Detection of Nanoparticles with Machine Learning Technique: Evaluation of Algorithm Performance

Nano-particles (NPs) are widely recognized as significant elements in a wide spectrum of goods, including aesthetics and electronics. Their application is expanding, despite the fact that their substantial financial and social possibilities has yet to be fulfilled. NPs possess distinct features that make them helpful in a range of purposes; nonetheless, their apparent toxicity increases security problems. The novelty of the study is autonomous detection of nanoparticles with improved surveillance. Advances have been done to comprehend the threats that NPs represent to human well-being and the surroundings, but further study and surveillance are required. In the past decade, Machine Learning (ML) approaches have used massive databases and computational capacity to make advancements in domains ranging from recognizing faces to genetics. In recent years, ML approaches are being used in nanotoxicology, with very promising findings. This study used ML techniques to autonomously detect NPs depending on their physical features, resulting in excellent classification accuracy. The findings show that ML algorithms are efficient in detecting nanoparticles and emphasize the requirement for more accurate characterization approaches to assure their safety in a variety of uses. The proposed ML algorithms was found to be efficient at detecting NPs, with the NN method outperforming all others with an accuracy of 0.95.

Перевод пока недоступен