压缩感知理论框架可以同时实现信号的采样和压缩,将压缩感知应用于语音信号处理是近年来的研究热点之一.本文根据语音信号的特点,采用K-SVD算法获得稀疏线性预测字典,作为语音信号的稀疏变换矩阵.高斯随机矩阵用于原语音信号的采样从而...压缩感知理论框架可以同时实现信号的采样和压缩,将压缩感知应用于语音信号处理是近年来的研究热点之一.本文根据语音信号的特点,采用K-SVD算法获得稀疏线性预测字典,作为语音信号的稀疏变换矩阵.高斯随机矩阵用于原语音信号的采样从而实现信号的压缩,最后通过正交匹配追踪算法(OMP)和采样压缩匹配追踪算法(Co Sa MP)将已采样压缩的语音信号进行信号重构.实验考察了待处理语音信号帧的长度、压缩比,稀疏变换字典以及压缩感知重构算法等因素对语音压缩感知重构性能的影响,结果表明,基于数据集训练的稀疏线性预测字典相比传统解析构造的离散余弦变换字典,对语音的重构性能具有0.6 d B左右的提升.展开更多
To solve the problem that the signal sparsity level is time-varying and not known as a priori in most cases,a signal sparsity level prediction and optimal sampling rate determination scheme is proposed.The discrete-ti...To solve the problem that the signal sparsity level is time-varying and not known as a priori in most cases,a signal sparsity level prediction and optimal sampling rate determination scheme is proposed.The discrete-time Markov chain is used to model the signal sparsity level and analyze the transition between different states.According to the current state,the signal sparsity level state in the next sampling period and its probability are predicted.Furthermore,based on the prediction results,a dynamic control approach is proposed to find out the optimal sampling rate with the aim of maximizing the expected reward which considers both the energy consumption and the recovery accuracy.The proposed approach can balance the tradeoff between the energy consumption and the recovery accuracy.Simulation results show that the proposed dynamic control approach can significantly improve the sampling performance compared with the existing approach.展开更多
For photovoltaic power prediction,a kind of sparse representation modeling method using feature extraction techniques is proposed.Firstly,all these factors affecting the photovoltaic power output are regarded as the i...For photovoltaic power prediction,a kind of sparse representation modeling method using feature extraction techniques is proposed.Firstly,all these factors affecting the photovoltaic power output are regarded as the input data of the model.Next,the dictionary learning techniques using the K-mean singular value decomposition(K-SVD)algorithm and the orthogonal matching pursuit(OMP)algorithm are used to obtain the corresponding sparse encoding based on all the input data,i.e.the initial dictionary.Then,to build the global prediction model,the sparse coding vectors are used as the input of the model of the kernel extreme learning machine(KELM).Finally,to verify the effectiveness of the combined K-SVD-OMP and KELM method,the proposed method is applied to a instance of the photovoltaic power prediction.Compared with KELM,SVM and ELM under the same conditions,experimental results show that different combined sparse representation methods achieve better prediction results,among which the combined K-SVD-OMP and KELM method shows better prediction results and modeling accuracy.展开更多
In the conditions of low Signal-to-Noise Ratio(SNR) of seismic data and a small quality of log information,the consequences of seismic interpretation through the impedance inversion of seismic data could be more preci...In the conditions of low Signal-to-Noise Ratio(SNR) of seismic data and a small quality of log information,the consequences of seismic interpretation through the impedance inversion of seismic data could be more precise. Constrained sparse spike inversion(CSSI) has advantage in oil and gas reservoir predication because it does not rely on the original model. By analyzing the specific algorithm of CSSI,the accuracy of inversion is controlled. Oriente Basin in South America has the low amplitude in geological structure and complex lithologic trap. The well predication is obtained by the application of CSSI.展开更多
The solution of large sparse linear systems is one of the most important problems in large scale scientific computing. Among the many methods developed, the preconditioned Krylov subspace methods [1] are considered th...The solution of large sparse linear systems is one of the most important problems in large scale scientific computing. Among the many methods developed, the preconditioned Krylov subspace methods [1] are considered the preferred methods. Selecting an effective preconditioner with appropriate parameters for a specific sparse linear system presents a challenging task for many application scientists and engineers who have little knowledge of preconditioned iterative methods. The purpose of this paper is to predict the parameter solvability space of the preconditioners with two or more parameters. The parameter solvability space is usually irregular, however, in many situations it shows spatial locality, i.e. the parameter locations that are closer in parameter space are more likely to have similar solvability. We propose three spatial data mining methods to predict the solvability of ILUT which make usage of spatial locality in different ways. The three methods are MSC （multi-points SVM classifier）, OSC （overall SVM classifier）, and OSAC （overall spatial autoregressive classifier）. The experimental results show that both MSC and OSAC can obtain 90% accuracy in prediction, but OSAC is much simpler to implement. We focus our work on ILUT preconditioner [2], but the proposed strategies should be applicable to other preconditioners with two or more parameters.展开更多
文摘压缩感知理论框架可以同时实现信号的采样和压缩,将压缩感知应用于语音信号处理是近年来的研究热点之一.本文根据语音信号的特点,采用K-SVD算法获得稀疏线性预测字典,作为语音信号的稀疏变换矩阵.高斯随机矩阵用于原语音信号的采样从而实现信号的压缩,最后通过正交匹配追踪算法(OMP)和采样压缩匹配追踪算法(Co Sa MP)将已采样压缩的语音信号进行信号重构.实验考察了待处理语音信号帧的长度、压缩比,稀疏变换字典以及压缩感知重构算法等因素对语音压缩感知重构性能的影响,结果表明,基于数据集训练的稀疏线性预测字典相比传统解析构造的离散余弦变换字典,对语音的重构性能具有0.6 d B左右的提升.
