基于貝葉斯壓縮感知的復(fù)數(shù)稀疏信號(hào)恢復(fù)方法
doi: 10.11999/JEIT151056
基金項(xiàng)目:
國(guó)家自然科學(xué)基金(61571148)，中國(guó)博士后科學(xué)基金(2014M550182)，黑龍江省博士后特別資助(LBH-TZ0410)，哈爾濱市科技創(chuàng)新人才資助課題(2013RFXXJ016)，中國(guó)博士后特別資助(2015T80328)
Sparse Signal Recovery Based on Complex Bayesian Compressive Sensing
Funds:
The National Natural Science Foundation of China (61571148), China Postdoctoral Science Foundation (2014M550182), Heilongjiang Province Postdoctoral Special Foundation (LBH-TZ0410), Harbin Science and Technology Innovation Talents (2013RFXXJ016), China Postdoctoral Special Funding (2015T 80328)
-
摘要: 該文利用復(fù)數(shù)稀疏信號(hào)的時(shí)域相互關(guān)系提出一種新的稀疏貝葉斯算法(CTSBL)。該算法利用復(fù)數(shù)信號(hào)的實(shí)部與虛部分量具有相同的稀疏結(jié)構(gòu)的特點(diǎn)，提升估計(jì)信號(hào)的稀疏程度。同時(shí)將多個(gè)測(cè)量信號(hào)間的內(nèi)部結(jié)構(gòu)信息引入到了信號(hào)恢復(fù)中，使原始的多測(cè)量稀疏信號(hào)恢復(fù)問(wèn)題轉(zhuǎn)變?yōu)閱螠y(cè)量塊稀疏信號(hào)恢復(fù)問(wèn)題，使恢復(fù)性能得到了提升。理論分析和仿真結(jié)果證明，提出的CTSBL算法相較于目前的針對(duì)復(fù)數(shù)信號(hào)的多測(cè)量矢量貝葉斯壓縮感知(CMTBCS)算法和塊正交匹配追蹤算法(BOMP)在估計(jì)精度上具有更好的性能。
-
關(guān)鍵詞:
- 壓縮感知 /
- 稀疏信號(hào)恢復(fù) /
- 多矢量測(cè)量模型 /
- 塊稀疏貝葉斯
Abstract: An effective Sparse Bayesian Learning algorithm exploiting Complex sparse Temporal correlation (CTSBL) is proposed in this paper, which is used to recover sparse complex signal. By exploiting the fact that the real and imaginary components of a complex value share the same sparsity pattern, it can improve the sparsity of the estimated signal. A multitask sparse signal recovery issue is transformed to a block sparse signal recovery issue of a single measurement by taking full advantage of the internal structure information among the multiple measurement vector signals. The experiments show that the proposed algorithm CTSBL achieves better recovery performance compared with the existing Complex MultiTask Bayesian Compressive Sensing (CMTBCS) algorithm and BOMP algorithm. -
DONOHO D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306. doi: 10.1109/ TIT.2006.871582. ELAD M. Sparse and Redundant Representations[M]. New York: Springer, 2010: 1094-1097. 王天云, 于小飛, 陳衛(wèi)東. 基于稀疏貝葉斯學(xué)習(xí)的無(wú)源雷達(dá)高分辨成像[J]. 電子與信息學(xué)報(bào), 2015, 37(5): 1023-1030. doi: 10.11999/JEIT140899. WANG T Y, YU X F, and CHEN W D. High-resolution imaging of passive radar based on sparse Bayesian learning[J]. Journal of Electronics Information Technology, 2015, 37(5): 1023-1030. doi: 10.11999/JEIT140899. 孫磊, 王華力, 許廣杰. 基于稀疏貝葉斯學(xué)習(xí)的高效 DOA 估計(jì)方法[J]. 電子與信息學(xué)報(bào), 2013, 35(5): 1196-1201. doi: 10.3724/SP.J.1146.2012.01429. SUN L, WANG H L, and XU G J. Efficient direction-of- arrival estimation via sparse Bayesian learning[J]. Journal of Electronics Information Technology, 2013, 35(5): 1196-1201. doi: 10.3724/SP.J.1146.2012.01429. CHEN S and DONOHO D L. Atomic decomposition by basis pursuit[J]. IEEE Transactions on Signal Processing, 1995, 43(1): 33-61. doi: 10.1137/S1064827596304010. THEIS F J, JUNG A, PUNTONET C