To improve the prediction accuracy of chaotic time series and reconstruct a more reasonable phase space structure of the prediction network,we propose a convolutional neural network-long short-term memory(CNN-LSTM)pre...To improve the prediction accuracy of chaotic time series and reconstruct a more reasonable phase space structure of the prediction network,we propose a convolutional neural network-long short-term memory(CNN-LSTM)prediction model based on the incremental attention mechanism.Firstly,a traversal search is conducted through the traversal layer for finite parameters in the phase space.Then,an incremental attention layer is utilized for parameter judgment based on the dimension weight criteria(DWC).The phase space parameters that best meet DWC are selected and fed into the input layer.Finally,the constructed CNN-LSTM network extracts spatio-temporal features and provides the final prediction results.The model is verified using Logistic,Lorenz,and sunspot chaotic time series,and the performance is compared from the two dimensions of prediction accuracy and network phase space structure.Additionally,the CNN-LSTM network based on incremental attention is compared with long short-term memory(LSTM),convolutional neural network(CNN),recurrent neural network(RNN),and support vector regression(SVR)for prediction accuracy.The experiment results indicate that the proposed composite network model possesses enhanced capability in extracting temporal features and achieves higher prediction accuracy.Also,the algorithm to estimate the phase space parameter is compared with the traditional CAO,false nearest neighbor,and C-C,three typical methods for determining the chaotic phase space parameters.The experiments reveal that the phase space parameter estimation algorithm based on the incremental attention mechanism is superior in prediction accuracy compared with the traditional phase space reconstruction method in five networks,including CNN-LSTM,LSTM,CNN,RNN,and SVR.展开更多
Irregular phase-space orbits of the electrons are harmful to the electron-beam transport quality and hence deteriorate the performance of a free-electron laser （FEL）. In previous literature, it was demonstrated that...Irregular phase-space orbits of the electrons are harmful to the electron-beam transport quality and hence deteriorate the performance of a free-electron laser （FEL）. In previous literature, it was demonstrated that the irregularity of the electron phase-space orbits could be caused in several ways, such as varying the wiggler amplitude and inducing sidebands. Based on a Hamiltonian model with a set of self-consistent differential equations, it is shown in this paper that the electron- beam normalized plasma frequency functions not only couple the electron motion with the FEL wave, which results in the evolution of the FEL wave field and a possible power saturation at a large beam current, but also cause the irregularity of the electron phase-space orbits when the normalized plasma frequency has a sufficiently large value, even if the initial energy of the electron is equal to the synchronous energy or the FEL wave does not reach power saturation.展开更多
Space satellite observations in an electron phase-space hole(electron hole) have shown that bipolar structures are discovered at the parallel cut of parallel electric field, while unipolar structures spring from the p...Space satellite observations in an electron phase-space hole(electron hole) have shown that bipolar structures are discovered at the parallel cut of parallel electric field, while unipolar structures spring from the parallel cut of perpendicular electric field. Particle-in-cell(PIC) simulations have demonstrated that the electron bi-stream instability induces several electron holes during its nonlinear evolution. However, how the unipolar structure of the parallel cut of the perpendicular electric field formed in these electron holes is still an unsolved problem,especially in a strongly magnetized plasma(Ω_e >ω_(pe), where Ω_e is defined as electron gyrofrequency and ω_(pe) is defined as plasma frequency, respectively). In this paper, with two-dimensional(2D) electrostatic PIC simulations, the evolution of the electron two-stream instability with a finite width in strongly magnetized plasma is investigated. Initially, those conditions lead to monochromatic electrostatic waves, and these waves coalesce with each other during their nonlinear evolution. At last, a solitary electrostatic structure is formed. In such an electron hole, a bipolar structure is formed in the parallel cut. of parallel electric field, while a unipolar structure presents in the parallel cut of perpendicular electric field.展开更多
针对正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)通信系统中存在的信息安全传输问题,提出了一种双重混沌加密安全传输方案。第一重加密为利用混沌加密矩阵对信号星座图进行置乱,其中混沌加密矩阵由复合离散混沌序...针对正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)通信系统中存在的信息安全传输问题,提出了一种双重混沌加密安全传输方案。第一重加密为利用混沌加密矩阵对信号星座图进行置乱,其中混沌加密矩阵由复合离散混沌序列作用到三层神经网络得到;第二重加密为利用复合离散混沌序列控制相位旋转因子对经过离散傅里叶逆变换后的信号进行相位旋转。仿真结果表明,采用所提出的双重加密方案进行传输,合作接收方的误码率低于不采用加密的OFDM系统和只采用第一重加密方案的OFDM系统,非合作方的误码率始终保持在0.5左右,密钥空间为2^(311),使系统具有较好的安全性能。展开更多
