Automatic harvesting robots are crucial for enhancing agricultural productivity, and precise fruit maturity detection is a fundamental and core technology for efficient and accurate harvesting. Strawberries are distributed irregularly, and their images contain a wealth of characteristic information. This characteristic information includes both simple and intuitive features, as well as deeper abstract meanings. These complex features pose significant challenges to robots in determining fruit ripeness. To increase the precision, accuracy, and efficiency of robotic fruit maturity detection methods, a strawberry maturity detection algorithm based on an improved CES-YOLOv8 network structure from YOLOv8 was developed in this study. Initially, to reflect the characteristics of actual planting environments, the study collected image data under various lighting conditions, degrees of occlusion, and angles during the data collection phase. Subsequently, parts of the C2f module in the YOLOv8 model’s backbone were replaced with the ConvNeXt V2 module to enhance the capture of features in strawberries of varying ripeness, and the ECA attention mechanism was introduced to further improve feature representation capability. Finally, the angle compensation and distance compensation of the SIoU loss function were employed to enhance the IoU, enabling the rapid localization of the model’s prediction boxes. The experimental results show that the improved CES-YOLOv8 model achieves an accuracy, recall rate, mAP50, and F1 score of 88.20%, 89.80%, 92.10%, and 88.99%, respectively, in complex environments, indicating improvements of 4.8%, 2.9%, 2.05%, and 3.88%, respectively, over those of the original YOLOv8 network. This algorithm provides technical support for automated harvesting robots to achieve efficient and precise automated harvesting. Additionally, the algorithm is adaptable and can be extended to other fruit crops.

Background: Lipoxygenases (LOXs) are key enzymes in the unsaturated fatty acid oxidation reaction pathway and play an important regulatory role in the synthesis of fruit aroma volatiles. Methods: LOX gene family members were identified in the whole genome database of bitter gourd and analyzed bioinformatically. An RT-qPCR was used to analyze the expression differences in different tissues. Monoterpenes were determined by gas chromatography-mass spectrometry (GC-MS) technique. Results: A total of 12 LOX gene family members were identified in the genome. The expression of LOX genes varied significantly among the tissues of roots, stems, leaves, flowers, fruits, seeds and tendrils. A total of 29 monoterpenes were detected in the fruits of five different fruit colors of bitter gourd, mainly containing six types of alcohols, aldehydes, terpenes, ketones, esters and alkynes, with the highest relative content of alcohols. Conclusions: The present study provides a reference for further elucidation of the biological functions of the LOX gene in the synthesis pathway of aroma volatiles in bitter gourd.

Domestication has been proven to significantly impact the biosynthesis of plant secondary metabolites. Cultivated green jujube (Ziziphus mauritiana Lam.), as an important autotetraploid fruit crop widely planted in tropical regions, exhibits differential physicochemical traits compared with its wild progenitor. To assess the traits lost in cultivated green jujube during domestication, the study performed comprehensive genomic, transcriptomic and metabolomic investigations of flavonoid pathways in wild and cultivated green jujube. Based on the four haplotype genomes of wild and cultivated green jujube, for the first time, the study bulk-identified 16 key gene families associated with flavonoid biosynthesis. Collinearity analysis revealed that tandem duplication was the predominant event in flavonoid-related genes rather than WGD. Through the expression profiles in different tissues, the distinct member of these gene families was classified as “redundant” or “functional”. Transcriptomic analyses illustrated the significant differential expressions (p < 0.05) of 13 flavonoid-related gene families in fruits of six cultivated and three wild green jujube accessions, except for FLS, LAR and PPO. The wild green jujube fruits accumulated more abundance of flavonoid metabolites than in cultivated fruits (p < 0.0001), as evidenced by upregulated chalcones, dihydroflavonol, isoflavones and flavonoid carbonoside. Gene–metabolite co-expression modules further validated the potential transcription regulators, such as BBX21, WRI1 and bZIP44. Together, the study suggested a genomic, transcriptomic and metabolic perspective for domestication regarding fruit flavonoid pathways in green jujube, which provides a valuable genetic resource for fruit quality improvement in cultivated green jujube.

