Small sample data generation weapon combat effectiveness evaluation method based on CGAN
The invention discloses a small sample data generation weapon combat effectiveness evaluation method based on a CGAN, and the method comprises the steps: obtaining a data set, dividing the data set into a sample set and a test set, and training a CMGAN model through the test set; constructing a feat...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a small sample data generation weapon combat effectiveness evaluation method based on a CGAN, and the method comprises the steps: obtaining a data set, dividing the data set into a sample set and a test set, and training a CMGAN model through the test set; constructing a feature data model conversion network; constructing and training a CMGAN network model, including constructing a generator, constructing a discriminator and training a CMGAN network; acquiring a virtual sample set of a specific condition; and obtaining an efficiency evaluation result. The effective weapon combat effectiveness evaluation sample can be generated, and the weapon combat effectiveness evaluation accuracy can be improved under the small sample condition.
本发明公开了基于CGAN的小样本数据生成的武器作战效能评估方法,该方法包括获取数据集划分为样本集和测试集,以测试集对CMGAN模型进行训练;构建特征数据模型转换网络;构建并训练CMGAN网络模型,包括构建生成器、构建鉴别器和训练CMGAN网络;获取特定条件的虚拟样本集;获取效能评估结果。本发明能够生成有效的武器作战效能评估样本,可以在小样本条件下提高武器作战效能评估准确度。 |
---|