Journal of Textile Research ›› 2019, Vol. 40 ›› Issue (04): 111-116.doi: 10.13475/j.fzxb.20180601407

• Apparel Engineering • Previous Articles     Next Articles

Application of BP neural network in prediction of shapewear pressure

ZHOU Jie(), MA Qiurui   

  1. Apparel & Art Design College, Xi'an Polytechnic University, Xi'an, Shaanxi 710048, China
  • Received:2018-06-01 Revised:2019-01-07 Online:2019-04-15 Published:2019-04-16

Abstract:

In order to predict underwear pressure when wearing shapewear, a prediction method based on neural network was proposed. A total of 26 female college students wore the shapewear of the same brand, and were asked to perform four poses. The pressure values at 20 body points of each subject were measured, respectively. Two different BP neural network toolbox functions were used to establish the pressure prediction models. The relationships between the pressure values and five body measurements were analyzed. The prediction results were tested and compared while using the two different toolbox functions and different input values. The results show that the method based on neural network does not need complicated calculation process. By this method, five body measurement values can be directly used to predict the pressure value of shapewear. The prediction accuracy of the newff function is superior to that of the feedforwardnet function. The accuracy of the prediction of pressure in the two standing poses is better than that in the two sitting poses. When taking the pressure values of standing pose and five body measurements as input values, the pressure values of the other three poses can be predicted with the accuracy over 82%.

Key words: shape wear, underwear pressure, BP neural network, pressure prediction model

CLC Number: 

  • TS941.763.5

Fig.1

Pressure test points for body shaper and girdle. (a) Front of body shaper; (b)Behind of body shaper; (c)Front of girdle; (d)Behind of girdle"

Tab.1

Reasons for pressure test points"

身体
部位
压力点 选择的原因


肩中点(S1) 肩带承受乳房的重力,压力较大
腋下点(S2) 此处收纳副乳、脂肪堆积和赘肉,为评价塑型效果关键点
胃部中点(S3) 收纳脂肪,评价塑型效果关键点
前侧腰中点(S4) 鱼骨所在位置,该点压力相对较大
侧腰处(S5) 收纳脂肪,评价塑型效果关键点
后侧腰中点(S6) 鱼骨所在位置,该点压力相对较大
底边前中点(S7) 收纳脂肪,该点压力相对较大,评价塑型效果关键点
底边侧中点(S8) 腹围线和侧缝线的交点,压力较大
底边后侧中点(S9) 该点压力相对较大
肩胛骨处(S10) 收紧肩胛赘肉,提拉背部肌肉的关键部位,评价塑型效果关键点



腹凸点(P1) 腹部赘肉,评价塑型效果关键点
前侧臀点(P2) 脂肪堆积,评价塑型效果关键点
侧臀点(P3) 此处为髂骨处,骨骼凸起易对人体产生压力
腹股沟点(P4) 影响健康关键点
大腿前凸点(P5) 评价塑型效果关键点
大腿侧(P6) 评价塑型效果关键点
大腿后凸点(P7) 评价塑型效果关键点
臀凸点(P8) 容易受力,评价塑型效果关键点
前腰中点(P9) 评价塑型效果关键点
侧腰中点(P10) 评价塑型效果关键点

Fig.2

Test poses. (a)Standing; (b)Standing forward; (c)Sitting; (d)Sitting forward"

Fig.3

newff function predicts pressure value of wearing shaper. (a)Standing; (b)Standing forward; (c)Sitting; (d)Sitting forward"

Fig.4

newff function predicts pressure value of wearing girdle. (a)Standing; (b)Standing forward; (c)Sitting; (d)Sitting forward"

Fig.5

feedforwardnet function predicts pressure value of wearing shaper. (a)Standing; (b)Standing forward; (c)Sitting; (d)Sitting forward"

Fig.6

feedormwardnet function predicts pressure value of wearing girdle. (a)Standing; (b)Standing forward; (c)Sitting; (d)Sitting forward"

Tab.2

Forecasting accuracy%"

