针对通信中软扩频信号伪码序列盲估计困难的问题,提出一种奇异值分解(singular value decomposition,SVD)和K-means聚类相结合的方法。该方法先对接收信号按照一倍伪码周期进行不重叠分段构造数据矩阵。其次对数据矩阵和相似性矩阵分别...针对通信中软扩频信号伪码序列盲估计困难的问题,提出一种奇异值分解(singular value decomposition,SVD)和K-means聚类相结合的方法。该方法先对接收信号按照一倍伪码周期进行不重叠分段构造数据矩阵。其次对数据矩阵和相似性矩阵分别进行SVD完成对伪码序列集合规模数的估计、数据降噪、粗分类以及初始聚类中心的选取。最后通过K-means算法优化分类结果,得到伪码序列的估计值。该算法在聚类之前事先确定聚类数目,大大减少了迭代次数。同时实验结果表明,该算法在信息码元分组小于5 bit,信噪比大于-10 dB时可以准确估计出软扩频信号的伪码序列,性能较同类算法有所提升。展开更多
航空发动机叶尖间隙是监控其运行状态的有效参数,现有间隙测量方法很难满足超高转速下间隙距离的奈奎斯特采样率,因此无法有效提取精确的叶尖间隙值。本文基于压缩感知原理,针对间隙距离数据特征提出一种采用K-SVD(K-singular value dec...航空发动机叶尖间隙是监控其运行状态的有效参数,现有间隙测量方法很难满足超高转速下间隙距离的奈奎斯特采样率,因此无法有效提取精确的叶尖间隙值。本文基于压缩感知原理,针对间隙距离数据特征提出一种采用K-SVD(K-singular value decomposition)字典训练稀疏基的数据重构方法,该方法首先构建出K-SVD字典稀疏基对数据进行稀疏化表示,然后使用m序列高斯随机矩阵对数据进行压缩观测,最后基于压缩欠采样观测值使用正交匹配追踪算法对数据进行重构,进而精确提取叶尖间隙值。实验结果表明,在欠采样条件下间隙距离数据可精确恢复重构,与高采样率下的间隙数据相比,重构误差不超过0.02 mm。展开更多
In geology, classification and lithological recognition of rocks plays an important role in the area of oil and gas exploration, mineral exploration and geological analysis. In other fields of activity such as constru...In geology, classification and lithological recognition of rocks plays an important role in the area of oil and gas exploration, mineral exploration and geological analysis. In other fields of activity such as construction and decoration, this classification makes sense and fully plays its role. However, this classification is slow, approximate and subjective. Automatic classification curbs this subjectivity and fills this gap by offering methods that reflect human perception. We propose a new approach to rock classification based on direct-view images of rocks. The aim is to take advantage of feature extraction methods to estimate a rock dictionary. In this work, we have developed a classification method obtained by concatenating four (4) K-SVD variants into a single signature. This method is based on the K-SVD algorithm combined with four (4) feature extraction techniques: DCT, Gabor filters, D-ALBPCSF and G-ALBPCSF, resulting in the four (4) variants named K-Gabor, K-DCT, KD-ALBPCSF and KD-ALBPCSF respectively. In this work, we developed a classification method obtained by concatenating four (4) variants of K-SVD. The performance of our method was evaluated on the basis of performance indicators such as accuracy with other 96% success rate.展开更多
基于K-SVD字典学习算法(K-singular value decomposition,K-SVD)的压缩感知技术应用在林区微环境监测站中,可极大地减少数据传输数量,从而降低监测站的使用能耗,延长监测站的使用寿命。本文选用空气温度作为实验对象,验证算法的可行性,...基于K-SVD字典学习算法(K-singular value decomposition,K-SVD)的压缩感知技术应用在林区微环境监测站中,可极大地减少数据传输数量,从而降低监测站的使用能耗,延长监测站的使用寿命。本文选用空气温度作为实验对象,验证算法的可行性,并与前人提出的基于离散傅里叶变换基(Discrete fourier transform,DFT)的压缩感知方法进行对比实验。实验结果表明,当稀疏度k相同时,K-SVD算法的平均稀疏化误差始终小于DFT算法,且误差分布范围更加集中;当稀疏度和压缩率均相同时,K-SVD算法的平均重构误差也始终小于DFT算法,且误差分布范围更加集中。在林区微环境监测站中,K-SVD算法具有更好的稀疏表示性能以及重构性能,在降低相同系统能耗的同时,也降低了数据传输的误差。展开更多
