Indicator Transfer Learning Based on Cloud Model and Maximum Mean Discrepancy

Authors

Lixia Xu, National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China
Jilong Zhong, National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China
Shaoshi Wu, National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China
Yishan Ding, National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China
Xiaoyu Zhai, National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China
Shizhao Chen, National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China
Yizhe Wang, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Xue Wen, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Juanfang Zeng, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Xinwen Hou, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

Abstract

Abstract: In response to the problem of rare data samples in application experiment scenarios, this paper proposes an indicator transfer learning method based on cloud models and Maximum Mean Discrepancy (MMD), which transfers the indicator calculation model from typical simulation experiment scenarios to application experiment scenarios to meet the needs across platform and domain simulation evaluation. Using the maximum mean difference method to align the indicator distribution in the typical simulation experiment scenario to the indicator distribution in the application experiment scenario, thereby achieves indicator transfer, and by using cloud models based on a small number of examples for modeling and sampling, improves the efficiency of indicator transfer learning modeling. The effectiveness of our method has been verified through several indicator model transfer learning experiments from typical simulation experiment scenario to several application experiment scenarios. The distributions of target domain by our method are closer than those by Generative Adversarial Network transfer learning to the distributions of source domain. The transfer learning peformance of perception, cognition, decision and action ability indicators improves averagely 36.62% by Wasserstein distance measure.

Recommended Citation

Xu, Lixia; Zhong, Jilong; Wu, Shaoshi; Ding, Yishan; Zhai, Xiaoyu; Chen, Shizhao; Wang, Yizhe; Wen, Xue; Zeng, Juanfang; and Hou, Xinwen (2024) "Indicator Transfer Learning Based on Cloud Model and Maximum Mean Discrepancy," Journal of System Simulation: Vol. 36: Iss. 9, Article 3.
DOI: 10.16182/j.issn1004731x.joss.24-0199
Available at: https://dc-china-simulation.researchcommons.org/journal/vol36/iss9/3

First Page

2004

Last Page

2015

CLC

TP391.9

Recommended Citation

Xu Lixia, Zhong Jilong, Wu Shaoshi, et al. Indicator Transfer Learning Based on Cloud Model and Maximum Mean Discrepancy[J]. Journal of System Simulation, 2024, 36(9): 2004-2015.

Corresponding Author

Hou Xinwen

DOI

10.16182/j.issn1004731x.joss.24-0199