.png){kind=icon}
.png){kind=icon}
Return
Quaternion Euclidean Direction Search Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.dsp.2026.106299.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Quaternion adaptive filters are of great importance in the analysis and treatment of three-dimensional and four-dimensional signals. However, when the output signal is disturbed by noise, the effectiveness of the quaternion least mean square (QLMS) algorithm, whose weight update function is merely based on the instantaneous gradient estimation, degrades significantly. Furthermore, the QEDS algorithm is enhanced by incorporating two different sliding-window strategies. Specifically, a finite sliding window (FSW) mechanism is developed to improve steady-state accuracy, leading to the FSWQEDS algorithm. In contrast, a variable sliding window (VSW) strategy is employed to enhance adaptability to an abruptly changed system, resulting in the VSWQEDS algorithm. The former achieves reduced steady-state error, while the latter provides improved tracking capability and results in a smaller steady-state error under abruptly changed conditions. Moreover, the stability of the QEDS algorithm is analyzed. Simulations validate the effectiveness of the proposed algorithms compared to the existing quaternion adaptive filtering method.
Journal
D
IF:
3
Papers:
653
Citations:
0