Design and Optimization of Porous-Core Photonic Crystal Fiber Biosensor for Label-Free White Blood Cell Classification Using Crayfish Equivariant Simplicial Quantum Attention Networks

Swift and precise categorization of white blood cells is crucial for diagnosis of several hematological conditions. Conventional techniques include intricate labeling procedures that are laborious and resource-demanding. A new porous core photonic crystal fiber biosensor was developed to tackle these issues, optimized using the Crayfish Equivariant Simplicial Quantum Attention Network (CESQAN) algorithm. The suggested sensor design utilizes graphene, capitalizing on its remarkable optical qualities and capacity to handle high-dimensional data while preserving geometric integrity. The graphene-based design increases interactions, leading to increased specificity and other output performance metrics. An improved sensor design was obtained by optimizing the design parameters, size, and chemical potential of graphene. The sensor has an outstanding quality factor of 11.468, higher accuracy of 99.92%, F1 score of 99.72%, lower processing time of 0.1 s, and a figure of merit of 2.887. To enhance the optimization and diminish computing complexity, CESQAN is included in this research for behavioral prediction. The model’s impressive performance suggests that the proposed biosensor has great promise for accurate and quick detection of white blood cells as well as the monitoring of health issues. The sensor’s superior performance metrics, together with its streamlined appearance, signify a significant progression in biosensing technology.