Professional Documents
Culture Documents
Alternative Approach For Computing The Activation Factor of The PNLMS Algorithm
Alternative Approach For Computing The Activation Factor of The PNLMS Algorithm
Authors Francisco das C. de Souza, Orlando Jos Tobias , and Rui Seara
LINSE - Circuits and Signal Processing Laboratory Federal University of Santa Catarina {fsouza, orlando, seara}@linse.ufsc.br
Dennis R. Morgan
Bell Laboratories, Alcatel-Lucent drrm@bell-labs.com
INTRODUCTION
Sparse impulse responses are encountered in many real-world applications: Communications, acoustics, seismic and chemical processes NLMS algorithm (the same step-size value for all filter coefficients) Slow convergence Algorithms that exploit the sparse nature of the impulse response: PNLMS (proportionate normalized least-mean-square) PNLMS ++ (both the NLMS and PNLMS are used in the coefficient vector update) IPNLMS (improved PNLMS) SC-PNLMS (sparseness controlled PNLMS)
INTRODUCTION
The standard PNLMS algorithm Formulation Coefficient update ( N 1) :
w (n + 1) = w (n) +
g N (n) ]
Individual gain:
gi ( n) =
i (n)
i (n)
i =1
Proportionality function:
Activation factor:
INTRODUCTION
The standard PNLMS algorithm performance depends on predefined parameters: (initialization) (proportionality or activation) These parameters are related to the algorithm variable, termed ACTIVATION FACTOR f ( n) The initialization parameter permits starting the adaptation process at n = 0, when all filter coefficients are initialized to zero.
f (0) = max , w (0) = The proportionality parameter prevents an individual coefficient from freezing when its magnitude is much smaller than the largest coefficient magnitude.
A central point: How to set suitable values for these parameters, since they impact the algorithm convergence speed?
INTRODUCTION
Activation factor in the standard PNLMS algorithm
Common to all coefficients, computed sample-by-sample. Depends on w (n) . Leads to a gain distribution between the adaptive filter coefficients not entirely in line with the concept of proportionality.
Proposed approach: Individual activation factor PNLMS (IAF-PNLMS) An individual activation factor is used for each adaptive filter coefficient. Each individual activation factor is computed in terms of the corresponding coefficient magnitude.
Consequence For impulse responses having high sparseness, numerical simulations show that the proposed approach has faster convergence as well as faster response to perturbations of the system plant than both the PNLMS and IPNLMS algorithms.
g inactive (n) =
i (n)
i =1
f ( n)
giactive (n) =
i (n)
i =1
wi (n)
Total gain distributed over the filter coefficients at each iteration NN tr [G (n) ] = N active f (n) + giactive (n) = 1 iA n ( ) i
i =1
The activation factor affects the gains assigned to both active and inactive coefficients.
Standard PNLMS algorithm performance with respect f (n) Scenario for all numerical simulations
Sparse impulse response p with N =100 coefficients, Active coefficient values: {0.1, 1.0, 0.5, 0.1} located at positions {1, 30, 35, 85}, respectively. S (p) = 0.9435 Input signal: Correlated unity-variance AR(2) process with = 74
= 0.5, = 0.01
i ,
Desired condition
p1 = 0.1, p30 = 1.0 g30 (n) > g1 (n)
1) When wi (n) is an active coefficient, its gain is always proportional to wi (n) . 2) When wi (n) is inactive, the gain is not proportional to wi (n) .
Objective:
To overcome the drawback (2) by making the gain gi (n) tend towards being proportional to wi (n) even when wi (n) is inactive. i (n) = max[ fi (n), wi (n) ] 1 inactive f (n) is replaced by fi (n) f i ( n) ( n) = N gi i (n) i =1
i = 1, 2, , N
f i ( n) > 0 ,
i = 1, 2, , N
fi (n) = wi (n) + (1 )i (n 1)
C2
By considering that no knowledge of the system plant is available a priori, it is reasonable to choose = 1/ 2 The activation factors are initialized with a small positive constant (typically, fi (0) = 102 / N )
IAF-PNLMS
NUMERICAL SIMULATIONS
Example 1 A perturbation in the plant takes place at n = 2500, whereby the plant
vector p is changed to p
Parameter values:
NUMERICAL SIMULATIONS
Example 2 A perturbation in the plant takes place at n = 2500, whereby the plant vector
CONCLUSIONS
The IAF-PNLMS algorithm uses an individual activation factor for each adaptive filter coefficient.
The IAF-PNLMS algorithm presents better gain distribution than the PNLMS and IPNLMS algorithms.
The IAF-PNLMS algorithm provides an improvement in convergence speed for plant impulse responses having high sparseness.