The Kalman filter (KF) compare with the ridge regression backpropagation algorithm (RRBp) by conducting a numerical simulation study that relied on generating random data applicable to the KF and the RRBp in different sample sizes to determine the performance and behavior of the two methods. After implementing the simulation, the mean square error (MSE) value was calculated, which is considered a performance measure, to find out which two methods are better in making an estimation for random data. After obtaining the results, we find that the Kalman filter has better performance, the higher the randomness and noise in generating the data, while the other algorithm is suitable for small sample sizes and where the noise ratios are lower.
Neamah, I., Abdul Redhaa, Z. (2021). Kalman filter and ridge regression backpropagation algorithms. International Journal of Nonlinear Analysis and Applications, 12(2), 485-493. doi: 10.22075/ijnaa.2021.5075
MLA
Irtefaa A. Neamah; Zainab Abdul Redhaa. "Kalman filter and ridge regression backpropagation algorithms". International Journal of Nonlinear Analysis and Applications, 12, 2, 2021, 485-493. doi: 10.22075/ijnaa.2021.5075
HARVARD
Neamah, I., Abdul Redhaa, Z. (2021). 'Kalman filter and ridge regression backpropagation algorithms', International Journal of Nonlinear Analysis and Applications, 12(2), pp. 485-493. doi: 10.22075/ijnaa.2021.5075
VANCOUVER
Neamah, I., Abdul Redhaa, Z. Kalman filter and ridge regression backpropagation algorithms. International Journal of Nonlinear Analysis and Applications, 2021; 12(2): 485-493. doi: 10.22075/ijnaa.2021.5075
)