Incremental Modified Leaky LMS

Incremental Least means squares algorithm is one of the simplest algorithm for parameter estimation in distributed wireless networks, which find a wide range of applications from monitoring environmental parameters to satellite positioning. Digital implementation of adaptive filters results in quantization errors and finite precision errors, which makes the ILMS algorithm to suffer from drift problem. Incremental Leaky LMS algorithm introduces a leakage factor in the update equation and overcomes the drift problem. But the overall performance of ILLMS is similar to ILMS in terms of convergence speed. To overcome this an incremental Modified Leaky LMS is proposed based on MLLMS algorithm which in turn derived from the Least Sum of Exponentials algorithm. LSE algorithm employs sum of exponentials of errors in its cost function and it results in convex and smooth error surface with more steepness, which results in faster convergence rate. Simulation results prove that the proposed IMLLMS outperforms the ILLMS.

[1]  B. Widrow,et al.  A variable leaky LMS adaptive algorithm , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

[2]  Ali H. Sayed,et al.  Fundamentals Of Adaptive Filtering , 2003 .

[3]  Sananda Kumar,et al.  Distributed Incremental Leaky LMS , 2015, 2015 International Conference on Communications and Signal Processing (ICCSP).

[4]  Ali H. Sayed,et al.  Incremental Adaptive Strategies Over Distributed Networks , 2007, IEEE Transactions on Signal Processing.

[5]  John M. Cioffi,et al.  Limited-precision effects in adaptive filtering , 1987 .

[6]  Benoît Champagne,et al.  A diffusion LMS strategy for parameter estimation in noisy regressor applications , 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

[7]  Bhaskar Krishnamachari,et al.  Distributed parameter estimation for monitoring diffusion phenomena using physical models , 2004, 2004 First Annual IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks, 2004. IEEE SECON 2004..

[8]  C. Richard Johnson,et al.  Parameter drift in LMS adaptive filters , 1986, IEEE Trans. Acoust. Speech Signal Process..

[9]  Kegen Yu,et al.  Modified Leaky LMS Algorithms Applied to Satellite Positioning , 2014, 2014 IEEE 80th Vehicular Technology Conference (VTC2014-Fall).

[10]  Tyseer Aboulnasr,et al.  Leaky LMS algorithm: MSE analysis for Gaussian data , 1997, IEEE Trans. Signal Process..

[11]  Gregory J. Pottie,et al.  Instrumenting the world with wireless sensor networks , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[12]  Bernard Widrow,et al.  The least mean fourth (LMF) adaptive algorithm and its family , 1984, IEEE Trans. Inf. Theory.

[13]  C. Boukis,et al.  A Generalised Mixed Norm Stochastic Gradient Algorithm , 2007, 2007 15th International Conference on Digital Signal Processing.