Advanced Mathematical Applications in Data Science

Kalman Filter: Data Modelling and Prediction

Author(s): Arnob Sarkar and Meetu Luthra * .

Pp: 24-50 (27)

DOI: 10.2174/9789815124842123010005

* (Excluding Mailing and Handling)

Abstract

We provide here an analysis of Kalman filter, which has wide applications in the experimental and observational fields. Kalman filter is a data fusion algorithm or a mathematical tool which is based on the estimation theory. It basically is a set of mathematical equations which provide a computational mechanism for evaluating the state of discrete processes with noisy data. In fact, observations and data analysis is a very key aspect of all theories. In any set of data, to make it useful, one has to minimize the error/noise by taking into consideration various aspects like the estimated values (the theoretical values), the measurement values, experimental errors and the estimated errors. We have shown here how this can be done using Kalman Filtering technique. Kalman Filter is a tool which can take the observational data and improvise it to identify the best possible value of the parameters involved. Kalman filter and its variants such as the extended Kalman filter have wide applications mainly in the field of communication e.g., in GPS receivers (global positioning system receivers), radio equipment used for filtering and removing noise from the output of laptop trackpads, image processing, face recognition and many more. 


Keywords: Acceleration, Big data, Data science, Extended kalman filter, GPS, Kalman filter, Mathematical modelling, Noise, Signals, Speed, Uncertainty.

Related Books
© 2024 Bentham Science Publishers | Privacy Policy