Title :
Error triangle rule and dynamical misadjustment process in LMS algorithm
Author_Institution :
Dept. of Electron. Eng., Zhengzhou Univ., Henan, China
Abstract :
The author opens a new relationship among the mean square error (MSE), minimum mean square error (MMSE) and excess mean square error (EMSE). The relationship, which is defined as an error triangle rule, is that the square roots of the physical dimension above make a trigon. It accords with the cosine law in trigonometry and with the vector triangle rule. The dynamical misadjustment (DM) and correlative angle (CA) are defined and discussed. The relationship between dynamical misadjustment and steady-state misadjustment is discussed.<>
Keywords :
filtering theory; least mean squares methods; signal processing; stochastic processes; LMS algorithm; adaptive FIR filter; correlative angle; dynamical misadjustment process; error triangle rule; excess mean square error; mean square error; minimum mean square error; trigon; trigonometry; vector triangle rule; Delta modulation; Equations; Finite impulse response filter; Iterative algorithms; Least squares approximation; Mathematics; Mean square error methods; Medical services; Steady-state; Stochastic processes;
Conference_Titel :
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-1233-3
DOI :
10.1109/TENCON.1993.320487
