Artificial Intelligence and Electrical & Electronics Engineering: AIEEE Open Access
New Modeling of Prime Number Series, IN-PAR
Abstract
Ricardo Oses Rodriguez
Objective The objective of our work is aimed at modeling prime number series using the ROR methodology and using the IN-PAR methodology as an improvement of the former.
Methods The Objective Regressive Methodology, ROR, and the IN-PAR methodology are used. To carry out this work, a self- developed database consisting of 25 cases of prime numbers less than 100 was used. Subsequently, this series was modeled according to the ROR methodology and with the IN-PAR methodology using the first 25 cases, the errors of the predicted values with respect to the actual values were calculated and descriptive statistics of the corresponding errors were obtained.
Results Perfect models are obtained for the prime number series using both methodologies. The IN-PAR methodology describes errors with zero mean, just like the ROR methodology, and a lower standard deviation than the ROR methodology. Both methodologies offer excellent results for prime numbers.
Discussion Our work shows that the IN-PAR methodology obtains better results than ROR for the prime number series.
Conclusions Perfect models are obtained for all series using both methodologies. The IN-PAR methodology offers better results for prime numbers than the ROR methodology. This alternative methodology to ROR is very interesting for artificial intelligence of computing machines. These methodologies could mean savings in machine time in the search for prime numbers, which are so important in cryptography.