Non-uniform quantization for messages in Low-Density Parity-Check(LDPC)decoding canreduce implementation complexity and mitigate performance loss.But the distribution of messagesvaries in the iterative decoding.This l...Non-uniform quantization for messages in Low-Density Parity-Check(LDPC)decoding canreduce implementation complexity and mitigate performance loss.But the distribution of messagesvaries in the iterative decoding.This letter proposes a variable non-uniform quantized Belief Propaga-tion(BP)algorithm.The BP decoding is analyzed by density evolution with Gaussian approximation.Since the probability density of messages can be well approximated by Gaussian distribution,by theunbiased estimation of variance,the distribution of messages can be tracked during the iteration.Thusthe non-uniform quantization scheme can be optimized to minimize the distortion.Simulation resultsshow that the variable non-uniform quantization scheme can achieve better error rate performance andfaster decoding convergence than the conventional non-uniform quantization and uniform quantizationschemes.展开更多
Aim at the defects of easy to fall into the local minimum point and the low convergence speed of back propagation（BP）neural network in the gesture recognition, a new method that combines the chaos algorithm with the...Aim at the defects of easy to fall into the local minimum point and the low convergence speed of back propagation（BP）neural network in the gesture recognition, a new method that combines the chaos algorithm with the genetic algorithm（CGA） is proposed. According to the ergodicity of chaos algorithm and global convergence of genetic algorithm, the basic idea of this paper is to encode the weights and thresholds of BP neural network and obtain a general optimal solution with genetic algorithm, and then the general optimal solution is optimized to the accurate optimal solution by adding chaotic disturbance. The optimal results of the chaotic genetic algorithm are used as the initial weights and thresholds of the BP neural network to recognize the gesture. Simulation and experimental results show that the real-time performance and accuracy of the gesture recognition are greatly improved with CGA.展开更多
Ultra-dense networking is widely accepted as a promising enabling technology to realize high power and spectrum efficient communications in future 5G communication systems. Although joint resource allocation schemes p...Ultra-dense networking is widely accepted as a promising enabling technology to realize high power and spectrum efficient communications in future 5G communication systems. Although joint resource allocation schemes promise huge performance improvement at the cost of cooperation among base stations,the large numbers of user equipment and base station make jointly optimizing the available resource very challenging and even prohibitive. How to decompose the resource allocation problem is a critical issue. In this paper,we exploit factor graphs to design a distributed resource allocation algorithm for ultra dense networks,which consists of power allocation,subcarrier allocation and cell association. The proposed factor graph based distributed algorithm can decompose the joint optimization problem of resource allocation into a series of low complexity subproblems with much lower dimensionality,and the original optimization problem can be efficiently solved via solving these subproblems iteratively. In addition,based on the proposed algorithm the amounts of exchanging information overhead between the resulting subprob-lems are also reduced. The proposed distributed algorithm can be understood as solving largely dimensional optimization problem in a soft manner,which is much preferred in practical scenarios. Finally,the performance of the proposed low complexity distributed algorithm is evaluated by several numerical results.展开更多
Gaussian belief propagation algorithm(GaBP) is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly co...Gaussian belief propagation algorithm(GaBP) is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly computes marginal density functions from a high dimensional joint density function over a Markov network in a finite number of iterations when the underlying Gaussian graph is acyclic. It is also known more recently that the algorithm produces correct marginal means asymptotically for cyclic Gaussian graphs under the condition of walk summability(or generalised diagonal dominance). This paper extends this convergence result further by showing that the convergence is exponential under the generalised diagonal dominance condition,and provides a simple bound for the convergence rate. Our results are derived by combining the known walk summability approach for asymptotic convergence analysis with the control systems approach for stability analysis.展开更多
火电厂在稳定运行的同时,不可避免地会排放大量污染气体,尤其是NOx。针对传统测量方法的不足,该文提出一种基于灰狼优化反向传播神经网络(grey wolf optimized-back propagation,GWO-BP)的NOx排放量软测量模型。首先使用典型相关性分析(...火电厂在稳定运行的同时,不可避免地会排放大量污染气体,尤其是NOx。针对传统测量方法的不足,该文提出一种基于灰狼优化反向传播神经网络(grey wolf optimized-back propagation,GWO-BP)的NOx排放量软测量模型。首先使用典型相关性分析(canonical correlation analysis,CCA)将任意两个相关度较高的变量归为一组,并去掉其中一个,从而选择了对NOx排放量影响最大的4个变量作为软测量模型的输入;然后,建立了反向传播(back propagation,BP)神经网络模型以对输入变量和NOx排放量做映射;最后,采用灰狼优化(grey wolf optimizer,GWO)算法优化了所提软测量模型的权重和偏置值,提升了模型的精度。实验结果表明,所提软测量模型可以准确测量NOx的排放量,在传感器故障或伴有噪声的时候很好地替代了传感器的角色,为优化算法及深度学习方法在工业现场的应用提供了参考。展开更多
基金the Aerospace Technology Support Foun-dation of China(No.J04-2005040).
