Data Censoring with Set-Membership Affine Projection Algorithm

In this paper, the set-membership affine projection (SM-AP) algorithm is utilized to censor non-informative data in big data applications. To this end, the probability distribution of the additive noise signal and the excess of the mean-squared error (EMSE) in steady-state are employed in order to estimate the threshold parameter of the single threshold SM-AP (ST-SM-AP) algorithm aiming at attaining the desired update rate. Furthermore, by defining an acceptable range for the error signal, the double threshold SM-AP (DT-SM-AP) algorithm is proposed to detect very large errors due to the irrelevant data such as outliers. The DT-SM-AP algorithm can censor non-informative and irrelevant data in big data applications, and it can improve the misalignment and convergence rate of the learning process with high computational efficiency. The simulation and numerical results corroborate the superiority of the proposed algorithms over traditional algorithms.

[1]  Paulo S. R. Diniz,et al.  Steady-state analysis of the set-membership affine projection algorithm , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Antonio De Maio,et al.  Censoring Outliers in Radar Data: An Approximate ML Approach and its Analysis , 2019, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Andreas Antoniou,et al.  Robust Set-Membership Affine-Projection Adaptive-Filtering Algorithm , 2012, IEEE Transactions on Signal Processing.

[4]  Paulo S. R. Diniz,et al.  On the robustness of set-membership adaptive filtering algorithms , 2017, EURASIP Journal on Advances in Signal Processing.

[5]  Stefan Werner,et al.  Set-membership affine projection algorithm for echo cancellation , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[6]  Pramod K. Varshney,et al.  Sequential Bayesian Estimation With Censored Data for Multi-Sensor Systems , 2014, IEEE Transactions on Signal Processing.

[7]  Paulo S. R. Diniz,et al.  On the robustness of the set-membership NLMS algorithm , 2016, 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM).

[8]  Yang Yang,et al.  Adaptive Queuing Censoring for Big Data Processing , 2018, IEEE Signal Processing Letters.

[9]  Paulo S. R. Diniz,et al.  Recursive Least-Squares algorithms for sparse system modeling , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Jesús Cid-Sueiro,et al.  Cooperative data censoring for energy-efficient communications in Sensor Networks , 2011, 2011 IEEE International Workshop on Machine Learning for Signal Processing.

[11]  Georgios B. Giannakis,et al.  Decentralized data selection for MAP estimation: A censoring and quantization approach , 2011, 14th International Conference on Information Fusion.

[12]  J. Deller.  Set membership identification in digital signal processing , 1989, IEEE ASSP Magazine.

[13]  Paulo S. R. Diniz,et al.  A simple set-membership affine projection algorithm for sparse system modeling , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[14]  Yih-Fang Huang,et al.  Set-membership adaptive equalization and an updator-shared implementation for multiple channel communications systems , 1998, IEEE Trans. Signal Process..

[15]  Paulo S. R. Diniz,et al.  Improved set-membership partial-update affine projection algorithm , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Shirish Nagaraj,et al.  Set-membership filtering and a set-membership normalized LMS algorithm with an adaptive step size , 1998, IEEE Signal Processing Letters.

[17]  Yih-Fang Huang,et al.  BEACON: an adaptive set-membership filtering technique with sparse updates , 1999, IEEE Trans. Signal Process..

[18]  Isao Yamada,et al.  Steady-State Mean-Square Performance Analysis of a Relaxed Set-Membership NLMS Algorithm by the Energy Conservation Argument , 2009, IEEE Transactions on Signal Processing.

[19]  Georgios B. Giannakis,et al.  Sensor-Centric Data Reduction for Estimation With WSNs via Censoring and Quantization , 2012, IEEE Transactions on Signal Processing.

[20]  P. Diniz,et al.  Set-membership affine projection algorithm , 2001, IEEE Signal Processing Letters.

[21]  Paulo S. R. Diniz,et al.  Data censoring with set-membership algorithms , 2017, 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[22]  Paulo S. R. Diniz,et al.  New Trinion and Quaternion Set-Membership Affine Projection Algorithms , 2017, IEEE Transactions on Circuits and Systems II: Express Briefs.