Investigation of nonlinear relationship of surface enhanced Raman scattering signal for robust prediction of thiabendazole in apple

Thiabendazole (TBZ) is extensively used in agriculture to control molds; residue of TBZ may pose a threat humans. Herein, surface-enhanced Raman spectroscopy (SERS) coupled variable selected regression methods have been proposed as simple and rapid quantification technique. The nonlinear correlation between the SERS data was first diagnosed by augmented partial residual plots method calculated runs test. [email protected] NPs with strong enhancement factor (EF = 4.07 × 106) signal active material collect spectra from TBZ. Subsequently, three models were comparatively investigated competitive adaptive reweighted sampling-extreme learning machine (CARS-ELM) achieved higher coefficient (Rp2 0.9406) lower root-mean-square-error prediction (RMSEP 0.5233 mg/L). Finally, recoveries apple samples 83.02–93.54% relative standard deviation (RSD) value < 10%. Therefore, CARS-ELM could be employed sensitive approach for detection Fuji apples.