The grading of green jujube is a key factor in improving production efficiency and market competitiveness. However, traditional grading methods are inefficient, imprecise, and struggle to detect minor damages. This study proposes an improved BCW-YOLO deep learning model specifically designed for automated grading of green jujube. The model integrates a Bidirectional Feature Pyramid Network (BiFPN) and a Contextual Transformer Attention (COT) mechanism to enhance feature fusion accuracy and capture fine-grained details. In addition, the WIoU v3 loss function is introduced to optimize object localization performance. By constructing a multi-angle green jujube dataset and applying data augmentation techniques, the model’s generalization capability was significantly improved. The results of the experiement indicate that the improved BCW-YOLO achieves precision, recall, mAP, and F1 score of 90.87%, 92.12%, 95.66%, and 91.49%, respectively, representing increases of 1.93%, 2.77%, 1.58%, and 2.34% compared to the original YOLO model. Through comprehensive validation using confusion matrices, PR curves, heatmap analyses, and ablation studies, the model’s performance was thoroughly verified. Compared with other YOLO series models, BCW-YOLO performs exceptionally well in detecting minor damages, demonstrating its potential in practical agricultural grading. The findings provide a new technical approach for precise grading and automated sorting of green jujube, showing promising application prospects.

Peanut, as an important economic crop, is widely cultivated and rich in nutrients. Classifying peanuts based on the number of seeds helps assess yield and economic value, providing a basis for selection and breeding. However, traditional peanut grading relies on manual labor, which is inefficient and time-consuming. To improve detection efficiency and accuracy, this study proposes an improved BTM-YOLOv8 model and tests it on an independently designed pod detection device. In the backbone network, the BiFormer module is introduced, employing a dual-route attention mechanism with dynamic, content-aware, and query-adaptive sparse attention to extract features from densely packed peanuts. In addition, the Triple Attention mechanism is incorporated to strengthen the model’s multidimensional interaction and feature responsiveness. Finally, the original CIoU loss function is replaced with MPDIoU loss, simplifying distance metric computation and enabling more scale-focused optimization in bounding box regression. The results show that BTM-YOLOv8 has stronger detection performance for ‘Quan Hua 557’ peanut pods, with precision, recall, mAP50, and F1 score reaching 98.40%, 96.20%, 99.00%, and 97.29%, respectively. Compared to the original YOLOv8, these values improved by 3.9%, 2.4%, 1.2%, and 3.14%, respectively. Ablation experiments further validate the effectiveness of the introduced modules, showing reduced attention to irrelevant information, enhanced target feature capture, and lower false detection rates. Through comparisons with various mainstream deep learning models, it was further demonstrated that BTM-YOLOv8 performs well in detecting ‘Quan Hua 557’ peanut pods. When comparing the device’s detection results with manual counts, the R2 value was 0.999, and the RMSE value was 12.69, indicating high accuracy. This study improves the efficiency of ‘Quan Hua 557’ peanut pod detection, reduces labor costs, and provides quantifiable data support for breeding, offering a new technical reference for the detection of other crops.

This study investigated the effects of solid-state fermentation with a compound microbial inoculant on the nutritional composition, microbial community structure, and metabolic products of green jujube (Ziziphus mauritiana Lam.) straw. The results demonstrated that solid-state fermentation significantly enhanced the nutritional value of the straw, as evidenced by a marked increase in crude protein content and significant reductions in neutral detergent fiber (NDF), acid detergent fiber (ADF), and cellulose content. Metagenomic analysis revealed that fermentation substantially altered the microbial community structure of the straw, with a pronounced increase in the relative abundance of bacteria from the phylum Pseudomonadota (particularly genera such as Klebsiella and Enterobacter), and an upward trend in the abundance of fungi from the phylum Basidiomycota (Astraeus). Functional annotation indicated that fermentation enhanced the potential of the straw microbiota in genetic information processing, ABC transporters, and starch and sucrose metabolism, while attenuating the oxidative phosphorylation pathway. Metabolomic analysis identified 1176 differential metabolites, with significant increases in bioactive compounds such as peptides, amino acids, polyunsaturated fatty acids, and flavonoids following fermentation. Correlation analysis further revealed significant associations between specific microorganisms (Klebsiella, Enterobacter, and Aureobasidium) and key metabolites (amino acids, peptides, and flavonoids) in the fermented green jujube straw. This study confirms that solid-state fermentation can effectively improve the nutritional value and functional properties of the agricultural by-product green jujube straw by reshaping its microbial ecosystem and metabolic network.