How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market.Deep reinforcement learning,which has recently been used to develop tradi...How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market.Deep reinforcement learning,which has recently been used to develop trading strategies by automatically extracting complex features from a large amount of data,is struggling to deal with fastchanging markets due to sample inefficiency.This paper applies the meta-reinforcement learning method to tackle the trading challenges faced by conventional reinforcement learning(RL)approaches in non-stationary markets for the first time.In our work,the history trading data is divided into multiple task data and for each of these data themarket condition is relatively stationary.Then amodel agnosticmeta-learning(MAML)-based tradingmethod involving a meta-learner and a normal learner is proposed.A trading policy is learned by the meta-learner across multiple task data,which is then fine-tuned by the normal learner through a small amount of data from a new market task before trading in it.To improve the adaptability of the MAML-based method,an ordered multiplestep updating mechanism is also proposed to explore the changing dynamic within a task market.The simulation results demonstrate that the proposed MAML-based trading methods can increase the annualized return rate by approximately 180%,200%,and 160%,increase the Sharpe ratio by 180%,90%,and 170%,and decrease the maximum drawdown by 30%,20%,and 40%,compared to the traditional RL approach in three stock index future markets,respectively.展开更多
To address the challenges of video copyright protection and ensure the perfect recovery of original video,we propose a dual-domain watermarking scheme for digital video,inspired by Robust Reversible Watermarking(RRW)t...To address the challenges of video copyright protection and ensure the perfect recovery of original video,we propose a dual-domain watermarking scheme for digital video,inspired by Robust Reversible Watermarking(RRW)technology used in digital images.Our approach introduces a parameter optimization strategy that incre-mentally adjusts scheme parameters through attack simulation fitting,allowing for adaptive tuning of experimental parameters.In this scheme,the low-frequency Polar Harmonic Transform(PHT)moment is utilized as the embedding domain for robust watermarking,enhancing stability against simulation attacks while implementing the parameter optimization strategy.Through extensive attack simulations across various digital videos,we identify the optimal low-frequency PHT moment using adaptive normalization.Subsequently,the embedding parameters for robust watermarking are adaptively adjusted to maximize robustness.To address computational efficiency and practical requirements,the unnormalized high-frequency PHT moment is selected as the embedding domain for reversible watermarking.We optimize the traditional single-stage extended transform dithering modulation(STDM)to facilitate multi-stage embedding in the dual-domain watermarking process.In practice,the video embedded with a robust watermark serves as the candidate video.This candidate video undergoes simulation according to the parameter optimization strategy to balance robustness and embedding capacity,with adaptive determination of embedding strength.The reversible watermarking is formed by combining errors and other information,utilizing recursive coding technology to ensure reversibility without attacks.Comprehensive analyses of multiple performance indicators demonstrate that our scheme exhibits strong robustness against Common Signal Processing(CSP)and Geometric Deformation(GD)attacks,outperforming other advanced video watermarking algorithms under similar conditions of invisibility,reversibility,and embedding capacity.This underscores the effectiveness and feasibility of our attack simulation fitting strategy.展开更多
The single-pixel imaging(SPI) technique is able to capture two-dimensional(2 D) images without conventional array sensors by using a photodiode. As a novel scheme, Fourier single-pixel imaging(FSI) has been proven cap...The single-pixel imaging(SPI) technique is able to capture two-dimensional(2 D) images without conventional array sensors by using a photodiode. As a novel scheme, Fourier single-pixel imaging(FSI) has been proven capable of reconstructing high-quality images. Due to the fact that the Fourier basis patterns(also known as grayscale sinusoidal patterns)cannot be well displayed on the digital micromirror device(DMD), a fast FSI system is proposed to solve this problem by binarizing Fourier pattern through a dithering algorithm. However, the traditional dithering algorithm leads to low quality as the extra noise is inevitably induced in the reconstructed images. In this paper, we report a better dithering algorithm to binarize Fourier pattern, which utilizes the Sierra–Lite kernel function by a serpentine scanning method. Numerical simulation and experiment demonstrate that the proposed algorithm is able to achieve higher quality under different sampling ratios.展开更多
Dithering optimization techniques can be divided into the phase-optimized technique and the intensity-optimized technique. The problem with the former is the poor sensitivity to various defocusing amounts, and the pro...Dithering optimization techniques can be divided into the phase-optimized technique and the intensity-optimized technique. The problem with the former is the poor sensitivity to various defocusing amounts, and the problem with the latter is that it cannot enhance phase quality directly nor efficiently. In this paper, we present a multi-objective optimization framework for three-dimensional(3D) measurement by utilizing binary defocusing technique. Moreover, a binary patch optimization technique is used to solve the time-consuming issue of genetic algorithm. It is demonstrated that the presented technique consistently obtains significant phase performance improvement under various defocusing amounts.展开更多
文摘How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market.Deep reinforcement learning,which has recently been used to develop trading strategies by automatically extracting complex features from a large amount of data,is struggling to deal with fastchanging markets due to sample inefficiency.This paper applies the meta-reinforcement learning method to tackle the trading challenges faced by conventional reinforcement learning(RL)approaches in non-stationary markets for the first time.In our work,the history trading data is divided into multiple task data and for each of these data themarket condition is relatively stationary.Then amodel agnosticmeta-learning(MAML)-based tradingmethod involving a meta-learner and a normal learner is proposed.A trading policy is learned by the meta-learner across multiple task data,which is then fine-tuned by the normal learner through a small amount of data from a new market task before trading in it.To improve the adaptability of the MAML-based method,an ordered multiplestep updating mechanism is also proposed to explore the changing dynamic within a task market.The simulation results demonstrate that the proposed MAML-based trading methods can increase the annualized return rate by approximately 180%,200%,and 160%,increase the Sharpe ratio by 180%,90%,and 170%,and decrease the maximum drawdown by 30%,20%,and 40%,compared to the traditional RL approach in three stock index future markets,respectively.
