Fig 1.
Research workflow for PCF-SPR biosensor model optimization.
Fig 2.
Schematic diagram of a Fiber-Optic SPR Biosensor system for biochemical detection.
Fig 3.
Cross-sectional diagram of a PCF-Based SPR biosensor.
Fig 4.
PCF-SPR biosensor: (a) meshed model, (b) core mode electric field distribution, and (c) SPP mode power flow distribution for y-polarized mode.
Table 1.
Description of dataset variables used in PCF-SPR biosensor modeling.
Fig 5.
Neff core and SPP mode phase matching at peak CL.
Fig 6.
Effect of d1and d2 variation on CL (a) wavelength vs. CL with different d1 for fixed d2 = 1µm (b) wavelength vs. CL with different d2 for fixed d1 = 1.2 µm.
Fig 7.
Effect of air hole diameter variation on SA (a) SA vs. wavelength with the changes of d1, (b) SA vs. wavelength with the changes of d2.
Fig 8.
(a) Wavelength vs. CL with variation of tg (b) wavelength vs. SA with different tg.
Fig 9.
(a) Wavelength vs. CL with variation of pitch (b) wavelength vs. SA based on pitch variation.
Fig 10.
CL vs. wavelength (a) na = 1.31-1.41, (b) na = 1.31-1.42.
Fig 11.
SA vs. wavelength for na = 1.31-1.41.
Table 2.
Optical properties of the proposed SPR biosensor for different na.
Table 3.
Optical properties for different na with best performing design parameters.
Table 4.
Maximum absolute SA values for different na.
Fig 12.
Polynomial regression analysis of resonance wavelength with the change of na.
Fig 13.
Actual vs. predicted Neff using RFR model.
Fig 14.
Validation of Neff predictions across different ML models.
Table 5.
Comparative performance metrics for Neff across different ML models.
Fig 15.
SHAP summary plot for Neff prediction.
Fig 16.
SHAP waterfall plot for Neff prediction.
Fig 17.
Actual vs. predicted CL using RFR model.
Fig 18.
Validation of different ML models for CL prediction against actual data.
Table 6.
Performance metrics of ML models for CL prediction.
Fig 19.
SHAP summary plot for CL prediction.
Fig 20.
SHAP waterfall plot for CL prediction.
Fig 21.
Actual vs. predicted result of SA using RFR model.
Fig 22.
Validation of SA predictions from various ML models against experimental data.
Table 7.
SA Prediction performance metrics for different ML models.
Fig 23.
SHAP summary plot of SA prediction.
Fig 24.
SHAP waterfall plot of SA prediction.
Table 8.
Comparison with previous work.