Characterization of integrated nanomaterials using deep learning method-based Mantis search algorithm

Abstract

The characterization of silver nanoparticles is vital for understanding unique properties and potential applications in various fields. This research aims to explore and evaluate characterization techniques to assess the quality and behavior of silver nanoparticles. Understanding characteristics is crucial for optimizing synthesis methods and ensuring safe and effective use in nanotechnology applications. In this research, bidirectional long short-term memory-Mantis search algorithm is deployed to characterizations of silver nanoparticle and also evaluates the characteristics of silver nanoparticle such as the accuracy, precision, recall, and f1-score values are recorded. The outcome of the recommended technique is implemented in MATLAB and benchmarked against existing approaches, demonstrating its effectiveness in achieving the proper characterization. The results indicate that the given approach outperforms existing techniques, demonstrating its effectiveness and also reduces the weighted square error by 0.6 and enhances the precession by 98.8%. This signifies not only the effectiveness, but also the efficiency of the given approach, indicating its potential for streamlining characterization processes and enhancing productivity in nanotechnology research and development.