Abstract
Researches described in the paper are aimed at studying the methods of data preprocessing from a sample of observations of a system characterized by input-output values of variables. We consider the data containing omissions and outliers. Algorithms for leveling outliers in a sample of observations, as well as algorithms for filling data gaps are presented. In addition, it is implemented a data repair algorithm that is able to recover lost values (outliers) after their exclusion. Our studies are useful in geographic information systems or in the analysis of information received from satellites during remote sensing of the earth.
Highlights
The sample of the input-output observations of the system under study plays a valuable role in solving the problem of identification
Author in paper [2] explores the potential of using geographical information systems (GIS) and paper [3] considers the applied side of working with quality data in such systems
The computational experiment showed that sampling censoring gives more accurate simulation results than filling omissions in the data, if both of these methods are used together, the final approximation results show the highest accuracy
Summary
The sample of the input-output observations of the system (object) under study plays a valuable role in solving the problem of identification. For example, during the process of shooting or transmitting data from satellites in cases when the transfer process was interrupted or due to some technical malfunction of the shooting device All of this may interfere with the further processing of the image. As a result, such significantly deviate values in data affects the final accuracy of the object of study approximation. The paper discusses two methods of data preprocessing, where the first one is a method of censoring a sample of observations to remove outliers, and the second one is restoring omissions using a non-parametric identification algorithm. After removing the outliers, it was decided to review and implement the data repair algorithm, which increase the accuracy of object modeling
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
