A Computationally Efficient Blind Source Extraction Using Idempotent Transformation Matrix
- 31 Downloads
Blind source separation (BSS) problem is an open area of research that requires further investigations. Various algorithms were presented in the literature based on second-order statistics and higher-order statistics. The computational complexity of those methods is a challenging task and must be carefully considered to produce fast BSS algorithms. In blind source extraction (BSE) using linear predictors, the adaptive filter update requires complex computations that need consideration. This work focus on new BSE using the idempotent transformation matrix. New algorithm is presented in this work to compute the matrix with less computational complexity as compared with the standard singular value decomposition method. New optimization problem was defined according to the proposed matrix equation, and solved by an iterative algorithm with low computational complexity. The proposed method is tested using speech and white Gaussian signals. The performance measures used in this work are the signal-to-interference ratio, signal-to-distortion ratio, and signal-to-artifact ratio. Simulation results show that the proposed algorithm significantly separate the source signals with better performance measures as compared with the state-of-the-art approaches such as second-order blind identification and fast independent component analysis.
KeywordsBlind source separation Blind source extraction Singular value decomposition Fast independent component analysis Second-order blind identification Speech signals.
- 2.L. Albera, A. Kachenoura, P. Comon, A. Karfoul, F. Wendling, L. Senhadji, I. Merlet, ICA-based EEG denoising: a comparative analysis of fifteen methods. Bull. Pol. Acad. Sci. Tech. Sci. 60(3), 407–418 (2012)Google Scholar
- 4.T. Bose, F. Meyer, Digital Signal and Image Processing (Wiley, London, 2003)Google Scholar
- 11.S. Ferdowsi, V. Abolghasemi, S. Sanei, Blind separation of ballistocardiogram from EEG via short-and-long-term linear prediction, in IEEE International Workshop on Machine Learning for Signal Process, pp. 1–6 (2012)Google Scholar
- 12.R. Gribonval, C. Févotte, E. Vincent, BSS EVAL toolbox user guide (IRISA Technical Report, 2005)Google Scholar
- 13.S.H. Hsu, T.R. Mullen, T.P. Jung, G. Cauwenberghs, Real-time adaptive EEG source separation using online recursive independent component analysis. IEEE Trans. Neural Syst. Rehab. 24(3), 209–3194 (2016)Google Scholar
- 15.https://www.mathworks.com/matlabcentral/fileexchange/10858-ecg-simulation-using-matlab (2006). Accessed Sep 2018
- 24.W. Liu, D.P. Mandic, A. Cichocki, A dual-linear predictor approach to blind source extraction for noisy mixtures. In Proceeding of IEEE Workshop on Sensor Array and Multichannel Signal Process, pp. 515–519 (2008)Google Scholar
- 27.D.P. Mandic, A. Cichocki, An online algorithm for blind extraction of sources with different dynamical structures, in Proceeding of the International Conference on Independent Component Analysis and Blind Signal Separation, pp. 645–650 (2003)Google Scholar
- 34.P. Sutha, V.E. Jayanthi, A. Cichocki, Fetal electrocardiogram extraction and analysis using adaptive noise cancellation and wavelet transformation techniques. J. Med. Syst. 42(21), 1–18 (2018)Google Scholar
- 36.A.L. Taha, L.Y. Taha, E. Abdel-Raheem, FastICA architecture utilizing FPGA and iterative symmetric orthogonalization for multivariate signals, in IEEE International Symposium on Signal Processing and Information Technology, pp. 279–284 (2015)Google Scholar
- 37.L.Y. Taha, E. Abdel-Raheem, A null space approach for complete and over-complete blind source separation of auto regressive source signals. In Proceeding of the IEEE Canadian Conference in Electrical and Computer Engineering, pp. 1–4 (2017)Google Scholar
- 40.H. Wang, Z. Su, H. Fang, A Cichocki, Simulating normal and abnormal ECG signals in children age 0–16, in Proceeding of the IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pp. 282–283, 17–19 July 2017Google Scholar