文摘Non-uniform quantization for messages in Low-Density Parity-Check(LDPC)decoding canreduce implementation complexity and mitigate performance loss.But the distribution of messagesvaries in the iterative decoding.This letter proposes a variable non-uniform quantized Belief Propaga-tion(BP)algorithm.The BP decoding is analyzed by density evolution with Gaussian approximation.Since the probability density of messages can be well approximated by Gaussian distribution,by theunbiased estimation of variance,the distribution of messages can be tracked during the iteration.Thusthe non-uniform quantization scheme can be optimized to minimize the distortion.Simulation resultsshow that the variable non-uniform quantization scheme can achieve better error rate performance andfaster decoding convergence than the conventional non-uniform quantization and uniform quantizationschemes.
基金supported by Natural Science Foundation of Heilongjiang Province Youth Fund(No.QC2014C054)Foundation for University Young Key Scholar by Heilongjiang Province(No.1254G023)the Science Funds for the Young Innovative Talents of HUST(No.201304)
文摘Aim at the defects of easy to fall into the local minimum point and the low convergence speed of back propagation（BP）neural network in the gesture recognition, a new method that combines the chaos algorithm with the genetic algorithm（CGA） is proposed. According to the ergodicity of chaos algorithm and global convergence of genetic algorithm, the basic idea of this paper is to encode the weights and thresholds of BP neural network and obtain a general optimal solution with genetic algorithm, and then the general optimal solution is optimized to the accurate optimal solution by adding chaotic disturbance. The optimal results of the chaotic genetic algorithm are used as the initial weights and thresholds of the BP neural network to recognize the gesture. Simulation and experimental results show that the real-time performance and accuracy of the gesture recognition are greatly improved with CGA.
基金supported by China Mobile Research Institute under grant [2014] 451National Natural Science Foundation of China under Grant No. 61176027+2 种基金Beijing Natural Science Foundation(4152047)the 863 project No.2014AA01A701111 Project of China under Grant B14010
文摘Ultra-dense networking is widely accepted as a promising enabling technology to realize high power and spectrum efficient communications in future 5G communication systems. Although joint resource allocation schemes promise huge performance improvement at the cost of cooperation among base stations,the large numbers of user equipment and base station make jointly optimizing the available resource very challenging and even prohibitive. How to decompose the resource allocation problem is a critical issue. In this paper,we exploit factor graphs to design a distributed resource allocation algorithm for ultra dense networks,which consists of power allocation,subcarrier allocation and cell association. The proposed factor graph based distributed algorithm can decompose the joint optimization problem of resource allocation into a series of low complexity subproblems with much lower dimensionality,and the original optimization problem can be efficiently solved via solving these subproblems iteratively. In addition,based on the proposed algorithm the amounts of exchanging information overhead between the resulting subprob-lems are also reduced. The proposed distributed algorithm can be understood as solving largely dimensional optimization problem in a soft manner,which is much preferred in practical scenarios. Finally,the performance of the proposed low complexity distributed algorithm is evaluated by several numerical results.
基金supported by the National Natural Science Foundation of China(61633014,61803101,U1701264)。
文摘Gaussian belief propagation algorithm(GaBP) is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly computes marginal density functions from a high dimensional joint density function over a Markov network in a finite number of iterations when the underlying Gaussian graph is acyclic. It is also known more recently that the algorithm produces correct marginal means asymptotically for cyclic Gaussian graphs under the condition of walk summability(or generalised diagonal dominance). This paper extends this convergence result further by showing that the convergence is exponential under the generalised diagonal dominance condition,and provides a simple bound for the convergence rate. Our results are derived by combining the known walk summability approach for asymptotic convergence analysis with the control systems approach for stability analysis.
文摘火电厂在稳定运行的同时,不可避免地会排放大量污染气体,尤其是NOx。针对传统测量方法的不足,该文提出一种基于灰狼优化反向传播神经网络(grey wolf optimized-back propagation,GWO-BP)的NOx排放量软测量模型。首先使用典型相关性分析(canonical correlation analysis,CCA)将任意两个相关度较高的变量归为一组,并去掉其中一个,从而选择了对NOx排放量影响最大的4个变量作为软测量模型的输入;然后,建立了反向传播(back propagation,BP)神经网络模型以对输入变量和NOx排放量做映射;最后,采用灰狼优化(grey wolf optimizer,GWO)算法优化了所提软测量模型的权重和偏置值,提升了模型的精度。实验结果表明,所提软测量模型可以准确测量NOx的排放量,在传感器故障或伴有噪声的时候很好地替代了传感器的角色,为优化算法及深度学习方法在工业现场的应用提供了参考。
