Research on prediction method from human body size to female trousers pattern size based on multi-model machine learning
Advances in Engineering Technology Research · 08.07.2026 · 17 (1) · 321
DOI: 10.56028/aetr.17.1.321.2026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Engineering Technology Research, online erschienen am 08.07.2026. Verfasst von Qianqian Ding und 2 weiteren Autor:innen.
Abstract (Originalsprache)
With the rise of customized apparel, traditional techniques for designing garment patterns are time-consuming, dependent on knowledge, and have limited precision..Based on 135 anthropometric data sets, this paper creates a prediction model between body size and pantsuit design features.Ridge regression, ElasticNet regression, GA-BP neural network and random forest were used to train the model, and the performance of the model was evaluated by RMSE, MAE and R². According to experimental results, the ElasticNet model performs best in terms of prediction accuracy (RMSE=0.3017, MAE=0.2744, R²=0.8204), suggesting that it has strong stability and feature selection ability while working with high-dimensional data from small samples.The research results provide a suitable reference for machine learning method in digital clothing pattern design.
Zitieren
APA
Ding, Q., Li, X., & Liu, Z. (2026). Research on prediction method from human body size to female trousers pattern size based on multi-model machine learning. Advances in Engineering Technology Research, 17(1), 321. https://doi.org/10.56028/aetr.17.1.321.2026
Vancouver
Ding Q, Li X, Liu Z. Research on prediction method from human body size to female trousers pattern size based on multi-model machine learning. Advances in Engineering Technology Research. 2026;17(1):321. doi:10.56028/aetr.17.1.321.2026
BibTeX
@article{Ding2026,
author = {Ding, Qianqian and Li, Xiaoyan and Liu, Zhengdong},
title = {Research on prediction method from human body size to female trousers pattern size based on multi-model machine learning},
journal = {Advances in Engineering Technology Research},
year = {2026},
volume = {17},
number = {1},
pages = {321},
doi = {10.56028/aetr.17.1.321.2026}
}
EUVIMED