文摘To improve the prediction accuracy of chaotic time series and reconstruct a more reasonable phase space structure of the prediction network,we propose a convolutional neural network-long short-term memory(CNN-LSTM)prediction model based on the incremental attention mechanism.Firstly,a traversal search is conducted through the traversal layer for finite parameters in the phase space.Then,an incremental attention layer is utilized for parameter judgment based on the dimension weight criteria(DWC).The phase space parameters that best meet DWC are selected and fed into the input layer.Finally,the constructed CNN-LSTM network extracts spatio-temporal features and provides the final prediction results.The model is verified using Logistic,Lorenz,and sunspot chaotic time series,and the performance is compared from the two dimensions of prediction accuracy and network phase space structure.Additionally,the CNN-LSTM network based on incremental attention is compared with long short-term memory(LSTM),convolutional neural network(CNN),recurrent neural network(RNN),and support vector regression(SVR)for prediction accuracy.The experiment results indicate that the proposed composite network model possesses enhanced capability in extracting temporal features and achieves higher prediction accuracy.Also,the algorithm to estimate the phase space parameter is compared with the traditional CAO,false nearest neighbor,and C-C,three typical methods for determining the chaotic phase space parameters.The experiments reveal that the phase space parameter estimation algorithm based on the incremental attention mechanism is superior in prediction accuracy compared with the traditional phase space reconstruction method in five networks,including CNN-LSTM,LSTM,CNN,RNN,and SVR.
基金Project supported by the Science Foundation of Department of Education of Sichuan Province,China (Grant No.12233454)the Youth Foundation of Department of Education of Sichuan Province,China (Grant No.10ZB080)the Xihua University Foundation,China (Grant No.Z0913306)
文摘Irregular phase-space orbits of the electrons are harmful to the electron-beam transport quality and hence deteriorate the performance of a free-electron laser （FEL）. In previous literature, it was demonstrated that the irregularity of the electron phase-space orbits could be caused in several ways, such as varying the wiggler amplitude and inducing sidebands. Based on a Hamiltonian model with a set of self-consistent differential equations, it is shown in this paper that the electron- beam normalized plasma frequency functions not only couple the electron motion with the FEL wave, which results in the evolution of the FEL wave field and a possible power saturation at a large beam current, but also cause the irregularity of the electron phase-space orbits when the normalized plasma frequency has a sufficiently large value, even if the initial energy of the electron is equal to the synchronous energy or the FEL wave does not reach power saturation.
基金Supported by the National Science Foundation of China(41474125,41331067,41421063)973 Program(2013CBA01503)Key Research Program of Frontier Sciences,CAS(QYZDJ-SSW-DQC010)
文摘Space satellite observations in an electron phase-space hole(electron hole) have shown that bipolar structures are discovered at the parallel cut of parallel electric field, while unipolar structures spring from the parallel cut of perpendicular electric field. Particle-in-cell(PIC) simulations have demonstrated that the electron bi-stream instability induces several electron holes during its nonlinear evolution. However, how the unipolar structure of the parallel cut of the perpendicular electric field formed in these electron holes is still an unsolved problem,especially in a strongly magnetized plasma(Ω_e >ω_(pe), where Ω_e is defined as electron gyrofrequency and ω_(pe) is defined as plasma frequency, respectively). In this paper, with two-dimensional(2D) electrostatic PIC simulations, the evolution of the electron two-stream instability with a finite width in strongly magnetized plasma is investigated. Initially, those conditions lead to monochromatic electrostatic waves, and these waves coalesce with each other during their nonlinear evolution. At last, a solitary electrostatic structure is formed. In such an electron hole, a bipolar structure is formed in the parallel cut. of parallel electric field, while a unipolar structure presents in the parallel cut of perpendicular electric field.
文摘针对正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)通信系统中存在的信息安全传输问题,提出了一种双重混沌加密安全传输方案。第一重加密为利用混沌加密矩阵对信号星座图进行置乱,其中混沌加密矩阵由复合离散混沌序列作用到三层神经网络得到;第二重加密为利用复合离散混沌序列控制相位旋转因子对经过离散傅里叶逆变换后的信号进行相位旋转。仿真结果表明,采用所提出的双重加密方案进行传输,合作接收方的误码率低于不采用加密的OFDM系统和只采用第一重加密方案的OFDM系统,非合作方的误码率始终保持在0.5左右,密钥空间为2^(311),使系统具有较好的安全性能。
