2]	郑晶晶, 赵清瑶, 阎玉秀. 跑步运动中运动文胸对乳房振幅的影响[J]. 纺织学报, 2020, 41(03): 130-135.
[3]	王晓晖, 刘月刚, 孟婥, 孙以泽. 基于遗传算法和神经网络的3D增材印花工艺参数优化[J]. 纺织学报, 2019, 40(11): 168-174.
[4]	陈慧娴, 鲁虹, 李书洋, 左恒. 运动文胸结构设计要素对穿着舒适性的影响[J]. 纺织学报, 2019, 40(09): 159-166.
[5]	查刘根, 谢春萍. 应用四层BP神经网络的棉纱成纱质量预测[J]. 纺织学报, 2019, 40(01): 52-56.
[6]	高晓晓江红霞. 应用3D打印技术的运动文胸模杯个性化定制[J]. 纺织学报, 2018, 39(11): 135-139.
[7]	巫莹柱　单颖法　黄伯熹　林广茂　梁家豪　张晓利. 聚对苯二甲酸丙二醇酯与聚对苯二甲酸丁二醇酯混纺纤维的智能识别[J]. 纺织学报, 2018, 39(09): 169-175.
[8]	张宁潘如如高卫东. 采用图像处理的织物缝纫平整度自动评估[J]. 纺织学报, 2017, 38(04): 145-150.
[9]	夏明陈益松张文斌. 基于椭圆傅里叶的人体胸围断面形状研究[J]. 纺织学报, 2014, 35(7): 107-0.
[10]	杨梦星张毅郑秋婷. BP神经网络预测环境对丝织物力学性能的影响[J]. 纺织学报, 2013, 34(8): 39-0.
[11]	于晓坤肖平张音. 文胸肩带拉伸性能测试分析[J]. 纺织学报, 2013, 34(7): 100-105.
[12]	张海波黄铁军修毅赵野军章江华. 基于神经网络的男西装图像情感语义识别[J]. 纺织学报, 2013, 34(12): 138-0.
[13]	王方圆陈晓娜王建萍. 胸部位移与文胸舒适性关系初探[J]. 纺织学报, 2013, 34(1): 106-109.
[14]	黄成王晓任春明王辉刘燕刘凯. 亚麻织物接枝率与透气率变化关系的数学模型[J]. 纺织学报, 2013, 34(1): 90-95.
[15]	林君焕张国庆张树有. 缝纫机缝纫性能测量评价系统的设计[J]. 纺织学报, 2013, 34(1): 116-121.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

标记点序号	距离/ cm	面密度/ (g·m^-2)	伸长率/%	强力/ N	每个标记点整体振幅/cm
标记点序号	距离/ cm	面密度/ (g·m^-2)	伸长率/%	强力/ N	x方向	y方向	z方向
1	7.18	66.3	133	0.553	0.45	1.13	0.23
2	4.31	51.3	82	1.036	0.40	0.66	0.23
3	6.20	73.8	80	1.458	0.47	0.77	0.21
?	?	?	?	?	?	?	?
431	5.78	59.4	74	1.462	1.69	1.63	0.96
432	6.68	69.4	81	1.570	1.74	1.91	1.10

隐含层神经元个数	logsig下的训练函数
隐含层神经元个数	trainbfg函数	traingd函数	traingdm函数	trainbfg函数	traingd函数	traingdm函数
20	net¹(0.078)	net²(0.053)	net³(0.045)	net⁴(0.045)	net⁵(0.033)	net⁶(0.025)
21	net⁷(0.096)	net⁸(0.066)	net⁹(0.040)	net¹⁰(0.040)	net¹¹(0.036)	net¹²(0.023)
22	net¹³(0.089)	net¹⁴(0.077)	net¹⁵(0.047)	net¹⁶(0.047)	net¹⁷(0.037)	net¹⁸(0.025)
23	net¹⁹(0.072)	net²⁰(0.087)	net²¹(0.048)	net²²(0.048)	net²³(0.037)	net²⁴(0.027)
24	net²⁵(0.078)	net²⁶(0.055)	net²⁷(0.048)	net²⁸(0.048)	net²⁹(0.045)	net³⁰(0.026)
25	net³¹(0.095)	net³²(0.059)	net³³(0.048)	net³⁴(0.045)	net³⁵(0.039)	net³⁶(0.029)
26	net³⁷(0.080)	net³⁸(0.062)	net³⁹(0.049)	net⁴⁰(0.049)	net⁴¹(0.030)	net⁴²(0.032)
27	net⁴³(0.097)	net⁴⁴(0.088)	net⁴⁵(0.059)	net⁴⁶(0.059)	net⁴⁷(0.038)	net⁴⁸(0.027)
28	net⁴⁹(0.096)	net⁵⁰(0.082)	net⁵¹(0.052)	net⁵²(0.052)	net⁵³(0.032)	net⁵⁴(0.026)
29	net⁵⁵(0.089)	net⁵⁶(0.083)	net⁵⁷(0.059)	net⁵⁸(0.049)	net⁵⁹(0.038)	net⁶⁰(0.027)

行列序号	输入层到隐含层					隐含层到输出层
	权值矩阵iw¹				阈值矩阵b¹	权值矩阵iw²的转置			阈值矩阵b²
	第1列	第2列	第3列	第4列	第1列	第1列	第2列	第3列	第1列
第1行	-26.17	56.67	-2.03	111.23	13.63	-0.47	-0.52	-0.41	1.10
第2行	2.28	-4.50	-0.01	0.66	-12.98	1.21	3.10	2.05	0.95
第3行	2.03	-58.88	0.39	17.01	-15.79	1.11	1.26	0.71	0.42
第4行	-0.41	-14.59	-0.15	-5.35	41.85	5.64	9.81	7.02
第5行	-3.32	-6.20	-0.16	-5.45	47.19	0.97	1.22	0.67
第6行	-6.78	-1.97	-0.59	-15.81	130.42	-0.32	-0.47	-0.34
第7行	-7.00	6.39	-0.15	-7.87	61.04	-0.61	-0.65	-0.48
第8行	0.32	11.22	0.07	1.68	-23.98	-5.09	-9.73	-6.76
第9行	-11.57	31.61	1.77	12.12	-122.90	0.66	0.98	0.53
第10行	-30.91	97.42	0.23	70.22	-63.00	-0.23	-0.32	-0.24
第11行	-1.48	4.75	-0.01	-1.28	8.89	1.93	4.04	2.63
第12行	-4.80	-46.03	0.30	-9.72	68.04	-0.81	-1.03	-0.60
第13行	-6.21	41.80	1.06	34.48	-145.52	-0.88	-1.12	-0.64
第14行	-51.15	-28.91	3.91	-54.67	-6.12	0.48	0.72	0.35
第15行	-0.36	-12.74	-0.10	-3.35	31.93	-10.30	-18.57	-13.07
第16行	-7.53	28.20	-0.20	20.64	-18.45	-0.63	-0.91	-0.45
第17行	-19.96	-11.37	0.33	29.72	46.60	0.59	0.68	0.43
第18行	-5.40	23.37	0.24	4.58	-26.83	0.98	1.37	0.79
第19行	40.27	-3.86	-0.01	-0.17	-225.58	0.09	0.51	0.07
第20行	-18.74	15.71	0.02	1.22	71.45	-1.63	-2.04	-1.21
第21行	7.02	-4.53	0.72	-31.33	-39.55	-0.77	-1.01	-0.58