Indicator Transfer Learning Based on Cloud Model and Maximum Mean Discrepancy

doi:10.16182/j.issn1004731x.joss.24-0199

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.

Key words: cloud model, maximum mean discrepancy(MMD), indicator transfer learning, simulation assessment across platform and domain, simulation assessment on small data, indicator aggregation

CLC Number:

TP391.9

Xu Lixia, Zhong Jilong, Wu Shaoshi, Ding Yishan, Zhai Xiaoyu, Chen Shizhao, Wang Yizhe, Wen Xue, Zeng Juanfang, Hou Xinwen. Indicator Transfer Learning Based on Cloud Model and Maximum Mean Discrepancy[J]. Journal of System Simulation, 2024, 36(9): 2004-2015.

Figures/Tables 31

Fig. 1

Table 1

Fig. 2

Fig. 3

Fig. 4

Table 2

Table 3

Table 4

Table 5

Table 6

Table 7

Table 8

Table 9

Table 10

Fig. 5

Table 11

Table 12

Fig. 6

Table 13

Fig. 7

Table 14

Table 15

Fig. 8

Table 16

Fig. 9

Table 17

Table 18

Fig. 10

Table 19

Table 20

Table 21

References 20

1	Qi Ziyuan, Zhang Yangyang, Fang Liqing, et al. Research on Effectiveness Evaluation Method of Weapon System Based on Cloud Model[J]. Journal of Physics: Conference Series, 2021, 1965(1): 012005.
2	Papernot N, McDaniel P. Deep K-nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning[EB/OL]. (2018-03-13) [2024-03-05]. .
3	Huang Qian, Katsman I, Gu Zeqi, et al. Enhancing Adversarial Example Transferability with an Intermediate Level Attack[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2019: 4732-4741.
4	Szabo Zoltan, Lorincz Andras. Real and Complex Independent Subspace Analysis by Generalized Variance [EB/OL]. (2006-10-13) [2024-03-05]. .
5	付玉, 张垚, 赵萌, 等. 基于仿真数据迁移学习的固定翼无人机检测[J]. 系统仿真学报, 2023, 35(5): 998-1007.
	Fu Yu, Zhang Yao, Zhao Meng, et al. Fixed-wing UAV Detection Based on Simulated Data Transfer Learning[J]. Journal of System Simulation, 2023, 35(5): 998-1007.
6	Qu Shi, Zheng Yi, Yan Hua, et al. Operational Effectiveness Evaluation of Antimissile Early Warning Based on Combination Weighted TOPSIS[J]. Journal of Physics: Conference Series, 2021, 1927(1): 012007.
7	Feng Hao, Wang Nian, Tang Jun. Deep Weibull Hashing with Maximum Mean Discrepancy Quantization for Image Retrieval[J]. Neurocomputing, 2021, 464: 95-106.
8	Pinto Giuseppe, Wang Zhe, Roy A, et al. Transfer Learning for Smart Buildings: A Critical Review of Algorithms, Applications, and Future Perspectives[J]. Advances in Applied Energy, 2022, 5: 100084.
9	Cody T, Beling P A. A Systems Theory of Transfer Learning[J]. IEEE Systems Journal, 2023, 17(1): 26-37.
10	Abuduweili A, Li Xingjian, Shi H, et al. Adaptive Consistency Regularization for Semi-supervised Transfer Learning[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2021: 6919-6928.
11	Zhu Zhuangdi, Lin Kaixiang, Jain A K, et al. Transfer Learning in Deep Reinforcement Learning: A Survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(11): 13344-13362.
12	Wu Ocean, Yun Sing Koh, Dobbie Gillian, et al. Transfer Learning with Adaptive Online TrAdaBoost for Data Streams[C]//Proceedings of the 13th Asian Conference on Machine Learning. Chia Laguna Resort: PMLR, 2021: 1017-1032.
13	Long Mingsheng, Cao Yue, Wang Jianmin, et al. Learning Transferable Features with Deep Adaptation Networks[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning. New York: JMLR, 2015: 97-105.
14	Yosinski J, Clune J, Bengio Y, et al. How Transferable Are Features in Deep Neural Networks?[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014: 3320-3328.
15	Li Na, Hao Huizhen, Gu Qing, et al. A Transfer Learning Method for Automatic Identification of Sandstone Microscopic Images[J]. Computers & Geosciences, 2017, 103: 111-121.
16	Xu Yonghui, Pan Jialin, Xiong Hui, et al. A Unified Framework for Metric Transfer Learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(6): 1158-1171.
17	Tzeng E, Hoffman J, Saenko K, et al. Adversarial Discriminative Domain Adaptation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 2962-2971.
18	Zhu Han, Long Mingsheng, Wang Jianmin, et al. Deep Hashing Network for Efficient Similarity Retrieval[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2016: 2415-2421.
19	Long Mingsheng, Zhu Han, Wang Jianmin, et al. Unsupervised Domain Adaptation with Residual Transfer Networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2016: 136-144.
20	Davis J, Domingos P. Deep Transfer via Second-order Markov Logic[C]//Proceedings of the 26th Annual International Conference on Machine Learning. New York: Association for Computing Machinery, 2009: 217-224.

方式	特点
基于实例	赋予源域实例一定的权重对其进行复用
基于特征	基于特征变换减少源域与目标域之间的差距
基于网络	找出源域与目标域网络模型之间的共享参数
基于关系	挖掘不同领域之间的关系相似性

参数	红方	蓝方
装备	侦察无人机	攻击无人车
数量	5	5
视野/km	15	10
攻击武器		地地导弹
射程/km		15
速度/(km/h)	30	6
分值	1	1

参数	红方	蓝方
装备	侦察无人车	侦察无人车
数量	5	5
视野/km	15	15
攻击武器
射程/km
速度/(km/h)	6	6
分值	1	1

参数	红方	蓝方
装备	攻击无人机	攻击无人机
数量	5	5
视野/km	10	10
攻击武器	空空导弹	空空导弹
射程/km	10	10
速度/(km/h)	30	30
分值	1	1

参数	红方	蓝方
装备	攻击无人机	防空无人车
数量	10	10
视野/km	10	15
攻击武器	空地导弹	地空导弹
射程/km	10	15
速度/(km/h)	30	6
分值	1	1