An Adaptive Measurement Scheme (AMS) is investigated with Compressed Sensing (CS) theory in Cognitive Wireless Sensor Network (C-WSN). Local sensing information is collected via energy detection with Analog-to-Informa...An Adaptive Measurement Scheme (AMS) is investigated with Compressed Sensing (CS) theory in Cognitive Wireless Sensor Network (C-WSN). Local sensing information is collected via energy detection with Analog-to-Information Converter (AIC) at massive cognitive sensors, and sparse representation is considered with the exploration of spatial temporal correlation structure of detected signals. Adaptive measurement matrix is designed in AMS, which is based on maximum energy subset selection. Energy subset is calculated with sparse transformation of sensing information, and maximum energy subset is selected as the row vector of adaptive measurement matrix. In addition, the measurement matrix is constructed by orthogonalization of those selected row vectors, which also satisfies the Restricted Isometry Property (RIP) in CS theory. Orthogonal Matching Pursuit (OMP) reconstruction algorithm is implemented at sink node to recover original information. Simulation results are performed with the comparison of Random Measurement Scheme (RMS). It is revealed that, signal reconstruction effect based on AMS is superior to conventional RMS Gaussian measurement. Moreover, AMS has better detection performance than RMS at lower compression rate region, and it is suitable for large-scale C-WSN wideband spectrum sensing.展开更多
In this paper, we propose a face recognition approach-Structed Sparse Representation-based classification when the measurement of the test sample is less than the number training samples of each subject. When this con...In this paper, we propose a face recognition approach-Structed Sparse Representation-based classification when the measurement of the test sample is less than the number training samples of each subject. When this condition is not satisfied, we exploit Nearest Subspaee approach to classify the test sample. In order to adapt all the eases, we combine the two approaches to an adaptive classification method-Adaptive approach. The adaptive approach yields greater recognition accuracy than the SRC approach and CRC_RLS approach with low ~ample rate on the Extend Yale B dataset. And it is more efficient than other two approaches.展开更多
针对工业机械设备实时监测中不可控因素导致的振动信号数据缺失问题,提出一种基于自适应二次临近项交替方向乘子算法(adaptive quadratic proximity-alternating direction method of multipliers, AQ-ADMM)的压缩感知缺失信号重构方法...针对工业机械设备实时监测中不可控因素导致的振动信号数据缺失问题,提出一种基于自适应二次临近项交替方向乘子算法(adaptive quadratic proximity-alternating direction method of multipliers, AQ-ADMM)的压缩感知缺失信号重构方法。AQ-ADMM算法在经典交替方向乘子算法算法迭代过程中添加二次临近项,且能够自适应选取惩罚参数。首先在数据中心建立信号参考数据库用于构造初始字典,然后将K-奇异值分解(K-singular value decomposition, K-SVD)字典学习算法和AQ-ADMM算法结合重构缺失信号。对仿真信号和两种真实轴承信号数据集添加高斯白噪声后作为样本,试验结果表明当信号压缩率在50%~70%时,所提方法性能指标明显优于其它传统方法,在重构信号的同时实现了对含缺失数据机械振动信号的快速精确修复。展开更多
针对工业环境中随机冲击干扰下滚动轴承微弱故障特征提取难题,提出一种基于自适应短时维纳滤波(Adaptive Short Time Wiener Filtering,ASTWF)和改进正交匹配追踪(Orthogonal Matching Pursuit,OMP)的滚动轴承故障特征提取方法。该方法...针对工业环境中随机冲击干扰下滚动轴承微弱故障特征提取难题,提出一种基于自适应短时维纳滤波(Adaptive Short Time Wiener Filtering,ASTWF)和改进正交匹配追踪(Orthogonal Matching Pursuit,OMP)的滚动轴承故障特征提取方法。该方法首先采用包络峭度和随余比(Random Shocks and Margin Ratio,RMR)作为联合判据,界定窗长界限并自适应确定STWF最优窗长参数,进而将随机冲击干扰从测试信号中分离出来;然后,利用立方包络自相关谱估计信号中周期频率,构造周期原子库,降低匹配原子冗余度;最后,利用相似性理论优化匹配追踪迭代终止条件,并结合周期原子库,实现弱故障冲击特征快速、准确提取。根据仿真信号和通过变速箱下线检测所得工程数据,可验证所提出方法可有效识别随机冲击干扰下的滚动轴承微弱故障特征。对比最小熵形态反卷积(Minimum Entropy Morphological Deconvolution,MEMD)方法对于随机冲击干扰下滚动轴承微弱故障特征提取效果,发现所提出方法具有更好的故障特征提取能力;与经典OMP方法相比,所提出改进OMP方法信号重构速度提升66%。展开更多
