将预测模型用于更为苛刻的燃烧试验（例如烃类燃烧炉试验），随着预测模型置信度的增加所需的试验会更少。
The extension of the predictive model to cover more severe fire tests, such as the hydrocarbon furnace test, will require less testing as confidence in the predictive model grows.
然后创建一个模型，再将这个模型应用到目标值尚且未知的记录上，以产生一个预测和该预测的置信度值。
Then a model is created, that can later be applied to records for which the target value is not yet known, yielding a prediction and a confidence value for this prediction.
数值分析证明本文建立的模糊支撑向量机模型可根据数据置信度大小有效的控制各数据在学习机中的作用。
Numerical analysis testified that these fuzzy models can effectively control the influence of each sample on learning machine according to its confidence.
应用推荐