To overcome the challenges of poor real-time performance,limited scalability,and low intelligence in conventional jamming pattern recognition methods,this paper proposes a method based on Wavelet Packet Decomposition(...To overcome the challenges of poor real-time performance,limited scalability,and low intelligence in conventional jamming pattern recognition methods,this paper proposes a method based on Wavelet Packet Decomposition(WPD)and enhanced deep learning techniques.In the proposed method,an agent at the receiver processes the received signal using WPD to generate an initial Spectrogram Waterfall(SW),which is subsequently segmented using a sliding window to serve as the input for the jamming recognition network.The network employs a bilateral filter to preprocess the input SW,thereby enhancing the edge features of the jamming signals.To extract abstract features,depthwise separable convolution is utilized instead of traditional convolution,thereby reducing the network’s parameter count and enhancing real-time performance.A pyramid pooling layer is integrated before the fully connected layer to enable the network to process input SW of varying sizes,thus enhancing scalability.During network training,adaptive moment estimation is employed as the optimizer,allowing the network to dynamically adjust the learning rate and accelerate convergence.A comprehensive comparison between the proposed jamming recognition network and six other models is conducted,along with Ablation Experiments(AE)based on numerical simulations.Simulation results demonstrate that the proposed method based on WPD and enhanced deep learning achieves high-precision recognition of various jamming patterns while maintaining a favorable balance among prediction accuracy,network complexity,and prediction time.展开更多
We investigate the diffractive paraxial wave equation with an external potential,utilizing self-similarity and variable separation methods.The exact solution to this evolution equation,expressed through Scorer functio...We investigate the diffractive paraxial wave equation with an external potential,utilizing self-similarity and variable separation methods.The exact solution to this evolution equation,expressed through Scorer functions,gives rise to the new Scorer beams.We explore the dynamics of counterpropagating Scorer beams,as promising optical wave packets,focusing on their compression behavior.The Scorer beams are characterized by two key parameters:the attenuation factor and the initial pulse width.By appropriately adjusting these parameters,significant beam compression can be achieved.Specifically,increasing the attenuation factor enhances compression and raises pulse amplitude,while reducing the initial pulse width further amplifies these effects.Along the way,we observe interesting interference patterns of the counterpropagating Scorer beams that have never been seen before.This study introduces a novel approach to beam compression and opens new possibilities for practical applications of Scorer beams.展开更多
Accurate forecasting of electricity spot prices is crucial for market participants in formulating bidding strategies.However,the extreme volatility of electricity spot prices,influenced by various factors,poses signif...Accurate forecasting of electricity spot prices is crucial for market participants in formulating bidding strategies.However,the extreme volatility of electricity spot prices,influenced by various factors,poses significant challenges for forecasting.To address the data uncertainty of electricity prices and effectively mitigate gradient issues,overfitting,and computational challenges associated with using a single model during forecasting,this paper proposes a framework for forecasting spot market electricity prices by integrating wavelet packet decomposition(WPD)with a hybrid deep neural network.By ensuring accurate data decomposition,the WPD algorithm aids in detecting fluctuating patterns and isolating random noise.The hybrid model integrates temporal convolutional networks(TCN)and long short-term memory(LSTM)networks to enhance feature extraction and improve forecasting performance.Compared to other techniques,it significantly reduces average errors,decreasing mean absolute error(MAE)by 27.3%,root mean square error(RMSE)by 66.9%,and mean absolute percentage error(MAPE)by 22.8%.This framework effectively captures the intricate fluctuations present in the time series,resulting in more accurate and reliable predictions.展开更多
We present a fully time-dependent quantum wave packet evolution method for investigating molecular dynamics in intense laser fields.This approach enables the simultaneous treatment of interactions among multiple elect...We present a fully time-dependent quantum wave packet evolution method for investigating molecular dynamics in intense laser fields.This approach enables the simultaneous treatment of interactions among multiple electronic states while simultaneously tracking their time-dependent electronic,vibrational,and rotational dynamics.As an illustrative example,we consider neutral H_(2)molecules and simulate the laser-induced excitation dynamics of electronic and rotational states in strong laser fields,quantitatively distinguishing the respective contributions of electronic dipole transitions(within the classical-field approximation)and non-resonant Raman processes to the overall molecular dynamics.Furthermore,we precisely evaluate the relative contributions of direct tunneling ionization from the ground state and ionization following electronic excitation in the strong-field ionization of H_(2).The developed methodology shows strong potential for performing high-precision theoretical simulations of electronic-vibrational-rotational state excitations,ionization,and dissociation dynamics in molecules and their ions under intense laser fields.展开更多
The state equation and observation equation of the structural dynamic systems under various analysis scales are derived based on wavelet packet analysis. The time-frequency properties of structural dynamic response un...The state equation and observation equation of the structural dynamic systems under various analysis scales are derived based on wavelet packet analysis. The time-frequency properties of structural dynamic response under various scales are further formulated. The theoretical analysis results reveal that the wavelet packet energy spectrum （WPES） obtained from wavelet packet decomposition of structural dynamic response will detect the presence of structural damage. The sensitivity analysis of the WPES to structural damage and measurement noise is also performed. The transfer properties of the structural system matrix and the observation noise under various analysis scales are formulated, which verify the damage alarming reliability using the proposed WPES with preferable damage sensitivity and noise robusticity.展开更多
基金supported by National Natural Science Foundation of China under Grant U23A20279China Electronics Tian’ao Innovation Theory and Technology Group Fund under Grand 20221193-04-04.
