Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics s...Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt numbers.The results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.展开更多
Circuits with switched current are described by an admittance matrix and seeking current transfers then means calculating the ratio of algebraic supplements of this matrix. As there are also graph methods of circuit a...Circuits with switched current are described by an admittance matrix and seeking current transfers then means calculating the ratio of algebraic supplements of this matrix. As there are also graph methods of circuit analysis in addition to algebraic methods, it is clearly possible in theory to carry out an analysis of the whole switched circuit in two-phase switching exclusively by the graph method as well. For this purpose it is possible to plot a Mason graph of a circuit, use transformation graphs to reduce Mason graphs for all the four phases of switching, and then plot a summary graph from the transformed graphs obtained this way. First the author draws nodes and possible branches, obtained by transformation graphs for transfers of EE （even-even） and OO （odd-odd） phases. In the next step, branches obtained by transformation graphs for EO and OE phase are drawn between these nodes, while their resulting transfer is 1 multiplied by z^1/2. This summary graph is extended by two branches from input node and to output node, the extended graph can then be interpreted by the Mason＇s relation to provide transparent current transfers. Therefore it is not necessary to compose a sum admittance matrix and to express this consequently in numbers, and so it is possible to reach the final result in a graphical way.展开更多
目的:基于脑电(electroencephalogram,EEG)信号探究个体在不同情绪状态下大脑网络的功能连接变化情况,并根据全局图论指标量化分析脑功能网络属性的差异性变化。方法:在多模态情绪数据库(Database for Emotion Analysis Using Physiolog...目的:基于脑电(electroencephalogram,EEG)信号探究个体在不同情绪状态下大脑网络的功能连接变化情况,并根据全局图论指标量化分析脑功能网络属性的差异性变化。方法:在多模态情绪数据库(Database for Emotion Analysis Using Physiological Signals,DEAP)中提取平静状态(作为平静状态组)和压力状态(作为压力状态组)的EEG信号,并根据EEG信号的预处理过程划分Theta频段([4,8)Hz)、Alpha频段([8,13)Hz)、Beta频段([13,31)Hz)和Gamma频段([31,45)Hz)4个频段,计算每个频段的相位锁值(phase locking value,PLV),得到PLV脑网络矩阵,然后利用小世界属性、聚类系数、特征路径长度3种全局图论属性指标对PLV网络矩阵的属性进行拓扑结构分析。比较2组情绪状态的脑网络功能连接情况,并分析2组情绪状态的全局图论属性指标的差异性。采用SPSS 25.0软件进行统计学分析。结果:2组情绪状态的功能连接比较表明,4个频段不同脑区连通性差异有统计学意义(P<0.05)。与平静状态组相比,压力状态组在Gamma频段的小世界属性显著减小,在Alpha、Beta和Gamma频段的聚类系数和特征路径长度显著增大,差异有统计学意义(P<0.05);在Theta频段,压力状态组与平静状态组的全局图论属性指标相近,差异无统计学意义(P>0.05)。结论:该研究证实了个体不同情绪状态能够在大脑功能连接方面得到显著表征,小世界属性、聚类系数和特征路径长度3个全局图论属性指标可以作为情绪状态识别的关键特征参数,为情绪状态及情感相关的脑功能疾病的诊断治疗研究提供了理论依据。展开更多
基金Project supported by the National Natural Science Foundation of China(Grant No.11702289)the Key Core Technology and Generic Technology Research and Development Project of Shanxi Province,China(Grant No.2020XXX013)。
文摘Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt numbers.The results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.
文摘Circuits with switched current are described by an admittance matrix and seeking current transfers then means calculating the ratio of algebraic supplements of this matrix. As there are also graph methods of circuit analysis in addition to algebraic methods, it is clearly possible in theory to carry out an analysis of the whole switched circuit in two-phase switching exclusively by the graph method as well. For this purpose it is possible to plot a Mason graph of a circuit, use transformation graphs to reduce Mason graphs for all the four phases of switching, and then plot a summary graph from the transformed graphs obtained this way. First the author draws nodes and possible branches, obtained by transformation graphs for transfers of EE （even-even） and OO （odd-odd） phases. In the next step, branches obtained by transformation graphs for EO and OE phase are drawn between these nodes, while their resulting transfer is 1 multiplied by z^1/2. This summary graph is extended by two branches from input node and to output node, the extended graph can then be interpreted by the Mason＇s relation to provide transparent current transfers. Therefore it is not necessary to compose a sum admittance matrix and to express this consequently in numbers, and so it is possible to reach the final result in a graphical way.
文摘目的:基于脑电(electroencephalogram,EEG)信号探究个体在不同情绪状态下大脑网络的功能连接变化情况,并根据全局图论指标量化分析脑功能网络属性的差异性变化。方法:在多模态情绪数据库(Database for Emotion Analysis Using Physiological Signals,DEAP)中提取平静状态(作为平静状态组)和压力状态(作为压力状态组)的EEG信号,并根据EEG信号的预处理过程划分Theta频段([4,8)Hz)、Alpha频段([8,13)Hz)、Beta频段([13,31)Hz)和Gamma频段([31,45)Hz)4个频段,计算每个频段的相位锁值(phase locking value,PLV),得到PLV脑网络矩阵,然后利用小世界属性、聚类系数、特征路径长度3种全局图论属性指标对PLV网络矩阵的属性进行拓扑结构分析。比较2组情绪状态的脑网络功能连接情况,并分析2组情绪状态的全局图论属性指标的差异性。采用SPSS 25.0软件进行统计学分析。结果:2组情绪状态的功能连接比较表明,4个频段不同脑区连通性差异有统计学意义(P<0.05)。与平静状态组相比,压力状态组在Gamma频段的小世界属性显著减小,在Alpha、Beta和Gamma频段的聚类系数和特征路径长度显著增大,差异有统计学意义(P<0.05);在Theta频段,压力状态组与平静状态组的全局图论属性指标相近,差异无统计学意义(P>0.05)。结论:该研究证实了个体不同情绪状态能够在大脑功能连接方面得到显著表征,小世界属性、聚类系数和特征路径长度3个全局图论属性指标可以作为情绪状态识别的关键特征参数,为情绪状态及情感相关的脑功能疾病的诊断治疗研究提供了理论依据。
