针对领域适应学习(Domain adaptation learning,DAL)问题,提出一种核分布一致局部领域适应学习机(Kernel distribution consistency based local domaina daptation classifier,KDC-LDAC),在某个通用再生核Hilbert空间(Universally repr...针对领域适应学习(Domain adaptation learning,DAL)问题,提出一种核分布一致局部领域适应学习机(Kernel distribution consistency based local domaina daptation classifier,KDC-LDAC),在某个通用再生核Hilbert空间(Universally reproduced kernel Hilbert space,URKHS),基于结构风险最小化模型,KDC-LDAC首先学习一个核分布一致正则化支持向量机(Support vector machine,SVM),对目标数据进行初始划分;然后,基于核局部学习思想,对目标数据类别信息进行局部回归重构;最后,利用学习获得的类别信息,在目标领域训练学习一个适于目标判别的分类器.人造和实际数据集实验结果显示,所提方法具有优化或可比较的领域适应学习性能.展开更多
Necessity of reserves classification further is discussed based on the producing feasibility. It is pointed out that the reserves of oil reservoirs unplaced on development planning during the certain future periods sh...Necessity of reserves classification further is discussed based on the producing feasibility. It is pointed out that the reserves of oil reservoirs unplaced on development planning during the certain future periods shouldn’ t be classified. Recalculation of reserves in Nankenmaqi oilfield shows that calibrated recovery efficiency is very difficult to reach according to the former calculated reserves. During the calculation of recovery efficiency, it should be fully considered on fluid properties , reservoir physical properties, heterogeneity, energy in oil reservoir and production technologies.展开更多
文摘Necessity of reserves classification further is discussed based on the producing feasibility. It is pointed out that the reserves of oil reservoirs unplaced on development planning during the certain future periods shouldn’ t be classified. Recalculation of reserves in Nankenmaqi oilfield shows that calibrated recovery efficiency is very difficult to reach according to the former calculated reserves. During the calculation of recovery efficiency, it should be fully considered on fluid properties , reservoir physical properties, heterogeneity, energy in oil reservoir and production technologies.