A new modification of Kalman filter algorithm

This study is concerned with estimating random data and in the presence of noise, as we used the Kalman filter estimation method through the backpropagation algorithm to estimate these data. This is because modern estimation methods have become more important as they were in the past years due to the expansion of the field of science and technology and the increasing data Therefore, the interest became in estimation methods that solve the noise problems that occur in the data. The Kalman filter has become one of the most popular and most reliable estimators in case of data noise. This study tests the use of the Kalman filter and Back Propagation algorithm to estimate the data containing noise and compare the results with the proposed method on the same data. The data is generated randomly in the simulation study. The results showed that Kalman is more efficient in filtering noise from the data and giving a lower mean square error compared to the backpropagation algorithm, but the results of the proposed method outperformed the results of the Kalman filter and the backpropagation with the least possible error.

Keywords:

Kalman filter , backpropagation algorithms , estimation , machine learning