通过WGAN-GP数据增强和XGBoost算法增强身体脂肪预测
1Department of Physical Education, Capital Normal University, Beijing, China.
Science progress
|August 7, 2025
概括
使用Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) 的生成数据增强显著提高了机器学习模型的准确性,用于从人类学数据中估计身体脂肪百分比,特别是在数据稀缺的情况下.
科学领域:
- 生物医学信息学 生物医学信息学
- 机器学习 机器学习
- 数据科学数据科学数据科学
背景情况:
- 机器学习模型可以使用人体测量数据估计身体脂肪百分比.
- 有限的生物医学数据往往会导致过拟合,并降低预测准确度.
- 生成式数据增强是数据稀缺的一个潜在解决方案.
研究的目的:
- 开发和评估一个生成数据增强框架,用于体脂预测.
- 使用有限的人类测量数据,提高机器学习模型的准确性.
主要方法:
- 与瓦斯斯坦生成对抗网络与梯度惩罚 (WGAN-GP),随机噪声注入和数据增强忠实性的混合进行了比较.
- 经过训练和验证的XGBoost,支持向量回归和多层感知器模型,有或没有增强.
- 在一个独立的测试集上使用R2,平均绝对误差和根平均平方误差评估模型概括.
主要成果:
- 在经过测试的方法中,WGAN-GP生成了最高准确度的合成数据.
- 通过WGAN-GP增强,XGBoost模型的性能从R2的0.67 (基线) 提高到0.77.
- 腹周被确定为身体脂肪百分比的最重要的预测指标.
结论:
- WGAN-GP有效地产生现实的合成人体测量数据.
- 整合WGAN-GP合成数据可以提高机器学习模型的概括性和预测准确性.
- 这种方法为在数据有限的环境中开发准确的预测健康模型提供了强大的解决方案.
相关概念视频
01:19Survival Tree
160
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
160
01:11Genome-wide Association Studies-GWAS
14.2K
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
14.2K