Optimization of Novel 2D Material Based SPR Biosensor Using Machine Learning

Area of Science:

• Nanomaterials Science
• Biomedical Engineering
• Analytical Chemistry

Background:

• Biosensors are crucial for health monitoring, requiring sensitive detection of biomolecules.
• Graphene's unique properties make it suitable for biosensor design.
• Hemoglobin detection is vital for diagnosing various health conditions.

Purpose of the Study:

• To propose and analyze a novel Graphene-Gold-Silver hybrid structure based on Zinc Oxide for enhanced biomolecule detection.
• To achieve highly sensitive detection of hemoglobin.
• To investigate the optical and electrical properties of the proposed hybrid structure.

Main Methods:

• Design and simulation of a Graphene-Gold-Silver hybrid structure on a Zinc Oxide base.
• Analysis of reflectance and electric field (E-field) properties.
• Optimization of physical parameters for enhanced sensitivity.
• Application of a machine learning algorithm for reflectance prediction.

Main Results:

• The proposed hybrid biosensor achieved a maximum sensitivity of 1000 nm/RIU for hemoglobin detection.
• The electric field results correlated well with the reflectance results, validating the design.
• Optimization of physical parameters significantly improved sensor sensitivity.
• Machine learning model demonstrated high prediction accuracy, reducing simulation resources.

Conclusions:

• The Graphene-Gold-Silver hybrid structure offers a highly sensitive platform for biosensing applications.
• The developed biosensor shows significant potential for real-time hemoglobin monitoring.
• The integration of machine learning aids in efficient design optimization and simulation.