The objective of this study was to detect and monitor the flavor of tomatoes, as impacted by different postharvest handlings, including chilling storage (CS) and blanching treatment (BT). CS tomatoes were stored in a refrigerator at 5 °C and tested at storage day 0, 3, and 7. BT tomatoes were dipped in 50 or 100 °C water for 1 min, and tested immediately. The taste, mouth feel, and aroma of tomatoes were evaluated by testing the total soluble solid content (TSS), titratable acidity (TA), ratio of TSS and TA (TSS/TA), firmness, and electronic nose (E-nose) response to tomatoes. The experimental results showed that the CS can prevent taste and firmness loss to a certain extent, but the sensory results indicated that CS accelerated flavor loss due to the TSS/TA of CS tomatoes increasing slower than control. The taste and firmness of tomatoes were impacted slightly by 50 °C BT, and were significantly impacted by 100 °C BT. Based on physicochemical parameters, different postharvest handling treatments for tomatoes could not be classified except for the 100 °C BT treated tomatoes, which were significantly impacted in terms of taste and mouth feel. The E-nose is an efficient way to detect differences in postharvest handling treatments for tomatoes, and indicated significant aroma changes for CS and BT treated tomato fruit. The classification of tomatoes after different postharvest handling treatments, based on comprehensive flavor (physicochemical parameters and E-nose combined data), is better than that based on single physicochemical parameters or E-nose, and the comprehensive flavor of 100 °C BT tomatoes changed the most. Even so, the tomato flavor change during postharvest handlings is suggested to be detected and monitored by single E-nose data. The E-nose has also been proved as a feasible way to predict the TSS and firmness of tomato fruit rather than TA or TSS/TA, during the postharvest handing process.

The objective of this study was to find an intelligent and fast method to detect the type, blended ratio, and mixed ratio of ancient Pu’er tea, which is significant in maintaining order in the Pu’er tea industry. An electronic nose (E-nose) and a visible near infrared spectrometer (VIS/NIR spectrometer) were applied for tea sampling. Feature extraction was conducted using both the traditional method and a convolutional neural network (CNN) technique. Linear discriminant analysis (LDA) and partial least square regression (PLSR) were applied for pattern recognition. After sampling while using the traditional method, the analysis of variance (ANOVA) results showed that the mean differential value of each sensor should be selected as the optimal feature extraction method for E-nose data, and raw data comparison results showed that 19 peak/valley values and two slope values were extracted. While the format of E-nose data was in accord with the input format for CNN, the VIS/NIR spectrometer data required matrixing to meet the format requirements. The LDA and PLSR analysis results showed that CNN has superior detection ability, being able to acquire more local features than the traditional method, but it has the risk of mixing in redundant information, which can act to reduce the detection ability. Multi-source information fusion (E-nose and VIS/NIR spectrometer fusion) can collect more features from different angles to improve the detection ability, but it also contains the risk of adding redundant information, which reduces the detection ability. For practical detection, the type of Pu’er tea should be recognizable using a VIS/NIR spectrometer and the traditional feature extraction method. The blended ratio of Pu’er tea should also be identifiable by using a VIS/NIR spectrometer with traditional feature extraction. Multi-source information fusion with traditional feature extraction should be used if the accuracy requirement is extremely high; otherwise, a VIS/NIR spectrometer with traditional feature extraction is preferred.