文摘To overcome the challenges of poor real-time performance,limited scalability,and low intelligence in conventional jamming pattern recognition methods,this paper proposes a method based on Wavelet Packet Decomposition(WPD)and enhanced deep learning techniques.In the proposed method,an agent at the receiver processes the received signal using WPD to generate an initial Spectrogram Waterfall(SW),which is subsequently segmented using a sliding window to serve as the input for the jamming recognition network.The network employs a bilateral filter to preprocess the input SW,thereby enhancing the edge features of the jamming signals.To extract abstract features,depthwise separable convolution is utilized instead of traditional convolution,thereby reducing the network’s parameter count and enhancing real-time performance.A pyramid pooling layer is integrated before the fully connected layer to enable the network to process input SW of varying sizes,thus enhancing scalability.During network training,adaptive moment estimation is employed as the optimizer,allowing the network to dynamically adjust the learning rate and accelerate convergence.A comprehensive comparison between the proposed jamming recognition network and six other models is conducted,along with Ablation Experiments(AE)based on numerical simulations.Simulation results demonstrate that the proposed method based on WPD and enhanced deep learning achieves high-precision recognition of various jamming patterns while maintaining a favorable balance among prediction accuracy,network complexity,and prediction time.
基金supported by the National Natural Science Foundation of China under Grant No.62275176the Natural Science Foundation of Guangdong Province,China,under Grant No.2022A1515010084+1 种基金by Key Projects of Basic Research and Applied Basic Research in Universities of Guangdong Province,China,under Grants Nos.2021ZDZX1118 and 2022ZDZX1079supported by the NPRP 13S-0121-200126 Project with the Qatar National Research Fund(a member of the Qatar Foundation).
文摘We investigate the diffractive paraxial wave equation with an external potential,utilizing self-similarity and variable separation methods.The exact solution to this evolution equation,expressed through Scorer functions,gives rise to the new Scorer beams.We explore the dynamics of counterpropagating Scorer beams,as promising optical wave packets,focusing on their compression behavior.The Scorer beams are characterized by two key parameters:the attenuation factor and the initial pulse width.By appropriately adjusting these parameters,significant beam compression can be achieved.Specifically,increasing the attenuation factor enhances compression and raises pulse amplitude,while reducing the initial pulse width further amplifies these effects.Along the way,we observe interesting interference patterns of the counterpropagating Scorer beams that have never been seen before.This study introduces a novel approach to beam compression and opens new possibilities for practical applications of Scorer beams.
基金partially supported by projects funded by the National Key R&D Program of China(2022YFB2403000)the State Grid Corporation of China Science and Technology Project(522722230034).
文摘Accurate forecasting of electricity spot prices is crucial for market participants in formulating bidding strategies.However,the extreme volatility of electricity spot prices,influenced by various factors,poses significant challenges for forecasting.To address the data uncertainty of electricity prices and effectively mitigate gradient issues,overfitting,and computational challenges associated with using a single model during forecasting,this paper proposes a framework for forecasting spot market electricity prices by integrating wavelet packet decomposition(WPD)with a hybrid deep neural network.By ensuring accurate data decomposition,the WPD algorithm aids in detecting fluctuating patterns and isolating random noise.The hybrid model integrates temporal convolutional networks(TCN)and long short-term memory(LSTM)networks to enhance feature extraction and improve forecasting performance.Compared to other techniques,it significantly reduces average errors,decreasing mean absolute error(MAE)by 27.3%,root mean square error(RMSE)by 66.9%,and mean absolute percentage error(MAPE)by 22.8%.This framework effectively captures the intricate fluctuations present in the time series,resulting in more accurate and reliable predictions.
基金supported by the National Key Research and Development Program of China(Grant No.2022YFA1602502)the National Natural Science Foundation of China(Grant No.12450404)。
文摘We present a fully time-dependent quantum wave packet evolution method for investigating molecular dynamics in intense laser fields.This approach enables the simultaneous treatment of interactions among multiple electronic states while simultaneously tracking their time-dependent electronic,vibrational,and rotational dynamics.As an illustrative example,we consider neutral H_(2)molecules and simulate the laser-induced excitation dynamics of electronic and rotational states in strong laser fields,quantitatively distinguishing the respective contributions of electronic dipole transitions(within the classical-field approximation)and non-resonant Raman processes to the overall molecular dynamics.Furthermore,we precisely evaluate the relative contributions of direct tunneling ionization from the ground state and ionization following electronic excitation in the strong-field ionization of H_(2).The developed methodology shows strong potential for performing high-precision theoretical simulations of electronic-vibrational-rotational state excitations,ionization,and dissociation dynamics in molecules and their ions under intense laser fields.
文摘The state equation and observation equation of the structural dynamic systems under various analysis scales are derived based on wavelet packet analysis. The time-frequency properties of structural dynamic response under various scales are further formulated. The theoretical analysis results reveal that the wavelet packet energy spectrum （WPES） obtained from wavelet packet decomposition of structural dynamic response will detect the presence of structural damage. The sensitivity analysis of the WPES to structural damage and measurement noise is also performed. The transfer properties of the structural system matrix and the observation noise under various analysis scales are formulated, which verify the damage alarming reliability using the proposed WPES with preferable damage sensitivity and noise robusticity.
