Origin traceability is an important step to control the nutritional and pharmacological quality of food products. Boletus edulis mushroom is a well-known food resource in the world. Its nutritional and medicinal properties are drastically varied depending on geographical origins. In this study, three sensor systems (inductively coupled plasma atomic emission spectrophotometer (ICP-AES), ultraviolet-visible (UV-Vis) and Fourier transform mid-infrared spectroscopy (FT-MIR)) were applied for the origin traceability of 184 mushroom samples (caps and stipes) in combination with chemometrics. The difference between cap and stipe was clearly illustrated based on a single sensor technique, respectively. Feature variables from three instruments were used for origin traceability. Two supervised classification methods, partial least square discriminant analysis (FLS-DA) and grid search support vector machine (GS-SVM), were applied to develop mathematical models. Two steps (internal cross-validation and external prediction for unknown samples) were used to evaluate the performance of a classification model. The result is satisfactory with high accuracies ranging from 90.625% to 100%. These models also have an excellent generalization ability with the optimal parameters. Based on the combination of three sensory systems, our study provides a multi-sensory and comprehensive origin traceability of B. edulis mushrooms.

Boletus edulis and Boletus tomentipes are two well-known mushroom species which are widely consumed in Yunnan province due to their high nutritional and medicinal values. Fourier transform mid-infrared spectroscopy can determine exclusive spectra fingerprint of a sample and further analyse its quality when combined with appropriate chemometrics. In this study, identification and discrimination of B. edulis and B. tomentipes mushrooms from different geographical locations were performed based on Fourier transform mid-infrared spectroscopy and chemometrics. Principal component analysis, hierarchical cluster analysis, and partial least squares discriminant analysis allowed us to identify and discriminate mushroom samples depending on their unique metabolic spectral fingerprints. The range of 1800–400 cm⁻¹, which exhibited major characteristics of mushroom samples was selected for next analysis. The unsupervised principal component analysis and hierarchical cluster analysis showed that mushroom samples from different geographical locations could be effectively identified. Furthermore, the supervised partial least squares discriminant analysis method was used to predict unknown mushroom samples successfully based on developed calibration model. In conclusion, these results indicated that Fourier transform mid-infrared technique combined with appropriate chemometrics can be used as an effective and rapid strategy for quality control of B. edulis and B. tomentipes mushrooms with respect to their geographical locations. In addition, this technique also can be applied in other mushroom species for this purpose when coupled with reasonable chemometrics.

Discrimination of wild and cultivated mushrooms is important for their quality assessment. In this study, data fusion of infrared and ultraviolet spectroscopies combined with support vector machine or random forest were applied for the discrimination of wild and cultivated W. cocos and P. portentosusis. For the low- and mid-level data fusion classification models, the accuracies of validation set are 90.91% and 98.70%, respectively. However, the parameter c is too large which means the models are unreliable. For the high-level data fusion, the results showed that the accuracy of validation set is 100% and the sensitivity and specificity increased significantly compared to the single technique. Therefore, high-level data fusion combined with random forest is an effective method for the discrimination of wild and cultivated grown W. cocos and P. portentosus, and may be applied for protecting the steady development of the edible mushroom market.