Medical Defense Nanorobots (MDNRs): a new evaluation and selection of controller criteria for improved disease diagnosis and patient safety using NARMA(L2)-FOP + D(ANFIS)^µ – Iλ-based Archimedes Optimization Algorithm

This article addresses the complexity of optimizing movements in Medical Defense Nanorobots (MDNRs) by proposing a novel integration approach. The challenge lies in selecting the Archimedes Optimization Algorithm (AOA) for MDNR movements, considering specific criteria for fractional-order proportional-integral-derivative (FOPID) controller gains. To overcome this, the study introduces a three-phase approach: MDNR-based NARMA-L2 controller Pre-process and Identification, Enhancement of NARMA-L2 controller-based NARMA(L2)- \(FOP+{D(ANFIS)}^{\mu } - {I}^{\lambda }\) $FOP+{D(ANFIS)}^{\mu }-I^{\lambda }$ , and Evaluation of FOPID criteria-based AOA. This approach integrates NARMA-L2 for criterion weighting and ANFIS for AOA selection, validated through NARMA(L2)- \(FOP+{D(ANFIS)}^{\mu } - {I}^{\lambda }\) $FOP+{D(ANFIS)}^{\mu }-I^{\lambda }$ evaluation, showcasing the efficacy of the proposed methodology.