Data fusion of near-infrared and Raman spectroscopy: An innovative tool for non-destructive prediction of the TVB-N content of salmon samples.

[Display omitted] • Two molecular spectroscopic techniques were used to predict TVB-N content in salmon. • 2D-COS was proposed to select the spectral feature variables of NIR and Raman spectroscopy. • The order of mainly chemical information and molecular changes were determined. • The low-level data fusion of NIR and Raman spectra produced good prediction results. Total volatile basic nitrogen (TVB-N) serves as a crucial indicator for evaluating the freshness of salmon. This study aimed to achieve accurate and non-destructive prediction of TVB-N content in salmon fillets stored in multiple temperature settings (−20, 0, −4, 20 °C, and dynamic temperature) using near-infrared (NIR) and Raman spectroscopy. A partial least square support vector machine (LSSVM) regression model was established through the integration of NIR and Raman spectral data using low-level data fusion (LLDF) and mid-level data fusion (MLDF) strategies. Notably, compared to a single spectrum analysis, the LLDF approach provided the most accurate prediction model, achieving an R2 P of 0.910 and an RMSEP of 1.922 mg/100 g. Furthermore, MLDF models based on 2D-COS and VIP achieved R2 P values of 0.885 and 0.906, respectively. These findings demonstrated the effectiveness of the proposed method for precise quantitative detection of salmon TVB-N, laying a technical foundation for the exploration of similar approaches in the study of other meat products. This approach has the potential to assess and monitor the freshness of seafood, ensuring consumer safety and enhancing product quality. [ABSTRACT FROM AUTHOR]