姿势 feedforwardnet函数 newff函数 平均值
腰背夹 提臀束裤 腰背夹 提臀束裤
站姿 75.14 72.37 75.29 74.34 74.92
站姿前倾 74.18 76.54 77.28 74.25
坐姿 68.34 69.19 76.56 69.79 69.56
坐姿前倾 62.17 62.54 72.28 75.59
平均值 70.06 74.42

Fig.7

Prediction diagram wearing shaper. (a)Standing forward; (b)Sitting; (c)Sitting forward"

Fig.8

Prediction diagram wearing girdle. (a)Standing forward; (b)Sitting; (c)Sitting forward"

Tab.3

Forecasting accuracy of newff function%"

姿势 腰背夹 提臀束裤 平均值
站姿前倾 91.64 88.81 90.23
坐姿 83.24 82.15 82.70
坐姿前倾 84.67 82.88 83.78
平均值 86.52 84.61 85.57
[1] 刘莉, 张渭源, 王永进. 调整型内衣压力对人体生理指标的影响[J]. 纺织学报, 2008,29(11):97-102.
LIU Li, ZHANG Weiyuan, WANG Yongjin. Analysis of physiological response by foundation garment[J]. Journal of Textile Research, 2008,29(11):97-102.
[2] 宋晓霞, 冯勋伟. 服装压力与人体舒适性之关系[J]. 纺织学报, 2006,27(3):103-105.
SONG Xiaoxia, FENG Xunwei. Relationship between garment pressure and human comfortableness[J]. Journal of Textile Research, 2006,27(3):103-105.
[3] 孟祥令, 张渭源. 服装压力舒适性的研究进展[J]. 纺织学报, 2006,27(7):109-112.
MENG Xiangling, ZHANG Weiyuan. Progress of study on pressure comfort of clothing[J]. Journal of Textile Research, 2006,27(7):109-112.
[4] 徐军, 陶开山, 张莉, 等. 基于运动生物力学的女子沙滩排球服压力舒适性研究[J]. 西安工程大学学报, 2009,23(2):454-460.
XU Jun, TAO Kaishan, ZHANG Li, et al. Comfortableness of female beach volleyball clothes based on movement biological mechanic[J]. Journal of Xi'an Polytechnic University, 2009,23(2):454-460.
[5] 尹玲, 张文斌, 夏蕾. 服装压力舒适性的研究综述与分析[J]. 纺织学报, 2008,29(3):137-142.
YIN Ling, ZHANG Wenbin, XIA Lei. Review and analysis of pressure comfort of garment[J]. Journal of Textile Research, 2008,29(3):137-142.
[6] 罗笑南, 曾龙, 聂卉. 三维紧身内衣的压力分布计算模型[J]. 中山大学学报(自然科学版), 2001,40(6):99-101.
LUO Xiaonan, ZENG Long, NIE Hui. A computable model of pressure distribution of tight underwear[J]. Acta Scientiarum Naturalium Universitatis Sunya-tseni (Natural Science Edition), 2001,40(6):99-101.
[7] WANG Jianmin, LUO Xiaonan, LI Yi, et al. The application of the volumetric subdivision scheme in the simulation of elastic human body deformation and garment pressure[J]. Textile Research Journal, 2005,75(8):591-597.
[8] MIRJALILI S A, RAFFEEYAN M, SOLTANZADEH Z. The analytical study of garment pressure on the human body using finite elements[J]. Fibres & Textiles in Eastern Europe, 2008,16(3):69-73.
[9] ZHANG X, YEUNG K W, LI Y. Numerical simulation of 3D dynamic garment pressure[J]. Textile Research Journal, 2002,72(3):245-252.
[10] 闵惜琳, 刘国华. 用MatLab神经网络工具箱开发BP网络应用[J]. 计算机应用, 2001,21(8):163-164.
MIN Xilin, LIU Guohua. Using MatLab neural network toolbox to develop BP network application[J]. Computer Applications, 2001,21(8):163-164.
[11] 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 network tool kit in MatLab[J]. Computer Simulations, 2004,21(5):109-111.
[12] 沈波. 基于BP神经网络的股价预测应用研究[D]. 长沙:湖南大学, 2010: 5-20.
SHEN Bo. Research on the application of stock price forecasting based on BP neural network[D]. Changsha: Hunan University, 2010: 5-20.
[13] 占辉. 服装压力舒适性的人工神经网络预测[D]. 西安:西安工程大学 2005: 33-34.
ZHAN Hui. Artificial neural network prediction of clothing pressure comfort[D]. Xi'an: Xi'an Polytechnic University, 2005: 33-34.
[14] 孙宇, 曾卫东, 赵永庆, 等. 应用人工神经网络研究化学元素对钛合金相变点的影响[J]. 稀有金属材料与工程, 2010,39(6):1031-1036.
