提出了一种高阶混合正则化图像盲复原方法,用于实现模糊噪声图像的清晰化盲复原。根据自然图像边缘的稀疏特性,对图像的边缘细节成分进行了全变差(total variation TV)正则化约束,根据自然图像同性质平滑区域内像素值的变化规律,将一种...提出了一种高阶混合正则化图像盲复原方法,用于实现模糊噪声图像的清晰化盲复原。根据自然图像边缘的稀疏特性,对图像的边缘细节成分进行了全变差(total variation TV)正则化约束,根据自然图像同性质平滑区域内像素值的变化规律,将一种高阶的类Tikhonov正则化约束运用于图像的平滑区域中,提出了一种新的高阶混合正则化模型。最后,提出一种多变量分裂布雷格曼(Multi-variable Split Bregman MSB)最优化迭代策略对提出的模型进行最优化求解。实验结果表明,提出的方法能够很好地保护图像的边缘细节,同时有效地消除图像平滑区域内的阶梯和假边缘瑕疵。与近几年的一些较好的图像盲复原方法相比,本文方法的信噪比增量(increase of the signal to noise ratio ISNR)增加了0.03～2.5dB。展开更多
Conventional artificial neural networks used to solve electrical resistivity imaging （ERI） inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian ne...Conventional artificial neural networks used to solve electrical resistivity imaging （ERI） inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network （PBNN） nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter αk, which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion.展开更多
Network traffic classification plays an important role and benefits many practical network issues,such as Next-Generation Firewalls(NGFW),Quality of Service(QoS),etc.To face the challenges brought by modern high speed...Network traffic classification plays an important role and benefits many practical network issues,such as Next-Generation Firewalls(NGFW),Quality of Service(QoS),etc.To face the challenges brought by modern high speed networks,many inspiring solutions have been proposed to enhance traffic classification.However,taking many factual network conditions into consideration,e.g.,diversity of network environment,traffic classification methods based on Deep Inspection(DI) technique still occupy the top spot in actual usage.In this paper,we propose a novel classification system employing Deep Inspection technique,aiming to achieve Parallel Protocol Parsing(PPP).We start with an analytical study of the existing popular DI methods,namely,regular expression based methods and protocol parsing based methods.Motivated by their relative merits,we extend traditional protocol parsers to achieve parallel matching,which is the representative merit of regular expression.We build a prototype system,and evaluation results show that significant improvement has been made comparing to existing open-source solutions in terms of both memory usage and throughput.展开更多
文摘提出了一种高阶混合正则化图像盲复原方法,用于实现模糊噪声图像的清晰化盲复原。根据自然图像边缘的稀疏特性,对图像的边缘细节成分进行了全变差(total variation TV)正则化约束,根据自然图像同性质平滑区域内像素值的变化规律,将一种高阶的类Tikhonov正则化约束运用于图像的平滑区域中,提出了一种新的高阶混合正则化模型。最后,提出一种多变量分裂布雷格曼(Multi-variable Split Bregman MSB)最优化迭代策略对提出的模型进行最优化求解。实验结果表明,提出的方法能够很好地保护图像的边缘细节,同时有效地消除图像平滑区域内的阶梯和假边缘瑕疵。与近几年的一些较好的图像盲复原方法相比,本文方法的信噪比增量(increase of the signal to noise ratio ISNR)增加了0.03～2.5dB。
基金supported by the National Natural Science Foundation of China(Grant No.41374118)the Research Fund for the Higher Education Doctoral Program of China(Grant No.20120162110015)+3 种基金the China Postdoctoral Science Foundation(Grant No.2015M580700)the Hunan Provincial Natural Science Foundation,the China(Grant No.2016JJ3086)the Hunan Provincial Science and Technology Program,China(Grant No.2015JC3067)the Scientific Research Fund of Hunan Provincial Education Department,China(Grant No.15B138)
文摘Conventional artificial neural networks used to solve electrical resistivity imaging （ERI） inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network （PBNN） nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter αk, which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion.
基金supported by the National Key Technology R&D Program of China under Grant No.2012BAH46B04
文摘Network traffic classification plays an important role and benefits many practical network issues,such as Next-Generation Firewalls(NGFW),Quality of Service(QoS),etc.To face the challenges brought by modern high speed networks,many inspiring solutions have been proposed to enhance traffic classification.However,taking many factual network conditions into consideration,e.g.,diversity of network environment,traffic classification methods based on Deep Inspection(DI) technique still occupy the top spot in actual usage.In this paper,we propose a novel classification system employing Deep Inspection technique,aiming to achieve Parallel Protocol Parsing(PPP).We start with an analytical study of the existing popular DI methods,namely,regular expression based methods and protocol parsing based methods.Motivated by their relative merits,we extend traditional protocol parsers to achieve parallel matching,which is the representative merit of regular expression.We build a prototype system,and evaluation results show that significant improvement has been made comparing to existing open-source solutions in terms of both memory usage and throughput.
