NOVEL STEEPEST DESCENT ADAPTIVE FILTER DERIVED FROM NEW PERFORMANCE-FUNCTION WITH ADDITIONAL EXPONENTIAL TERM

A new steepest descent adaptive filter algorithm derived from a newly devised performance index function is presented. The performance funct ion of the new algorithm is introduced from that of the least mean squ are (LMS) considering that the stochastic steepest descent method util ises a gradient search in order to minimise the performance function i teratively. Through mathematical analyses and computer simulations, it is verified that there are significant improvements in convergence sp eed and misadjustment error. Nevertheless its computational simplicity and robustness are maintained with little degradation (compared to th ose of the LMS algorithm). The new algorithm can be interpreted as a n ew kind of variable step size adaptive algorithm, and in this respect a modified method is proposed in order to reduce the noise caused by f luctuation of the varying step size.