基金Innovation Funds for Outstanding Graduate Students in School of Information and Communication Engineering in BUPTthe National Natural Science Foundation of China(No.61001115, 61271182)
文摘To solve the problem that the signal sparsity level is time-varying and not known as a priori in most cases,a signal sparsity level prediction and optimal sampling rate determination scheme is proposed.The discrete-time Markov chain is used to model the signal sparsity level and analyze the transition between different states.According to the current state,the signal sparsity level state in the next sampling period and its probability are predicted.Furthermore,based on the prediction results,a dynamic control approach is proposed to find out the optimal sampling rate with the aim of maximizing the expected reward which considers both the energy consumption and the recovery accuracy.The proposed approach can balance the tradeoff between the energy consumption and the recovery accuracy.Simulation results show that the proposed dynamic control approach can significantly improve the sampling performance compared with the existing approach.
基金National Natural Science Foundation of China(No.51467008)。
文摘For photovoltaic power prediction,a kind of sparse representation modeling method using feature extraction techniques is proposed.Firstly,all these factors affecting the photovoltaic power output are regarded as the input data of the model.Next,the dictionary learning techniques using the K-mean singular value decomposition(K-SVD)algorithm and the orthogonal matching pursuit(OMP)algorithm are used to obtain the corresponding sparse encoding based on all the input data,i.e.the initial dictionary.Then,to build the global prediction model,the sparse coding vectors are used as the input of the model of the kernel extreme learning machine(KELM).Finally,to verify the effectiveness of the combined K-SVD-OMP and KELM method,the proposed method is applied to a instance of the photovoltaic power prediction.Compared with KELM,SVM and ELM under the same conditions,experimental results show that different combined sparse representation methods achieve better prediction results,among which the combined K-SVD-OMP and KELM method shows better prediction results and modeling accuracy.
基金Supported by the Fundamental Research Funds for the Central Universities(No.2011PY0186)
文摘In the conditions of low Signal-to-Noise Ratio(SNR) of seismic data and a small quality of log information,the consequences of seismic interpretation through the impedance inversion of seismic data could be more precise. Constrained sparse spike inversion(CSSI) has advantage in oil and gas reservoir predication because it does not rely on the original model. By analyzing the specific algorithm of CSSI,the accuracy of inversion is controlled. Oriente Basin in South America has the low amplitude in geological structure and complex lithologic trap. The well predication is obtained by the application of CSSI.
文摘The solution of large sparse linear systems is one of the most important problems in large scale scientific computing. Among the many methods developed, the preconditioned Krylov subspace methods [1] are considered the preferred methods. Selecting an effective preconditioner with appropriate parameters for a specific sparse linear system presents a challenging task for many application scientists and engineers who have little knowledge of preconditioned iterative methods. The purpose of this paper is to predict the parameter solvability space of the preconditioners with two or more parameters. The parameter solvability space is usually irregular, however, in many situations it shows spatial locality, i.e. the parameter locations that are closer in parameter space are more likely to have similar solvability. We propose three spatial data mining methods to predict the solvability of ILUT which make usage of spatial locality in different ways. The three methods are MSC （multi-points SVM classifier）, OSC （overall SVM classifier）, and OSAC （overall spatial autoregressive classifier）. The experimental results show that both MSC and OSAC can obtain 90% accuracy in prediction, but OSAC is much simpler to implement. We focus our work on ILUT preconditioner [2], but the proposed strategies should be applicable to other preconditioners with two or more parameters.