基金supported in part by the National Natural Science Foundation of China under Grant 62202496,62272478the Basic Frontier Innovation Project of Engineering University of People Armed Police under Grant WJY202314,WJY202221.
文摘To address the challenges of video copyright protection and ensure the perfect recovery of original video,we propose a dual-domain watermarking scheme for digital video,inspired by Robust Reversible Watermarking(RRW)technology used in digital images.Our approach introduces a parameter optimization strategy that incre-mentally adjusts scheme parameters through attack simulation fitting,allowing for adaptive tuning of experimental parameters.In this scheme,the low-frequency Polar Harmonic Transform(PHT)moment is utilized as the embedding domain for robust watermarking,enhancing stability against simulation attacks while implementing the parameter optimization strategy.Through extensive attack simulations across various digital videos,we identify the optimal low-frequency PHT moment using adaptive normalization.Subsequently,the embedding parameters for robust watermarking are adaptively adjusted to maximize robustness.To address computational efficiency and practical requirements,the unnormalized high-frequency PHT moment is selected as the embedding domain for reversible watermarking.We optimize the traditional single-stage extended transform dithering modulation(STDM)to facilitate multi-stage embedding in the dual-domain watermarking process.In practice,the video embedded with a robust watermark serves as the candidate video.This candidate video undergoes simulation according to the parameter optimization strategy to balance robustness and embedding capacity,with adaptive determination of embedding strength.The reversible watermarking is formed by combining errors and other information,utilizing recursive coding technology to ensure reversibility without attacks.Comprehensive analyses of multiple performance indicators demonstrate that our scheme exhibits strong robustness against Common Signal Processing(CSP)and Geometric Deformation(GD)attacks,outperforming other advanced video watermarking algorithms under similar conditions of invisibility,reversibility,and embedding capacity.This underscores the effectiveness and feasibility of our attack simulation fitting strategy.
基金Project supported by the National Natural Science Foundation of China(Grant No.61271376)the Anhui Provincial Natural Science Foundation,China(Grant No.1208085MF114)
文摘The single-pixel imaging(SPI) technique is able to capture two-dimensional(2 D) images without conventional array sensors by using a photodiode. As a novel scheme, Fourier single-pixel imaging(FSI) has been proven capable of reconstructing high-quality images. Due to the fact that the Fourier basis patterns(also known as grayscale sinusoidal patterns)cannot be well displayed on the digital micromirror device(DMD), a fast FSI system is proposed to solve this problem by binarizing Fourier pattern through a dithering algorithm. However, the traditional dithering algorithm leads to low quality as the extra noise is inevitably induced in the reconstructed images. In this paper, we report a better dithering algorithm to binarize Fourier pattern, which utilizes the Sierra–Lite kernel function by a serpentine scanning method. Numerical simulation and experiment demonstrate that the proposed algorithm is able to achieve higher quality under different sampling ratios.
基金Project supported by the Zhejiang Provincial Welfare Technology Applied Research Project,China(Grant No.2017C31080)
文摘Dithering optimization techniques can be divided into the phase-optimized technique and the intensity-optimized technique. The problem with the former is the poor sensitivity to various defocusing amounts, and the problem with the latter is that it cannot enhance phase quality directly nor efficiently. In this paper, we present a multi-objective optimization framework for three-dimensional(3D) measurement by utilizing binary defocusing technique. Moreover, a binary patch optimization technique is used to solve the time-consuming issue of genetic algorithm. It is demonstrated that the presented technique consistently obtains significant phase performance improvement under various defocusing amounts.
