Mathematical Modeling Optimization Based on Machine Learning

Optimization techniques plays a significant role in every engineering domains, particularly Artificial Intelligence (AI), Machine learning (ML) and operational systems. These algorithms provides the mathematical framework for determining the best possible solutions under various conditions. Several optimization algorithms, like Particle swarm optimization (PSO), Ant-colony optimization (ACO), Bat algorithms, and Honey Badger Optimization Model are utilized in ML models for the tuning process, which enhances the performance of the detection process. However, establishing the fine balance between the different stages in the optimization algorithms is considered to be mandatory, which has its own affect on ability to detect. To overcome this aforementioned challenge, this research paper proposes the novel integration of a chaotic variable in the honey-badger optimization model for increasing the search path to attain the global optimum solution with less complex overhead. To enrich the searching behaviour and to avoid being trapped into local optimum, Multi-scroll chaotic maps are incorporated in the starling murmuration optimization model for efficiently generate solutions suitable for tuning the ML algorithms. The suggested technique statistically evaluated and compared to other traditional optimization model. Empirical outcomes demonstrate that the suggested incorporation has consumed only 5.00 s to achieve the global optimal solutions and enhanced the performance of ML by 23 % when compared with the traditional algorithm.