Green fruit detection is of great significance for estimating orchard yield and the allocation of water and fertilizer. However, due to the similar colors of green fruit and the background of images, the complexity of backgrounds and the difficulty in collecting green fruit datasets, there is currently no accurate and convenient green fruit detection method available for small datasets. The YOLO object detection model, a representative of the single-stage detection framework, has the advantages of a flexible structure, fast inference speed and excellent versatility. In this study, we proposed a model based on the improved YOLOv5 model that combined data augmentation methods to detect green fruit in a small dataset with a background of similar color. In the improved YOLOv5 model (YOLOv5-AT), a Conv-AT block and SA and CA blocks were designed to construct feature information from different perspectives and improve the accuracy by conveying local key information to the deeper layer. The proposed method was applied to green oranges, green tomatoes and green persimmons, and the mAPs were higher than those of other YOLO object detection models, reaching 84.6%, 98.0% and 85.1%, respectively. Furthermore, taking green oranges as an example, a mAP of 82.2% was obtained on the basis of retaining 50% of the original dataset (163 images), which was only 2.4% lower than that obtained when using 100% of the dataset (326 images) for training. Thus, the YOLOv5-AT model combined with data augmentation methods can effectively achieve accurate detection in small green fruit datasets under a similar color background. These research results could provide supportive data for improving the efficiency of agricultural production.

This paper reported a real-time detection strategy for Hg²⁺ inspired by the visible spectrophotometer that used a smartphone as a low-cost micro-spectrometer. In combination with the smartphone’s camera and optical accessories, the phone’s built-in software can process the received light band image and then read out the spectral data in real time. The sensor was also used to detect gold nanoparticles with an LOD of 0.14 μM, which are widely used in colorimetric biosensors. Ultimately, a gold nanoparticles-glutathione (AuNPs-GSH) conjugate was used as a probe to detect Hg²⁺ in water with an LOD of 1.2 nM and was applied successfully to natural mineral water, pure water, tap water, and river water samples.

Determination of Occidental pear (Pyrus communis) ripening is difficult because the appearance of Occidental pears does not change significantly during the ripening process. Occidental pears at different ripening stages release different volatile organic compounds (VOCs), which can be used to determine fruit ripeness non-destructively and rapidly. In this study, VOCs were detected using proton-transfer-reaction mass spectrometry (PTR-MS). Notably, data were acquired within 1 min. Occidental pears harvested at five separate times were divided into three ripening stages: unripe, ripe, and overripe. The results showed that the composition of VOCs differed depending on the ripening stage. In particular, the concentrations of esters and terpenes significantly increased during the overripe stage. Three ripening stages were clearly discriminated by heatmap clustering and principal component analysis (PCA). This study provided a rapid and non-destructive method to evaluate the ripening stages of Occidental pears. The result can help fruit farmers to decide the optimum harvest time and hence reduce their economic losses.