The magnetic dipole (MD) and electric quadrupole (EQ) moments, which are fundamental properties of the atomic nucleus, are two measurable quantities vital for understanding nuclear structure. Although the ground-state MD and EQ moments of many nuclei have been measured using various experimental techniques, creating a substantial pool of experimental data, no complete nuclear model or analysis system has yet been developed to fully explain this nuclear data. A similar situation arises in the analysis of ground-state MD and EQ moments for nuclei with odd numbers of neutrons and protons. In recent years, machine learning techniques have gained attention for their applcation in data analysis and prediction in complex systems, such as multi-nucleon systems like individual nuclei.

In this context, the Adaptive Neuro-Fuzzy Inference System (ANFIS) will be used for the first time to address the gap in analyzing and predicting ground-state MD and EQ moment data for individual nuclei. Based on the promising results of the ANFIS approach in nuclear data modeling and prediction, it is expected to deliver successful outcomes in modeling, analyzing, and predicting MD and EQ moments for individual nuclei across different mass regions. Therefore, the project aims to contribute to the original value of predicting MD and EQ moments, which have not yet been measured, for odd nuclei in the Z≤29 (A≤56) region, including ^8,10N(Z=7), ^12,14,16F (Z=9), ^16,18Na (Z=11), ^20,22,24Al (Z=13), ^26,30,34,36P(Z=15), ^34,40Cl (Z=17), ^36,38,42Sc (Z=21), ^40,42,44V (Z=23), ^44,46,48,50Mn (Z=25), ^48,50,52,54Co (Z=27), ^52,54,56Cu (Z=29), using the ANFIS model. The obtained results will be compared with existing experimental and theoretical MD and EQ moment data to generate a comprehensive dataset, contributing new data to the literature.