基于时间可预测性的差分搜索盲信号分离算法

doi:10.3969/j.issn.1000-436x.2014.06.015

通信学报 ›› 2014, Vol. 35 ›› Issue (6): 117-125.doi: 10.3969/j.issn.1000-436x.2014.06.015

基于时间可预测性的差分搜索盲信号分离算法

陈雷^1,²,张立毅¹,郭艳菊³,黄勇¹,梁静毅¹

¹ 天津商业大学信息工程学院，天津 300134
² 天津大学精密仪器与光电子工程学院，天津 300072
³ 河北工业大学信息工程学院，天津 300401

出版日期:2014-06-25 发布日期:2017-06-29
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目

Blind signal separation algorithm based on temporal predictability and differential search algorithm

Lei CHEN^1,²,Li-yi ZHANG¹,Yan-ju GUO³,Yong HUANG¹,Jing-yi LIANG¹

¹ School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China
² School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China
³ School of Information Engineering, Hebei University of Technology, Tianjin 300401, China

Online:2014-06-25 Published:2017-06-29
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China

摘要/Abstract

摘要：

针对基于仿生智能优化的盲信号分离算法计算量偏大的问题，提出了一种新的基于差分搜索的盲信号分离算法。采用信号在时间上的可预测性度量作为目标函数，使用差分搜索算法对目标函数进行优化求解。利用去相关消源方法从混合信号中去除每次分离出的源信号成分，通过逐次分离最终实现对所有源信号的成功恢复。仿真实验表明，所提算法可以有效实现对混合信号的盲分离。与其他算法相比，该算法在保证了更高分离精度的同时，具有更低的运算量。

关键词: 盲信号分离, 时间可预测性, 差分搜索算法, 消源

Abstract:

A novel blind signal separation algorithm based on differential search was proposed for solving the high cal-culated amount problem in blind signal separation algorithm based on bio-inspired optimization. The temporal predict-ability of signal was used as the objective function and the differential search algorithm was used for solving it. The source signal component separated was wiped off using deflation method and all the source signals could be recovered successfully by repeating the separation process. Simulation results show that the algorithm can achieve blind separation from mixed signals efficiently with very high separation precision and very low computing time.

Key words: blind signal separation, temporal predictability, differential search algorithm, deflation

陈雷,张立毅,郭艳菊,黄勇,梁静毅. 基于时间可预测性的差分搜索盲信号分离算法[J]. 通信学报, 2014, 35(6): 117-125.

Lei CHEN,Li-yi ZHANG,Yan-ju GUO,Yong HUANG,Jing-yi LIANG. Blind signal separation algorithm based on temporal predictability and differential search algorithm[J]. Journal on Communications, 2014, 35(6): 117-125.

图/表 5

图2

表1

表2

表3

图3

参考文献 22

[1]	MATO-MENDEZ F J , SOBREIRA-SEOANE M A . Blind separation to improve classification of traffic noise[J]. Applied Acoustics, 2011,72(8): 590-598.
[2]	OZGEN M T , KURUOGLU E E . Blind separation to improve classification of traffic noise[J]. Applied Acoustics, 2011,72(8): 590-598.
[3]	IKHLEF A , ABED-MERAIM K , GUENNEC D L . Blind signal sepa-ration and equalization with controlled delay for MIMO convolutive systems[J]. Signal Processing, 2010,90(9): 2655-2666.
[4]	SALIDO RUIZ R A , RANTA R , LOUIS-DORR V . EEG montage analysis in the blind source separation framework[J]. Biomedical Sig-nal Processing and Control, 2011,6(1): 77-84.
[5]	CICHOCKI A , THAWONMAS R , AMARI S . Sequential blind signal extraction in order specified by stochastic properties[J]. Electronics Letters, 1997,33(1): 64-65.
[6]	HYVARINEN A . Fast and robust fixed-point algorithms for inde-pendent component analysis[J]. IEEE Transactions on Neural Net-works, 1999,10(3): 626-634.
[7]	孙守宇，郑君里，吴里江等. 峭度自适应学习率的盲信源分离[J]. 电子学报， 2005,33(3): 473-476. SUN S Y , ZHENG J L , WU C L J , et al. Blind source separation with kurtosis adaptive learning rate[J]. Acta Electronica Sinica, 2005,33(3): 473-476.
[8	段海滨，张祥银，徐春芳 . 仿生智能计算[M]．北京：科学出版社， 2011. DUAN H B , ZHANG X Y , XU C F . Bio-inspired Computing[M]. Bei-jing: Science Press, 2011.
[9]	张朝柱，张健沛，孙晓东 . 基于自适应粒子群优化的盲源分离[J]. 系统工程与电子技术， 2009,31(6): 1275-1278. ZHANG C Z , ZHANG J P , SUN X D . Blind source separation based on adaptive particle swarm optimization[J]. Systems Engineering and Electronics, 2009,31(6): 1275-1278.
[10]	张银雪，田学民，邓晓刚 . 基于改进人工蜂群算法的盲源分离方法[J]. 电子学报， 2012,40(10): 2026-2030. ZHANG Y X , TIAN X M , DENG X G . Blind source separation based on modified artificial bee colony algorithm[J]. Acta Electronica Sinica, 2012,40(10): 2026-2030.
[11]	陈雷，张立毅，郭艳菊等. 基于粒子群优化的有序盲信号分离算法[J]. 天津大学学报， 2011,44(2): 174-179. CHEN L , ZHANG L Y , GUO Y J , et al. Sequential blind signal sepa-ration algorithm based on particle swarm optimization[J]. Journal of Tianjin University, 2011,44(2): 174-179.
[12]	MAVADDATY S , EBRAHIMZADEH A . A comparative study of bees colony algorithm for blind source separation[J]. 20th Iranian Conference on Electrical Engineering[C]. 2012.1172-1177.
[13]	CIVICIOGLU P . Transforming geocentric cartesian coordinates to geodetic coordinates by using differential search algorithm[J]. Com-puters and Geosciences, 2012,46: 229-247.
[14]	STONE J V . Independent Component Analysis-A Tutorial Introduc-tion[M]． MIT Press, 2004.
[15]	TRIANNI V , TUCI E , PASSINO K M , et al. Swarm cognition: an interdisciplinary approach to the study of self-organising biological collectives[J]. Swarm Intelligence, 2011,5(1): 3-18.
[16]	KENNEDY J , EBERHART R C . Particle swarm optimization[J]. Proceedings of IEEE International Conference on Neural Networks[C]. Perth, Australia, 1995.1942-1948.
[17]	KARABOGA D , BASTURK B . A powerful and efficient algorithm for numerical function optimization: artificial bee colony(ABC) algo-rithm[J]. Journal of Global Optimization, 2007,39(3): 459-471.
[18]	ZHANG J , SANDERSON A C .JADE: adaptive differential evolution with optional external archive[J]. IEEE Transactions on Evolutionary Computation, 2009,13(5): 945-958.
[19]	WANG Y , CAI Z X , ZHANG Q F . Differential evolution with com-posite trial vector generation strategies and control parameters[J]. IEEE Transactions on Evolutionary Computation, 2011,15(1): 55-66.
[20]	OMRAN M G H , CLERC M . SPSO 2011[EB/OL]. . 2011,15(1): 55-66.
[21]	FREEDMAN D , PISANI R , PURVES R . Statistics[M]. W W Norton＆Company, 2007.
[22]	BOFILL P , ZIBULEVSKY M . Underdetermined blind source separa-tion using sparse representations[J]. Signal Processing, 2001,81(11): 2353-2362.

