基于自训练半监督学习的战场态势评估模型

Battlefield Situation Assessment Model Based on Self-training Semi-supervised Learning

针对标记样本不足条件下基于机器学习的战场态势评估模型准确性不高的问题,提出了基于自训练半监督学习的战场态势评估模型。以适用于小样本条件下分类的支持向量机模型为基础分类器,通过自训练半监督学习方法利用无标签样本对支持向量机模型进行辅助训练来提高模型的准确性和泛化性能。实验表明,在标记样本不足条件下,相对于只采用有标签样本的支持向量机模型来说,所提模型在评估准确率方面有较大的提高。

Aiming at the problem that the accuracy of battlefield situation assessment based on machine learning is not high under the condition of insufficient labeled sample,a battlefield situation assessment model based on self-training semi-supervised learning is proposed.Based on the support vector machine(SVM)model which is suitable for classification under the condition of small samples,the self-training semi-supervised learning method is used to train the SVM model with unlabeled samples to improve the accuracy and generalization performance of the model.Experimental results show that the proposed model has a great improvement in the evaluation accuracy compared with the SVM model only using labeled samples under the condition of insufficient labeled samples.