针对现有多维时间序列数据(multivariate time series,MTS)预测中变量间依赖关系捕获能力不足和时间序列数据多通道信息利用不充分的问题,提出一种融合双注意力机制的多维时间序列预测模型(feature fusion and dual attention mechanism...针对现有多维时间序列数据(multivariate time series,MTS)预测中变量间依赖关系捕获能力不足和时间序列数据多通道信息利用不充分的问题,提出一种融合双注意力机制的多维时间序列预测模型(feature fusion and dual attention mechanism based GNN,FFDA-GNN)。该模型将图神经网络与空间注意力机制融合,用于增强多变量之间依赖关系捕获能力;利用并行的多层膨胀卷积和通道注意力机制,对时间序列数据进行多通道的特征提取,实现对时间序列数据多通道信息的充分利用,从而提升预测性能。在经济、电力、交通3个领域数据集上与基准模型进行对比实验,该模型预测精度优于其他基准方法,有良好的可行性。展开更多
现有的多变量灰色预测模型的背景值估计误差及模型结构单一是导致该模型预测性能不稳定的重要因素,致使该模型在实际预测领域中应用并不广泛.本文通过分析背景值函数的几何意义,结合积分几何面积公式,提出一种改进的背景值优化方法,使...现有的多变量灰色预测模型的背景值估计误差及模型结构单一是导致该模型预测性能不稳定的重要因素,致使该模型在实际预测领域中应用并不广泛.本文通过分析背景值函数的几何意义,结合积分几何面积公式,提出一种改进的背景值优化方法,使预测模型在背景值系数的选取上更加灵活.在此基础上,模型中加入灰色作用量,提出一种改进背景值及结构相容性的多维灰色预测模型(Improved background value and structure compatibility of grey prediction model,IBSGM(1,N)).通过对模型参数的改变分析,新模型理论上可达到与传统单变量和多变量灰色预测模型的兼容性.为检验新模型的性能,本文进行了三个案例对比分析,实验结果表明,与现有的灰色预测模型(Grey model,GM)GM(1,1)和GM(1,N)相比较,所提出的IBSGM(1,N)模型在背景值参数估计上误差明显减小,结构相容性更强,泛化性能更好,具有更高的预测精度.展开更多
A model of transmembrane helices of dopamine D2 receptor was constructed using the X ray coordinates of bacteriorhodopsin (BR) as a template. Based on the results from the model and the site directed mutagenesis exp...A model of transmembrane helices of dopamine D2 receptor was constructed using the X ray coordinates of bacteriorhodopsin (BR) as a template. Based on the results from the model and the site directed mutagenesis experience, the binding pocket, including nine amino acid residues beside indispensable Asp86, Ser141 and Ser144 residues, was defined. In order to testify the 3D structure of dopamine D2 receptor and specially test the binding sites, two sets of D2 receptor agonists (one was rigid and the other flexible) were selected for docking. A good result of correlation between logIC 50 and binding energy E b indicates that the predicted model is reliable for the investigation of the receptor ligand interaction and design of new active molecules.展开更多
Structure-stratigraphy analysis" is a new method used in the study and prediction of and small-scaled structures in coal mines. The object of this method is coalbed structure that includes the folds and fracture ...Structure-stratigraphy analysis" is a new method used in the study and prediction of and small-scaled structures in coal mines. The object of this method is coalbed structure that includes the folds and fracture occurred in the vicinity of coal-seams. It emphases the analysis on the relationship between structural deformation and stratal lithologic combination.Based on the statistics of a series of related parameters in stratigraphy and structure,comprehensive analysis and drawing, this method may provide a good means for the quantitative evaluation and prediction of small scale structure in coal mines.展开更多
文摘针对现有多维时间序列数据(multivariate time series,MTS)预测中变量间依赖关系捕获能力不足和时间序列数据多通道信息利用不充分的问题,提出一种融合双注意力机制的多维时间序列预测模型(feature fusion and dual attention mechanism based GNN,FFDA-GNN)。该模型将图神经网络与空间注意力机制融合,用于增强多变量之间依赖关系捕获能力;利用并行的多层膨胀卷积和通道注意力机制,对时间序列数据进行多通道的特征提取,实现对时间序列数据多通道信息的充分利用,从而提升预测性能。在经济、电力、交通3个领域数据集上与基准模型进行对比实验,该模型预测精度优于其他基准方法,有良好的可行性。
文摘现有的多变量灰色预测模型的背景值估计误差及模型结构单一是导致该模型预测性能不稳定的重要因素,致使该模型在实际预测领域中应用并不广泛.本文通过分析背景值函数的几何意义,结合积分几何面积公式,提出一种改进的背景值优化方法,使预测模型在背景值系数的选取上更加灵活.在此基础上,模型中加入灰色作用量,提出一种改进背景值及结构相容性的多维灰色预测模型(Improved background value and structure compatibility of grey prediction model,IBSGM(1,N)).通过对模型参数的改变分析,新模型理论上可达到与传统单变量和多变量灰色预测模型的兼容性.为检验新模型的性能,本文进行了三个案例对比分析,实验结果表明,与现有的灰色预测模型(Grey model,GM)GM(1,1)和GM(1,N)相比较,所提出的IBSGM(1,N)模型在背景值参数估计上误差明显减小,结构相容性更强,泛化性能更好,具有更高的预测精度.
文摘A model of transmembrane helices of dopamine D2 receptor was constructed using the X ray coordinates of bacteriorhodopsin (BR) as a template. Based on the results from the model and the site directed mutagenesis experience, the binding pocket, including nine amino acid residues beside indispensable Asp86, Ser141 and Ser144 residues, was defined. In order to testify the 3D structure of dopamine D2 receptor and specially test the binding sites, two sets of D2 receptor agonists (one was rigid and the other flexible) were selected for docking. A good result of correlation between logIC 50 and binding energy E b indicates that the predicted model is reliable for the investigation of the receptor ligand interaction and design of new active molecules.
文摘Structure-stratigraphy analysis" is a new method used in the study and prediction of and small-scaled structures in coal mines. The object of this method is coalbed structure that includes the folds and fracture occurred in the vicinity of coal-seams. It emphases the analysis on the relationship between structural deformation and stratal lithologic combination.Based on the statistics of a series of related parameters in stratigraphy and structure,comprehensive analysis and drawing, this method may provide a good means for the quantitative evaluation and prediction of small scale structure in coal mines.
