针对现有标签分布学习(Label Distribution Learning,LDL)算法较少考虑标签间关联性的问题,提出一种融合结构化标签依赖性的LDL算法.算法分为扩展、学习和恢复三个阶段:在扩展阶段,结合成对标签之间的关联性,构建结构化标签依赖性;在学...针对现有标签分布学习(Label Distribution Learning,LDL)算法较少考虑标签间关联性的问题,提出一种融合结构化标签依赖性的LDL算法.算法分为扩展、学习和恢复三个阶段:在扩展阶段,结合成对标签之间的关联性,构建结构化标签依赖性;在学习阶段,结合该依赖性,构建学习框架;在恢复阶段,利用最小二乘法求解超定方程组以预测标签分布.与七种常用的标签分布学习算法相比,在八个开放数据集上进行实验,提出的算法在Euclidean距离、Sørensen距离、Squardχ2距离、Kullback‐Leibler散度、Intersection相似度和Fidelity相似度六个主流评估指标上明显占优.展开更多
The problem of abnormal flight recovery has always been the focus and difficulty in the field of civil aviation,and has important research significance. According to the recovery strategy,characteristics,and constrain...The problem of abnormal flight recovery has always been the focus and difficulty in the field of civil aviation,and has important research significance. According to the recovery strategy,characteristics,and constraints of aircraft,aircrews and flights,this paper is based on the column generation algorithms. A mathematical optimization model for the integrated recovery of aircraft and aircrew in the case of temporary aircraft failures was established,and the corresponding solution algorithm was designed. At the same time,the influence of aircraft and aircrew on route selection was taken into account. Finally,the method of calling Cplex by Java was used. Part of the flight plan data actually operated by the company verifies the feasibility,accuracy and timeliness of the model and algorithm.展开更多
文摘针对现有标签分布学习(Label Distribution Learning,LDL)算法较少考虑标签间关联性的问题,提出一种融合结构化标签依赖性的LDL算法.算法分为扩展、学习和恢复三个阶段:在扩展阶段,结合成对标签之间的关联性,构建结构化标签依赖性;在学习阶段,结合该依赖性,构建学习框架;在恢复阶段,利用最小二乘法求解超定方程组以预测标签分布.与七种常用的标签分布学习算法相比,在八个开放数据集上进行实验,提出的算法在Euclidean距离、Sørensen距离、Squardχ2距离、Kullback‐Leibler散度、Intersection相似度和Fidelity相似度六个主流评估指标上明显占优.
文摘The problem of abnormal flight recovery has always been the focus and difficulty in the field of civil aviation,and has important research significance. According to the recovery strategy,characteristics,and constraints of aircraft,aircrews and flights,this paper is based on the column generation algorithms. A mathematical optimization model for the integrated recovery of aircraft and aircrew in the case of temporary aircraft failures was established,and the corresponding solution algorithm was designed. At the same time,the influence of aircraft and aircrew on route selection was taken into account. Finally,the method of calling Cplex by Java was used. Part of the flight plan data actually operated by the company verifies the feasibility,accuracy and timeliness of the model and algorithm.
