Fast compressed sensing spectral measurement with adaptive gradient multiscale resolution

We propose a fast,adaptive multiscale resolution spectral measurement method based on compressed sensing.The method can apply variable measurement resolution over the entire spectral range to reduce the measurement time by over 75%compared to a global high-resolution measurement.Mimicking the characteristics of the human retina system,the resolution distribution follows the principle of gradually decreasing.The system allows the spectral peaks of interest to be captured dynamically or to be specified a priori by a user.The system was tested by measuring single and dual spectral peaks,and the results of spectral peaks are consistent with those of global high-resolution measurements.

Water Gauge Image Denoising Model Based on Improved Adaptive Total Variation

As an important part of water level warning in water conservancy projects,often due to the influence of environmental factors such as light and stains,the acquired water gauge images have sticky,broken and bright spot conditions,which affect the identification of water gauges.To solve this problem,a water gauge image denoising model based on improved adaptive total variation is proposed.Firstly,the regular term exponent in the adaptive total variational equation is changed to an inverse cosine function;secondly,the differential curvature is used to distinguish the image noise points and increase the smoothing strength at the noise points;finally,according to the characteristics of the gradient mode and adaptive gradient threshold after Gaussian filtering,the New model can adaptively denoise in the smooth area and protect the edge area,so as to have the characteristics of both edge-preserving denoising.The experimental results show that the new model has a great improvement in image vision,higher iteration efficiency and an average increase of 1.6 dB in peak signal-to-noise ratio,and an average increase of 9%in structural similarity,which is more beneficial to practical applications.

Training Generative Adversarial Networks with Adaptive Composite Gradient

The wide applications of Generative adversarial networks benefit from the successful training methods,guaranteeing that an object function converges to the local minimum.Nevertheless,designing an efficient and competitive training method is still a challenging task due to the cyclic behaviors of some gradient-based ways and the expensive computational cost of acquiring the Hessian matrix.To address this problem,we proposed the Adaptive Composite Gradients(ACG)method,linearly convergent in bilinear games under suitable settings.Theory analysis and toy-function experiments both suggest that our approach alleviates the cyclic behaviors and converges faster than recently proposed SOTA algorithms.The convergence speed of the ACG is improved by 33%than other methods.Our ACG method is a novel Semi-Gradient-Free algorithm that can reduce the computational cost of gradient and Hessian by utilizing the predictive information in future iterations.The mixture of Gaussians experiments and real-world digital image generative experiments show that our ACG method outperforms several existing technologies,illustrating the superiority and efficacy of our method.

Reversible Data Hiding in Encrypted Images Based on Adaptive Prediction and Labeling

Recently,reversible data hiding in encrypted images(RDHEI)based on pixel prediction has been a hot topic.However,existing schemes still employ a pixel predictor that ignores pixel changes in the diagonal direction during prediction,and the pixel labeling scheme is inflexible.To solve these problems,this paper proposes reversible data hiding in encrypted images based on adaptive prediction and labeling.First,we design an adaptive gradient prediction(AGP),which uses eight adjacent pixels and combines four scanning methods(i.e.,horizontal,vertical,diagonal,and diagonal)for prediction.AGP can adaptively adjust the weight of the linear prediction model according to the weight of the edge attribute of the pixel,which improves the prediction ability of the predictor for complex images.At the same time,we adopt an adaptive huffman coding labeling scheme,which can adaptively generate huffman codes for labeling according to different images,effectively improving the scheme’s embedding performance on the dataset.The experimental results show that the algorithm has a higher embedding rate.The embedding rate on the test image Jetplane is 4.2102 bpp,and the average embedding rate on the image dataset Bossbase is 3.8625 bpp.

Specht Triangle Approximation of Large Bending Isometries

We propose a Specht triangle discretization for a geometrically nonlinear Kirchhoff plate model with large bending isometry.A combination of an adaptive time-stepping gradient flow and a Newton’s method is employed to solve the ensuing nonlinear minimization problem.Γ−convergence of the Specht triangle discretization and the unconditional stability of the gradient flow algorithm are proved.We present several numerical examples to demonstrate that our approach significantly enhances both the computational efficiency and accuracy.

Reactive Navigation of Underwater Mobile Robot Using ANFIS Approach in a Manifold Manner

Learning and self-adaptation ability is highly required to be integrated in path planning algorithm for underwater robot during navigation through an unspecified underwater environment. High frequency oscillations during underwater motion are responsible for nonlinearities in dynamic behavior of underwater robot as well as uncertainties in hydrodynamic coefficients. Reactive behaviors of underwater robot are designed considering the position and orientation of both target and nearest obstacle from robot s current position. Human like reasoning power and approximation based learning skill of neural based adaptive fuzzy inference system（ANFIS）has been found to be effective for underwater multivariable motion control. More than one ANFIS models are used here for achieving goal and obstacle avoidance while avoiding local minima situation in both horizontal and vertical plane of three dimensional workspace.An error gradient approach based on input-output training patterns for learning purpose has been promoted to spawn trajectory of underwater robot optimizing path length as well as time taken. The simulation and experimental results endorse sturdiness and viability of the proposed method in comparison with other navigational methodologies to negotiate with hectic conditions during motion of underwater mobile robot.

Decision Model for Market of Performing Arts with Factorization Machine

Performing arts and movies have become commercial products with high profit and great market potential. Previous research works have developed comprehensive models to forecast the demand for movies. However,they did not pay enough attention to the decision support for performing arts which is a special category unlike movies. For performing arts with high-dimensional categorical attributes and limit samples, determining ticket prices in different levels is still a challenge job faced by the producers and distributors. In terms of these difficulties, factorization machine(FM), which can handle huge sparse categorical attributes, is used in this work first. Adaptive stochastic gradient descent(ASGD) and Markov chain Monte Carlo(MCMC) are both explored to estimate the model parameters of FM. FM with ASGD(FM-ASGD) and FM with MCMC(FM-MCMC) both can achieve a better prediction accuracy, compared with a traditional algorithm. In addition, the multi-output model is proposed to determine the price in multiple price levels simultaneously, which avoids the trouble of the models' repeating training. The results also confirm the prediction accuracy of the multi-output model, compared with those from the general single-output model.