Wang Song, Xi Ning, Zhou Zhengfang
Department of Data and Systems Engineering, The University of Hong Kong, Pok Fu Lam, Hong Kong.
Department of Mathematics, Michigan State University at East Lansing, East Lansing, USA.
Sci Rep. 2025 Jul 1;15(1):22385. doi: 10.1038/s41598-025-05320-6.
This paper proposes a novel machine learning paradigm called the generative adversarial tri-model (GAT) to incorporate analytical knowledge into neural networks through a unique positive-sum game strategy. The motivation is to solve the problem that pure machine learning models fail to obey the fundamental governing laws of physics in engineering fields. The GAT method is successfully implemented to solve ODE (ordinary differential equation) problems with various constraints. A strict error bound is proven for initial-constraint problems, which certifies its reliability. The real-world significance of the GAT method is reflected by its application to a human body oscillation recovery problem, based on balance sensor measurements, which is critical for human balancing evaluation, yet unresolved after massive precedent research work. Further human experiment results prove the effectiveness of the GAT method. Both theoretical and experimental studies demonstrate that the GAT method is useful and reliable. It envisions great scalability for wider applications and adaptions prospect.
本文提出了一种名为生成对抗三元模型（GAT）的新型机器学习范式，通过独特的正和博弈策略将分析知识融入神经网络。其动机是解决工程领域中纯机器学习模型无法遵循物理基本定律的问题。GAT方法已成功用于解决具有各种约束的常微分方程（ODE）问题。对于初始约束问题证明了严格的误差界，这证明了其可靠性。GAT方法的实际意义体现在其基于平衡传感器测量应用于人体振荡恢复问题上，该问题对于人体平衡评估至关重要，但经过大量的前期研究工作仍未得到解决。进一步的人体实验结果证明了GAT方法的有效性。理论和实验研究均表明，GAT方法是有用且可靠的。它具有广阔的扩展性，有望得到更广泛的应用和适应。
