摘要
为克服线性回归方法对人体尺寸预测缺少精度的缺陷,将灰色神经网络模型引入人体测量中.对36个测试样本进行灰色建模,并利用人工神经网络修正模型残差,以提高腹围尺寸的预测精度.为了验证模型的可靠性,用同一样本建立回归模型,并以7个测试样本检验两种模型的预测效果.结果显示,灰色神经网络模型的预测精度更高,能有效地简化量体工作,为实现特体服装定制化生产奠定基础.
In order to overcome the inaccuracy in human body size prediction by linear regression method,the grey neural network model was introduced into the human body measurement.Thirty six test samples were used for establishing the grey system modeling,and artificial neural network was used to correct model residuals,to improve the prediction accuracy of abdominal circumference size.In order to verify the reliability of the model,a regression model was established with the same sample,and seven test samples were taken to test the prediction effect of the two models.The results show that the prediction accuracy of grey neural network modeling was higher,which can effectively simplify the work volume,and lay the foundation for the personalized customization.
作者
李健
周捷
马秋瑞
LI Jian;ZHOU Jie;MA Qiurui(School of Fashion and Art Dcsign,Xi＇an Polytcchnic Univcrsity,Xi＇an 7100＇18,China)
出处
《西安工程大学学报》
CAS
2018年第3期266-271,共6页
Journal of Xi’an Polytechnic University
基金
陕西省教育厅国际科技合作计划项目(2018JM1044)
关键词
特殊体型
腹围尺寸
灰色模型
神经网络模型
组合预测
special body size
abdomen size
gray model
neural network model
combined forecast