算法		信号1			信号2			信号3		总平均值/dB
算法	最大值/dB	最小值/dB	平均值/dB	最大值/dB	最小值/dB	均值/dB	最大值/dB	小值/dB	平均值/dB	总平均值/dB
文献[9]	0.999 94	0.999 76	0.999 92	0.999 84	0.999 50	0.999 78	0.999 66	0.998 92	0.999 46	0.999 72
文献[10]	0.999 98	0.999 81	0.999 93	0.999 97	0.999 69	0.999 81	0.999 80	0.999 29	0.999 50	0.999 75
文献[11]	0.999 73	0.999 73	0.999 73	0.999 74	0.999 71	0.999 73	0.999 61	0.999 60	0.999 60	0.999 69
文献[12]	0.999 66	0.999 23	0.999 60	0.999 99	0.999 30	0.999 76	0.999 90	0.999 51	0.999 74	0.999 70
本文算法	1.000 00	0.999 97	0.999 99	0.999 88	0.999 87	0.999 87	0.999 62	0.999 60	0.999 61	0.999 82

算法		信号1			信号2			信号3		总平均值/dB
算法	最大值/dB	最小值/dB	平均值/dB	最大值/dB	最小值/dB	平均值/dB	最大值/dB	最小值/dB	平均值/dB	总平均值/dB
文献[9]	34.671 0	32.733 4	34.343 5	34.984 0	33.346 9	34.026 3	32.866 1	31.000 7	31.504 6	33.291 5
文献[10]	40.475 0	29.173 6	34.399 0	41.294 9	32.024 3	34.415 4	35.716 9	30.230 4	31.723 7	33.512 7
文献[11]	30.357 6	30.338 6	30.349 5	32.823 3	32.637 7	32.725 3	33.325 8	33.315 9	33.317 8	32.130 9
文献[12]	33.410 0	29.798 8	32.396 7	41.721 5	24.052 4	32.773 9	37.082 6	30.174 0	33.007 1	32.725 9
本文算法	42.736 2	37.367 1	41.218 2	36.155 8	35.851 7	36.024 7	32.398 4	31.754 8	32.120 8	36.454 6

算法	最大值/s	最小值/s	平均值/s
文献[9]	9.953	8.576	9.061
文献[10]	19.998	17.442	18.113
文献[11]	7.533	7.175	7.235
文献[12]	9.679	9.524	9.561
本文算法	0.1928	0.1201	0.1472

基于时间可预测性的差分搜索盲信号分离算法

Blind signal separation algorithm based on temporal predictability and differential search algorithm

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 22

相关文章 4

Metrics

推荐阅读 0

[1]	陈雷，张立毅，郭艳菊，黄勇，梁静毅. 基于时间可预测性的差分搜索盲信号分离算法[J]. 通信学报, 2014, 35(6): 15-125.
[2]	肖明,高峰,孙功宪,谢胜利. 经时频掩码的欠定混叠信号的盲提取[J]. 通信学报, 2012, 33(8): 77-84.
[3]	陈雷,张立毅,郭艳菊,赵俊青,李锵. 基于细菌群体趋药性的有序盲信号分离算法[J]. 通信学报, 2011, 32(4): 77-85.
[4]	郭滨,白雪梅. 基于信道矩阵结构划分的用户信号恢复[J]. 通信学报, 2011, 32(12): 146-150.