Abstract
In the first time we apply the statistics of the complex moments for selection of an optimal pressure sensor (from the available set of sensors) based on their statistical/correlation characteristics. The complex moments contain additional source of information and, therefore, they can realize the comparison of random sequences registered for almost identical devices or gadgets. The proposed general algorithm allows to calculate 12 key correlation parameters in the significance space. These correlation parameters allow to realize the desired comparison. New algorithm is rather general and can be applied for a set of other data if they are presented in the form of rectangle matrices. Each matrix contains N data points and M columns that are connected with repetitious cycle of measurements. In addition, we want to underline that the value of correlations evaluated with the help of Pearson correlation coefficient (PCC) has a relative character. One can introduce also external correlations based on the statistics of the fractional/complex moments that form a complete picture of correlations. To the PCC value of internal correlations one can add at least 7 additional external correlators evaluated in the space of fractional and complex moments in order to realize the justified choice. We do suppose that the proposed algorithm (containing an additional source of information in the complex space) can find a wide application in treatment of different data, where it is necessary to select the “best sensors/chips” based on their measured data, presented usually in the form of random rectangle matrices.
Highlights
The key problem that is followed from the statistics of the complex moments can be formulated as: What kind of new informative component is added by imaginary part of the complex moments in a feature space for evaluation of correlations more accurately in comparison with the conventional
We apply the statistics of the complex moments for evaluation of the
We apply the statistics of the complex moments for evaluation of the additional correlations
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. In real situations it is difficult to realize the requirements of this theorem and a potential researcher does not have conditions for its verification This brief analysis of the existing methods allows to put forward the following question: Is it possible to suppose a “universal” method that is free from the model assumptions and treatment errors and can be applied to any set of random functions?. We make necessary conclusions and discuss some details that can be useful for potential researches that will deal with their own random data
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