图像去噪作为图像处理过程一个重要的环节,直接影响图像进一步处理的效果.在图像去噪方法中,基于稀疏表示的K-means singular value decomposition(K-SVD)方法通过将图像表示成训练字典和稀疏系数两部分来有效分离噪声以达到去噪目的,...图像去噪作为图像处理过程一个重要的环节,直接影响图像进一步处理的效果.在图像去噪方法中,基于稀疏表示的K-means singular value decomposition(K-SVD)方法通过将图像表示成训练字典和稀疏系数两部分来有效分离噪声以达到去噪目的,具有很好的去噪效果.然而该算法包含了复杂矩阵运算,因而去噪速度较慢.本文提出的快速的K-SVD(SK-SVD)算法综合了均值滤波的速度快及K-SVD方法对图像细节处理好的优势,将噪声图像分为背景块集与内容块集两部分,对背景块集采用均值滤波方法去噪,内容块集用K-SVD算法去噪.为达到更高的去噪精度,首先对内容块集进行聚类,再对每一类分别训练稀疏字典去噪.实验结果表明,该算法在去除噪声时不但能很好地保留图像的细节,去噪效率也有显著的提高.展开更多
文摘针对通信中软扩频信号伪码序列盲估计困难的问题,提出一种奇异值分解(singular value decomposition,SVD)和K-means聚类相结合的方法。该方法先对接收信号按照一倍伪码周期进行不重叠分段构造数据矩阵。其次对数据矩阵和相似性矩阵分别进行SVD完成对伪码序列集合规模数的估计、数据降噪、粗分类以及初始聚类中心的选取。最后通过K-means算法优化分类结果,得到伪码序列的估计值。该算法在聚类之前事先确定聚类数目,大大减少了迭代次数。同时实验结果表明,该算法在信息码元分组小于5 bit,信噪比大于-10 dB时可以准确估计出软扩频信号的伪码序列,性能较同类算法有所提升。
文摘航空发动机叶尖间隙是监控其运行状态的有效参数,现有间隙测量方法很难满足超高转速下间隙距离的奈奎斯特采样率,因此无法有效提取精确的叶尖间隙值。本文基于压缩感知原理,针对间隙距离数据特征提出一种采用K-SVD(K-singular value decomposition)字典训练稀疏基的数据重构方法,该方法首先构建出K-SVD字典稀疏基对数据进行稀疏化表示,然后使用m序列高斯随机矩阵对数据进行压缩观测,最后基于压缩欠采样观测值使用正交匹配追踪算法对数据进行重构,进而精确提取叶尖间隙值。实验结果表明,在欠采样条件下间隙距离数据可精确恢复重构,与高采样率下的间隙数据相比,重构误差不超过0.02 mm。
文摘In geology, classification and lithological recognition of rocks plays an important role in the area of oil and gas exploration, mineral exploration and geological analysis. In other fields of activity such as construction and decoration, this classification makes sense and fully plays its role. However, this classification is slow, approximate and subjective. Automatic classification curbs this subjectivity and fills this gap by offering methods that reflect human perception. We propose a new approach to rock classification based on direct-view images of rocks. The aim is to take advantage of feature extraction methods to estimate a rock dictionary. In this work, we have developed a classification method obtained by concatenating four (4) K-SVD variants into a single signature. This method is based on the K-SVD algorithm combined with four (4) feature extraction techniques: DCT, Gabor filters, D-ALBPCSF and G-ALBPCSF, resulting in the four (4) variants named K-Gabor, K-DCT, KD-ALBPCSF and KD-ALBPCSF respectively. In this work, we developed a classification method obtained by concatenating four (4) variants of K-SVD. The performance of our method was evaluated on the basis of performance indicators such as accuracy with other 96% success rate.
文摘基于K-SVD字典学习算法(K-singular value decomposition,K-SVD)的压缩感知技术应用在林区微环境监测站中,可极大地减少数据传输数量,从而降低监测站的使用能耗,延长监测站的使用寿命。本文选用空气温度作为实验对象,验证算法的可行性,并与前人提出的基于离散傅里叶变换基(Discrete fourier transform,DFT)的压缩感知方法进行对比实验。实验结果表明,当稀疏度k相同时,K-SVD算法的平均稀疏化误差始终小于DFT算法,且误差分布范围更加集中;当稀疏度和压缩率均相同时,K-SVD算法的平均重构误差也始终小于DFT算法,且误差分布范围更加集中。在林区微环境监测站中,K-SVD算法具有更好的稀疏表示性能以及重构性能,在降低相同系统能耗的同时,也降低了数据传输的误差。
文摘图像去噪作为图像处理过程一个重要的环节,直接影响图像进一步处理的效果.在图像去噪方法中,基于稀疏表示的K-means singular value decomposition(K-SVD)方法通过将图像表示成训练字典和稀疏系数两部分来有效分离噪声以达到去噪目的,具有很好的去噪效果.然而该算法包含了复杂矩阵运算,因而去噪速度较慢.本文提出的快速的K-SVD(SK-SVD)算法综合了均值滤波的速度快及K-SVD方法对图像细节处理好的优势,将噪声图像分为背景块集与内容块集两部分,对背景块集采用均值滤波方法去噪,内容块集用K-SVD算法去噪.为达到更高的去噪精度,首先对内容块集进行聚类,再对每一类分别训练稀疏字典去噪.实验结果表明,该算法在去除噪声时不但能很好地保留图像的细节,去噪效率也有显著的提高.
