In multiple attribute group decision making (MAGDM) problems based on linguistic information, the granularities of linguistic label sets are usually different due to the differences of thinking modes and habits amon...In multiple attribute group decision making (MAGDM) problems based on linguistic information, the granularities of linguistic label sets are usually different due to the differences of thinking modes and habits among decision makers. In order to deal with this inconvenience, the transformation relationships among multigranular linguistic labels (TRMLLs), which are applied to unify linguistic labels with different granularities into a certain linguistic label set with fixed granularity, are presented in this paper. Furthermore, the reference tables are made according to TRMLLs so that the interrelated calculation will be less complicated, and the method of how to use them is explained in detail. At length, the TRMLLs are illustrated through an application example.展开更多
文章提出了一种波分复用(WDM)多粒度网络中的静态波带通道分配算法———平衡路由双向首次命中算法(BBFF,Bal-anced-routing-B id irectional-F irst-fit)。该算法旨在减少全网多粒度全光域光交叉连接器(MG-PXC)的端口数,降低网络成本...文章提出了一种波分复用(WDM)多粒度网络中的静态波带通道分配算法———平衡路由双向首次命中算法(BBFF,Bal-anced-routing-B id irectional-F irst-fit)。该算法旨在减少全网多粒度全光域光交叉连接器(MG-PXC)的端口数,降低网络成本和控制复杂度。算法在路由选择阶段尽量保证全网负载平衡;在波长分配阶段采用改进了的首次命中(FF)算法,减少了因配置零散波长通道而无法建立波带通道的可能。仿真结果表明,BBFF算法的两个特征,都有效地减少了MG-PXC的端口数,降低了网络成本。展开更多
微博文本特殊性的存在使得微博用户兴趣画像难以有效构建。为此,提出了一种集成算法--新词发现-双向长短期记忆网络-梯度提升算法。首先针对微博文本的非正式性,提出了一种基于支持度视角的新词发现(New Word Discovery, NWD)算法,发掘...微博文本特殊性的存在使得微博用户兴趣画像难以有效构建。为此,提出了一种集成算法--新词发现-双向长短期记忆网络-梯度提升算法。首先针对微博文本的非正式性,提出了一种基于支持度视角的新词发现(New Word Discovery, NWD)算法,发掘其中大量存在的网络用语以实现更加准确的分词及语义把握;其次,引入Simhash算法使得微博文本中的"信息过载"现象得到改观;再次,为改善微博文本的简洁性而引起的特征稀疏问题,采用双向长短期记忆网络(Bidirectional Long Short-term Memory,Bi-LSTM)模型提取博文语义特征;最后,通过融合微博用户静态特征训练梯度提升(extreme Gradient Boosting,XGBoost)模型,从而有效构建多粒度微博用户兴趣画像。实验结果表明,粗粒度(一级)兴趣标签模型NWD-Bi-LSTM和细粒度(二级)兴趣标签模型NWD-Bi-LSTM-XGBoost的宏平均F1值(Macroaverage F1 score, mF1)和受试者工作特征曲线下面积(Area Under ROC Crave, AUC)分别高达83.6%, 79.7%和70.4%,63.6%,相对于基准模型, NWD算法的集成使得模型的m F1值和AUC值均能提升3%~5%,其促进作用优于现有的新词发现方法。展开更多
基金supported by the National Science Fund for Distinguished Young Scholars of China (No.70625005)
文摘In multiple attribute group decision making (MAGDM) problems based on linguistic information, the granularities of linguistic label sets are usually different due to the differences of thinking modes and habits among decision makers. In order to deal with this inconvenience, the transformation relationships among multigranular linguistic labels (TRMLLs), which are applied to unify linguistic labels with different granularities into a certain linguistic label set with fixed granularity, are presented in this paper. Furthermore, the reference tables are made according to TRMLLs so that the interrelated calculation will be less complicated, and the method of how to use them is explained in detail. At length, the TRMLLs are illustrated through an application example.
文摘文章提出了一种波分复用(WDM)多粒度网络中的静态波带通道分配算法———平衡路由双向首次命中算法(BBFF,Bal-anced-routing-B id irectional-F irst-fit)。该算法旨在减少全网多粒度全光域光交叉连接器(MG-PXC)的端口数,降低网络成本和控制复杂度。算法在路由选择阶段尽量保证全网负载平衡;在波长分配阶段采用改进了的首次命中(FF)算法,减少了因配置零散波长通道而无法建立波带通道的可能。仿真结果表明,BBFF算法的两个特征,都有效地减少了MG-PXC的端口数,降低了网络成本。
文摘微博文本特殊性的存在使得微博用户兴趣画像难以有效构建。为此,提出了一种集成算法--新词发现-双向长短期记忆网络-梯度提升算法。首先针对微博文本的非正式性,提出了一种基于支持度视角的新词发现(New Word Discovery, NWD)算法,发掘其中大量存在的网络用语以实现更加准确的分词及语义把握;其次,引入Simhash算法使得微博文本中的"信息过载"现象得到改观;再次,为改善微博文本的简洁性而引起的特征稀疏问题,采用双向长短期记忆网络(Bidirectional Long Short-term Memory,Bi-LSTM)模型提取博文语义特征;最后,通过融合微博用户静态特征训练梯度提升(extreme Gradient Boosting,XGBoost)模型,从而有效构建多粒度微博用户兴趣画像。实验结果表明,粗粒度(一级)兴趣标签模型NWD-Bi-LSTM和细粒度(二级)兴趣标签模型NWD-Bi-LSTM-XGBoost的宏平均F1值(Macroaverage F1 score, mF1)和受试者工作特征曲线下面积(Area Under ROC Crave, AUC)分别高达83.6%, 79.7%和70.4%,63.6%,相对于基准模型, NWD算法的集成使得模型的m F1值和AUC值均能提升3%~5%,其促进作用优于现有的新词发现方法。