为了充分利用稀疏表示分类算法中重构残差包含的特征信息,将重构残差的波段信息反馈到测试样本中,自适应增强样本的稀疏特征提取。但反馈调整过程可能会出现特征过拟合的问题,为了进一步提高算法的稳定性和分类精度,提出了紧耦合像元生...为了充分利用稀疏表示分类算法中重构残差包含的特征信息,将重构残差的波段信息反馈到测试样本中,自适应增强样本的稀疏特征提取。但反馈调整过程可能会出现特征过拟合的问题,为了进一步提高算法的稳定性和分类精度,提出了紧耦合像元生成算法(close coupled set of pixels,CCSP)来平滑特征分布以解决过拟合问题,并最终提出了基于紧耦合像元的自适应增强类内稀疏表示高光谱图像分类方法(close coupled set of pixels-based adaptive boosting class-wise sparse representation classifier,CCSP-ABCWSRC)。在Indian Pines,University of Pavia,Salinas三个高光谱数据集上的实验结果表明,提出的算法对高光谱图像进行了稳定有效的分类并且其分类精度优于同类算法。展开更多
基金Supported by the National Natural Science Foundation of China (No. 61102066, 60972058)the China Postdoctoral Science Foundation (No. 2012M511365)the Scientific Research Project of Zhejiang Provincial Education Department (No. Y201119890)
文摘An Adaptive Measurement Scheme (AMS) is investigated with Compressed Sensing (CS) theory in Cognitive Wireless Sensor Network (C-WSN). Local sensing information is collected via energy detection with Analog-to-Information Converter (AIC) at massive cognitive sensors, and sparse representation is considered with the exploration of spatial temporal correlation structure of detected signals. Adaptive measurement matrix is designed in AMS, which is based on maximum energy subset selection. Energy subset is calculated with sparse transformation of sensing information, and maximum energy subset is selected as the row vector of adaptive measurement matrix. In addition, the measurement matrix is constructed by orthogonalization of those selected row vectors, which also satisfies the Restricted Isometry Property (RIP) in CS theory. Orthogonal Matching Pursuit (OMP) reconstruction algorithm is implemented at sink node to recover original information. Simulation results are performed with the comparison of Random Measurement Scheme (RMS). It is revealed that, signal reconstruction effect based on AMS is superior to conventional RMS Gaussian measurement. Moreover, AMS has better detection performance than RMS at lower compression rate region, and it is suitable for large-scale C-WSN wideband spectrum sensing.
基金Supported by National Natural Science Foundation of China(No.61170324 and No.61100105)
文摘In this paper, we propose a face recognition approach-Structed Sparse Representation-based classification when the measurement of the test sample is less than the number training samples of each subject. When this condition is not satisfied, we exploit Nearest Subspaee approach to classify the test sample. In order to adapt all the eases, we combine the two approaches to an adaptive classification method-Adaptive approach. The adaptive approach yields greater recognition accuracy than the SRC approach and CRC_RLS approach with low ~ample rate on the Extend Yale B dataset. And it is more efficient than other two approaches.
文摘针对工业机械设备实时监测中不可控因素导致的振动信号数据缺失问题,提出一种基于自适应二次临近项交替方向乘子算法(adaptive quadratic proximity-alternating direction method of multipliers, AQ-ADMM)的压缩感知缺失信号重构方法。AQ-ADMM算法在经典交替方向乘子算法算法迭代过程中添加二次临近项,且能够自适应选取惩罚参数。首先在数据中心建立信号参考数据库用于构造初始字典,然后将K-奇异值分解(K-singular value decomposition, K-SVD)字典学习算法和AQ-ADMM算法结合重构缺失信号。对仿真信号和两种真实轴承信号数据集添加高斯白噪声后作为样本,试验结果表明当信号压缩率在50%~70%时,所提方法性能指标明显优于其它传统方法,在重构信号的同时实现了对含缺失数据机械振动信号的快速精确修复。
文摘针对工业环境中随机冲击干扰下滚动轴承微弱故障特征提取难题,提出一种基于自适应短时维纳滤波(Adaptive Short Time Wiener Filtering,ASTWF)和改进正交匹配追踪(Orthogonal Matching Pursuit,OMP)的滚动轴承故障特征提取方法。该方法首先采用包络峭度和随余比(Random Shocks and Margin Ratio,RMR)作为联合判据,界定窗长界限并自适应确定STWF最优窗长参数,进而将随机冲击干扰从测试信号中分离出来;然后,利用立方包络自相关谱估计信号中周期频率,构造周期原子库,降低匹配原子冗余度;最后,利用相似性理论优化匹配追踪迭代终止条件,并结合周期原子库,实现弱故障冲击特征快速、准确提取。根据仿真信号和通过变速箱下线检测所得工程数据,可验证所提出方法可有效识别随机冲击干扰下的滚动轴承微弱故障特征。对比最小熵形态反卷积(Minimum Entropy Morphological Deconvolution,MEMD)方法对于随机冲击干扰下滚动轴承微弱故障特征提取效果,发现所提出方法具有更好的故障特征提取能力;与经典OMP方法相比,所提出改进OMP方法信号重构速度提升66%。
文摘为了充分利用稀疏表示分类算法中重构残差包含的特征信息,将重构残差的波段信息反馈到测试样本中,自适应增强样本的稀疏特征提取。但反馈调整过程可能会出现特征过拟合的问题,为了进一步提高算法的稳定性和分类精度,提出了紧耦合像元生成算法(close coupled set of pixels,CCSP)来平滑特征分布以解决过拟合问题,并最终提出了基于紧耦合像元的自适应增强类内稀疏表示高光谱图像分类方法(close coupled set of pixels-based adaptive boosting class-wise sparse representation classifier,CCSP-ABCWSRC)。在Indian Pines,University of Pavia,Salinas三个高光谱数据集上的实验结果表明,提出的算法对高光谱图像进行了稳定有效的分类并且其分类精度优于同类算法。