G, et al. Signal recovery from partial information via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 15(2): 419-439. TIBSHIRANI R. Regression shrinkage and subset selection with the Lasso[J]. Journal of the Royal Statistical Society, 1996, 58(1): 267-288. HUANG J and ZHANG T. The benefit of group sparsity[J]. Annals of Statistics, 2009, 38(4): 1978-2004. doi: 10.1214/09- AOS778. YUAN M and LIN Y. Model selection and estimation in regression with grouped variables[J]. Journal of the Royal Statistical Society, 2006, 68(1): 49-67. doi: 10.1111/j. 1467-9868.2005.00532.x. FU Y L, LI H F, ZHANG Q H, et al. Block-sparse recovery via redundant block OMP[J]. Signal Processing, 2014, 97(7): 162-171. doi: 10.1016/j.sigpro.2013.10.030. LI B, SHEN Y, LI J, et al. Sensing and measurement dictionaries design for block OMP algorithm[J]. Electronics Letters, 2014, 50(19): 1351-1353. doi : 10.1049/el.2014. 2000. ZHANG Z and RAO B D. Sparse signal recovery with temporally correlated source vectors using sparse Bayesian learning[J]. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(5): 912-926. doi: 10.1109/JSTSP.2011. 2159773. WANG W, JIA M, and GUO Q. A compressive sensing recovery algorithm based on sparse Bayesian learning for block sparse signal[C]. 2014 International Symposium on Wireless Personal Multimedia Communications, Sydney, 2014: 547-551. doi: 10.1109/WPMC.2014.7014878. 王峰, 向新, 易克初, 等. 基于隱變量貝葉斯模型的稀疏信號(hào)恢復(fù)[J]. 電子與信息學(xué)報(bào), 2015, 37(1): 97-102. doi: 10.11999/ JEIT140169. WANG F, XIANG X, YI K C et al. Sparse signals recovery based on latent variable Bayesian models[J]. Journal of Electronics Information Technology, 2015, 37(1): 97-102. doi: 10.11999/JEIT140169. CARLIN M, ROCCA P, OLIVERI G, et al. Directions-of- arrival estimation through Bayesian compressive sensing strategies[J]. IEEE Transactions on Antennas Propagation, 2013, 61(7): 3828-3838. doi : 10.1109/TAP.2013.2256093. WU Q, ZHANG Y D, AMIN M G, et al. Complex multitask Bayesian compressive sensing[C]. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, 2014: 3375-3379. doi: 10.1109/ICASSP.2014. 6854226. CAWLEY G C and TALBOT N L C. Preventing over-fitting during model selection via Bayesian regularisation of the hyper-parameters[J]. Journal of Machine Learning Research, 2007, 8(4): 841-861. ZHANG Z and RAO B D. Extension of SBL algorithms for the recovery of block sparse signals with Intra-Block correlation[J]. IEEE Transactions on Signal Processing, 2013, 61(8): 2009-2015. doi: 10.1109/TSP.2013.2241055. ZHANG Z and RAO B D. Recovery of block sparse signals using the framework of block sparse Bayesian learning[C]. 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan, 2012: 3345-3348. doi: 10.1109/ICASSP.2012.6288632. KAY S M. Fundamentals of statistical signal processing: estimation theory[J]. Technometrics, 1995, 37(4): 465-466. -
計(jì)量
- 文章訪問(wèn)數(shù): 2268
- HTML全文瀏覽量: 174
- PDF下載量: 768
- 被引次數(shù): 0
下載:
