FIRLMS

Filters a vector through the FIR LMS filter.

Syntax

IppStatus ippsFIRLMS_32f(const Ipp32f* pSrc, const Ipp32f* pRef, Ipp32f* pDst, int len, float mu, IppsFIRLMSState_32f* pState);

IppStatus ippsFIRLMS32f_16s(const Ipp16s* pSrc, const Ipp16s* pRef, Ipp16s* pDst, int len, float mu, IppsFIRLMSState32f_16s* pState);

Parameters

pState	Pointer to the FIR LMS filter state structure.
pSrc	Pointer to the source vector .
pRef	Pointer to the reference signal
pDst	Pointer to the output signal
len	Number of elements in the vector.
mu	Adaptation step.

Description

The function ippsFIRLMS is declared in the ipps.h file. This function filters a source vector pSrc using an adaptive FIR LMS filter.

Each of len iterations performed by the function consists of two main procedures. First, ippsLMS filters the current element of the source vector pSrc and stores the result in pDst. Next, the function updates the current taps using the reference signal pRef, the computed result signal pDst, and the adaptation step mu.

The filtering procedure can be described as a FIR filter operation:

Here the input sample to be filtered is denoted by x(n), the taps are denoted by h(i), and y(n) is the return value.

The function updates the filter coefficients that are stored in the filter state structure pState. Updated filter coefficients are defined as h_n+1(i) = h_n(i) + 2* mu* errVal * x(n-i),

where h_n+1(i) denotes new taps, h_n(i) denotes initial taps, mu and errVal are the adaptation step and adaptation error value, respectively. An adaptation error value errVal is computed inside the function as the difference between the output and reference signals.

Before using ippsFIRLMS, initialize the pState structure by calling the function ippsFIRLMSInitAlloc.

The code example below demonstrates how the use of the functions ippsFIRLMS_32f to filter a signal sample.

Return Values

ippStsNoErr	Indicates no error.
ippStsNullPtrErr	Indicates an error when one of the specified pointers is NULL.
ippStsSizeErr	Indicates an error when len is less or equal to 0.
ippStsContextMatchErr	Indicates an error when the state identifier is incorrect.

Filtering with the Function ippsFIRLMS

IppStatus firlms(void) {

     IppStatus st;

     Ipp32f taps = 0, x[LEN], y[LEN], mu = 0.03f;

     IppsFIRLMSState_32f* ctx;

     int i;

     /// no taps and no delay line from outside

     ippsFIRLMSInitAlloc_32f( &ctx, 0, 1, 0, 0 );

     /// make a const signal of amplitude 1 and noise it

     for(i=0; i<LEN; ++i) x[i] = 0.4f * rand()/RAND_MAX + 0.8f;

     st = ippsFIRLMS_32f( x, x+1, y, LEN-1, mu, ctx);

     /// get FIR LMS tap, it must be near to 1

     ippsFIRLMSGetTaps_32f(ctx, &taps);

     ippsFIRLMSFree_32f(ctx);

     printf_32f("FIR LMS tap fitted =", &taps, 1, st);

     return st;

Output:

    FIR LMS tap adapted = 0.986842