CAJ | 학술논문

针对当前军用飞机 NPD（Noise-Power-Distance）数据集成过程中面临小样本、小范围及数据失真问题，给出基于范例推理监督的支持向量机预测方法。用支持向量机作为数据回归与预测模型，通过范例推理检索出与目标范例相似的 NPD 数据，用相似范例来指导 NPD 数据的回归与预测。提出基于坡度的相似性检索、检验及修正方法，成功将范例推理的监督作用与预测模型有机结合，降低预测模型对数据样本的敏感性及依赖性。实例表明，该方法经济可行，能提高回归及预测精度。
침대당전군용비궤 NPD（Noise-Power-Distance）수거집성과정중면림소양본、소범위급수거실진문제，급출기우범례추리감독적지지향량궤예측방법。용지지향량궤작위수거회귀여예측모형，통과범례추리검색출여목표범례상사적 NPD 수거，용상사범례래지도 NPD 수거적회귀여예측。제출기우파도적상사성검색、검험급수정방법，성공장범례추리적감독작용여예측모형유궤결합，강저예측모형대수거양본적민감성급의뢰성。실례표명，해방법경제가행，능제고회귀급예측정도。
A support vector machine prediction method based on the surveillance of case-based reasoning was presented,aiming at solving the problems of small sample,small range and data distortion during the military aircraft noise-power-distance (NPD)data integration.In the method,support vector machine was adopted as a regression and prediction model,and similar case was searched via case-based reasoning to supervise the process of regression and prediction.In the process,a method of comparability searching,checkout and revising based on gradient was put forward successfully to combine the case-based reasoning and prediction model,which reduces the sensitivity and dependence of the model on the data sample.An example indicates that the mothed is economical and effective,and will greatly improve the precision of regression and prediction.