Modified Infomax Algorithm for Smaller Data Block Lengths

AbstractIndependent component analysis (ICA) is a signal processing technique used for blind source separation of the mixed received data. In general, performance of the ICA algorithms degrade as data block lengths become smaller. The existing work for smaller data blocks lengths inserts extra bits in the transmitted data blocks that increases the data blocks lengths at the transmitter side and removes them after processing through the ICA algorithm at receiver side. Insertion of the extra bits in the transmitted data blocks decreases the bandwidth efficiency and increases the transmission power. In this paper, firstly we analyze the infomax (IF) algorithm of the ICA for different blocks lengths, step sizes and number of iterations. Performance degradation of the IF algorithm observed for reduced lengths of the processing data blocks due to the expectation operator used in the update equation of the algorithm that can’t be avoided through the learning rate parameter and the number of iterations. Secondly, we propose a modified Infomax (MIF) algorithm for smaller block lengths. The proposed MIF algorithm performs well for smaller block lengths with negligible increase in the computational complexity as compared to the existing IF algorithm. The proposed MIF algorithm processes the received data blocks without changing their lengths at the transmitter side. Simulation results show that the proposed algorithm outperforms the existing IF algorithm for smaller blocks lengths.

[1]  Wasfy B. Mikhael,et al.  A Gradient-Based Optimum Block Adaptation ICA Technique for Interference Suppression in Highly Dynamic Communication Channels , 2006, EURASIP J. Adv. Signal Process..

[2]  Desheng Zhu,et al.  Maximum likelihood blind equalization via blind separation using fractional sampling , 2010, 2010 IEEE 12th International Conference on Communication Technology.

[3]  Van Khanh Nguyen,et al.  Blind Separation of Mutually Correlated Sources Using Precoders , 2010, IEEE Transactions on Neural Networks.

[4]  James V. Stone Independent Component Analysis: A Tutorial Introduction , 2007 .

[5]  Jiancheng Sun,et al.  Blind MIMO-OFDM Channel Estimation Based on ICA and KRLS Algorithm , 2009, 2009 5th International Conference on Wireless Communications, Networking and Mobile Computing.

[6]  Ernest Otto Doebelin,et al.  Measurement Systems Application and Design , 1966 .

[7]  Adel Mohammadpour,et al.  Parametric independent component analysis for stable distributions , 2013, Artif. Intell. Res..

[8]  Tian Jinhua,et al.  Overcomplete ICA algorithm of speech signal extraction in underdetermined mixtures , 2011, 2011 International Conference on Electric Information and Control Engineering.

[9]  D. Obradovic,et al.  Independent component analysis for semi-blind signal separation in MIMO mobile frequency selective communication channels , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[10]  Tianyou Liu,et al.  The Application of Ant Colony Optimization Algorithm in Linear-Combination Blind Source Separation Problem , 2009, 2009 2nd International Congress on Image and Signal Processing.

[11]  Sergios Theodoridis,et al.  A Novel Efficient Cluster-Based MLSE Equalizer for Satellite Communication Channels with-QAM Signaling , 2006, EURASIP J. Adv. Signal Process..

[12]  Guolong Liang,et al.  A new algorithm of Infomax for small numbers of sound signal separation , 2010, 2010 International Conference on Artificial Intelligence and Education (ICAIE).

[13]  Tamal Bose,et al.  Blind Adaptive Equalization of MIMO Systems: New Recursive Algorithms and Convergence Analysis , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[14]  Kiyohiro Shikano,et al.  Two-stage blind source separation based on ICA and binary masking for real-time robot audition system , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Jun Zhang,et al.  Research and application of ICA technique in fault diagnosis for equipments , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[16]  Bhuvan Unhelkar,et al.  Separation performance of ICA algorithms in communication systems , 2009, 2009 International Multimedia, Signal Processing and Communication Technologies.

[17]  E. Oja,et al.  Independent Component Analysis , 2013 .

[18]  Qinggui Jin,et al.  Blind Signal Separation by Entropy Maximization (INFOMAX) , 2010, 2010 6th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM).

[19]  Hiroshi Sawada,et al.  Underdetermined Convolutive Blind Source Separation via Frequency Bin-Wise Clustering and Permutation Alignment , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[20]  R. Saatchi,et al.  Assessing material densities by vibration analysis and independent component analysis , 2014 .

[21]  Sang-Hoon Oh,et al.  A modified infomax algorithm for blind signal separation , 2006, Neurocomputing.

[22]  Terrence J. Sejnowski,et al.  Independent Component Analysis for Mixed Sub- Gaussian and Super- Gaussian Sources , 1999 .

[23]  Pierre Comon,et al.  Robust Independent Component Analysis by Iterative Maximization of the Kurtosis Contrast With Algebraic Optimal Step Size , 2010, IEEE Transactions on Neural Networks.

[24]  Jun Bai,et al.  Natural Gradient Improvement Methods in Blind Source Separation , 2009, 2009 2nd International Congress on Image and Signal Processing.

[25]  Wee Gin Lim,et al.  Multi-user multimodulus algorithm in blind source separation and equalization for MIMO systems , 2009, 2009 IEEE 9th Malaysia International Conference on Communications (MICC).

[26]  Chong Meng Samson See,et al.  Doppler aided blind source separation of communication signals , 2010, 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010).

[27]  Rajiv Chopra,et al.  Calculation of Intravascular Signal in Dynamic Contrast Enhanced-MRI Using Adaptive Complex Independent Component Analysis , 2013, IEEE Transactions on Medical Imaging.

[28]  Yannick Deville,et al.  Blind Separation of Nonstationary Markovian Sources Using an Equivariant Newton–Raphson Algorithm , 2009, IEEE Signal Processing Letters.

[29]  Fernando Puente León,et al.  Adaptive Underdetermined ICA for Handling an Unknown Number of Sources , 2010, LVA/ICA.

[30]  M. Gupta,et al.  ICA based blind adaptive MAI suppression in DS-CDMA systems , 2004, 3rd IEEE Signal Processing Education Workshop. 2004 IEEE 11th Digital Signal Processing Workshop, 2004..

[31]  Hualiang Li,et al.  A Class of Complex ICA Algorithms Based on the Kurtosis Cost Function , 2008, IEEE Transactions on Neural Networks.

[32]  Xiumei Li,et al.  Blind source separation of vibration signal of electric traction experiment system , 2010, 2010 International Conference on Intelligent Control and Information Processing.

[33]  Katsumi Yamashita,et al.  An Optimum ICA Based Multiuser Data Separation for Short Message Service , 2010, AST/UCMA/ISA/ACN.

[34]  Hideaki Sakai,et al.  A New Adaptive Filter Algorithm for System Identification using Independent Component Analysis , 2007, ICASSP.

[35]  Seungjin Choi,et al.  Independent Component Analysis , 2009, Handbook of Natural Computing.

[36]  Chonghui Guo,et al.  Noisy blind source separation by nonlinear autocorrelation , 2010, 2010 3rd International Congress on Image and Signal Processing.

[37]  J. Ramírez,et al.  Elitist genetic algorithm guided by higher order statistic for blind separation of digital signals , 2010, IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society.

[38]  Asoke K. Nandi,et al.  Non-redundant precoding and PAPR reduction in MIMO OFDM systems with ICA based blind equalization , 2009, IEEE Transactions on Wireless Communications.