The occurrence of pests at high frequencies has been identified as a major cause of reduced citrus yields, and early detection and prevention are of great significance to pest control. At present, studies related to citrus pest identification using deep learning suffer from unbalanced sample sizes between data set classes, which may cause slow convergence of network models and low identification accuracy. To address the above problems, this study built a dataset including 5182 pest images in 14 categories. Firstly, we expanded the dataset to 21,000 images by using the Attentive Recurrent Generative Adversarial Network (AR-GAN) data augmentation technique, then we built Visual Geometry Group Network (VGG), Residual Neural Network (ResNet) and MobileNet citrus pest recognition models by using transfer learning, and finally, we introduced an appropriate attention mechanism according to the model characteristics to enhance the ability of the three models to operate effectively in complex, real environments with greater emphasis placed on incorporating the deep features of the pests themselves. The results showed that the average recognition accuracy of the three models reached 93.65%, the average precision reached 93.82%, the average recall reached 93.65%, and the average F1-score reached 93.62%. The integrated application of data augmentation, transfer learning and attention mechanisms in the research can significantly enhance the model’s ability to classify citrus pests while saving training cost and time, which can be a reference for researchers in the industry or other fields.

Real-time, rapid, accurate, and non-destructive batch testing of fruit growth state is crucial for improving economic benefits. However, for plums, environmental variability, multi-scale, occlusion, overlapping of leaves or fruits pose significant challenges to accurate and complete labeling using mainstream algorithms like YOLOv5. In this study, we established the first artificial dataset of plums and used deep learning to improve target detection. Our improved YOLOv5 algorithm achieved more accurate and rapid batch identification of immature plums, resulting in improved quality and economic benefits. The YOLOv5-plum algorithm showed 91.65% recognition accuracy for immature plums after our algorithmic improvements. Currently, the YOLOv5-plum algorithm has demonstrated significant advantages in detecting unripe plums and can potentially be applied to other unripe fruits in the future.

In the vanguard of oncological advancement, this investigation delineates the integration of deep learning paradigms to refine the screening process for Anticancer Peptides (ACPs), epitomizing a new frontier in broad-spectrum oncolytic therapeutics renowned for their targeted antitumor efficacy and specificity. Conventional methodologies for ACP identification are marred by prohibitive time and financial exigencies, representing a formidable impediment to the evolution of precision oncology. In response, our research heralds the development of a groundbreaking screening apparatus that marries Natural Language Processing (NLP) with the Pseudo Amino Acid Composition (PseAAC) technique, thereby inaugurating a comprehensive ACP compendium for the extraction of quintessential primary and secondary structural attributes. This innovative methodological approach is augmented by an optimized BERT model, meticulously calibrated for ACP detection, which conspicuously surpasses existing BERT variants and traditional machine learning algorithms in both accuracy and selectivity. Subjected to rigorous validation via five-fold cross-validation and external assessment, our model exhibited exemplary performance, boasting an average Area Under the Curve (AUC) of 0.9726 and an F1 score of 0.9385, with external validation further affirming its prowess (AUC of 0.9848 and F1 of 0.9371). These findings vividly underscore the method's unparalleled efficacy and prospective utility in the precise identification and prognostication of ACPs, significantly ameliorating the financial and temporal burdens traditionally associated with ACP research and development. Ergo, this pioneering screening paradigm promises to catalyze the discovery and clinical application of ACPs, constituting a seminal stride towards the realization of more efficacious and economically viable precision oncology interventions.

In social recommendation, a key yet overlooked issue is the mismatch between users’ social ties and item preferences that people often trust friends with divergent tastes. Existing graph-based methods either treat social and interaction graphs separately or merge them naively, failing to reconcile their semantic discrepancies, especially under data sparsity or cold-start conditions. We propose SoCoGNN, a novel framework that addresses this dissonance via two components: (1) a Graph Feature Fusion Network (GFFN) that jointly propagates information while preserving each graph’s semantics, and (2) a self-supervised contrastive objective that aligns user/item embeddings across views without extra labels, acting as an implicit regularizer. Experiments on three real-world datasets show SoCoGNN consistently outperforms state-of-the-art methods, achieving up to 20.24% relative gain in Precision@10, particularly in cold-start settings. Our work shows better social recommendation comes not from blindly trusting friends, but from intelligently reconciling friendship with taste.