SUN Yu, ZENG Weidong, ZHAO Yongqing, et al. Study on effects of elloying elements on β transus temperature of titanium alloys using artificial neural network[J]. Rare Metal Materials and Engineering, 2010,39(6):1031-1036.
[15] 郭利辉, 周雅. 基于MatLab神经网络工具箱的BP网络设计[J]. 信息技术与信息化, 2009(3):20-22.
GUO Lihui, ZHOU Ya. The design of BP network based on MatLab toolbox[J]. Information Technology & Informatization, 2009(3):20-22.
[16] 董君. MatLab语言的特点与应用[J]. 吉林省经济管理干部学院学报, 2009,23,(5):60-63.
DONG Jun. The characteristics and application of MatLab language[J]. Journal of Jilin Province Economic Management Cadre College, 2009,23,(5):60-63.
[17] 蒲春, 孙政顺, 赵世敏. MatLab神经网络工具箱BP算法比较[J]. 计算机仿真, 2006,23(5):142-144.
PU Chun, SUN Zhengshun, ZHAO Shimin. Comparison of BP algorithm of MatLab NN toolbox[J]. Computer Simulation, 2006,23(5):142-144.
[1] ZHANG Xiaoxia, LIU Fengkun, MAI Wei, MA Chongqi. Prediction of loom efficiency based on BP neural network and its improved algorithm [J]. Journal of Textile Research, 2020, 41(08): 121-127.
[2] JIN Shoufeng, LIN Qiangqiang, MA Qiurui, ZHANG Hao. Method for detecting fluff quality of fabric surface based on BP neural network [J]. Journal of Textile Research, 2020, 41(02): 69-76.
[3] WANG Xiaohui, LIU Yuegang, MENG Zhuo, SUN Yize. Optimization of process parameters for 3D additive screen printing based on genetic algorithm and neural network [J]. Journal of Textile Research, 2019, 40(11): 168-174.
[4] 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.
[5] ZHA Liugen, XIE Chunping. Prediction of cotton yarn quality based on four-layer BP neural network [J]. Journal of Textile Research, 2019, 40(01): 52-56.
[6] . Intelligent determination of blending fiber for polytrimethylene terephthalate and polybutylene terephthalate [J]. Journal of Textile Research, 2018, 39(09): 169-175.
[7] . Generation of intelligent fitting pattern based on BP neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(07): 116-121.
[8] . Shape analysis of bust slice using Elliptic Fourier [J]. JOURNAL OF TEXTILE RESEARCH, 2014, 35(7): 107-0.
[9] . Prediction for effect of environmental factors on silk fabric mechanical property by BP neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(8): 39-0.
[10] . Men’s suit image emotional semantic recognition based on BP neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(12): 138-0.
[11] Xiao WANG. Mathematical mdel for relationship between graft ratio and variation of air permeability of linen fabric [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(1): 90-95.
[12] . Forecast of women's SS fashion color based on BP neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2011, 32(7): 111-116.
[13] LI Xiang;PENG Zhiqin;JIN Fengying;GU Zongdong;XUE Yuan;HU Guoliang. Comparing prediction models for worsted yarn performances based on neutral networks [J]. JOURNAL OF TEXTILE RESEARCH, 2011, 32(3): 51-56.
[14] WU Xionghua;LIU Ya;. Optimizing technological parameters of manufacturing meltblown nonwovens by BP neural networks [J]. JOURNAL OF TEXTILE RESEARCH, 2011, 32(1): 51-54.
[15] . K/S Value Prediction of Reactive Dyestuff with Improved LM-BP Algorithm [J]. JOURNAL OF TEXTILE RESEARCH, 2010, 31(8): 82-85.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!