Search

Objective: To improve the classification accuracy of strawberries. Methods: A method of strawberry classification based on improved CNN was proposed by improving CNN through mixing pool method. Firstly, through the combination of maximum pooling and average pooling techniques, a hybrid pooling method was obtained. Then, the hybrid pool method was used to improve the generalization ability of CNN model. After that, image data acquisition, image preprocessing and image feature extraction were carried out. Finally, sensitivity, specificity, accuracy, recall rate and F1 score were used to evaluate the effectiveness of the trained strawberry classification method. Results: The sensitivity, specificity, accuracy, recall rate and F1 score of the proposed method for strawberry classification in 16 pixel×16 pixel images reached 0.993, 0.993, 0.994, 0.992 and 0.991, respectively. Compared with the other five classification methods, the sensitivity, specificity, accuracy, recall rate and F1 score of the proposed method were improved by 3.44%, 3.96%, 4.26%, 3.92% and 4.08%, respectively. Conclusion: This method can achieve accurate classification of strawberries with different maturity, and is expected to provide technical support for the research and development of high-performance strawberry packaging robots and supermarket fruit automatic recognition machines.

Introduction: Diffuse high-grade gliomas are the most common malignant adult neuroepithelial tumors in humans and a leading cause of cancer-related death worldwide. The advancement of high throughput transcriptome sequencing technology enables rapid and comprehensive acquisition of transcriptome data from target cells or tissues. This technology aids researchers in understanding and identifying critical therapeutic targets for the prognosis and treatment of diffuse high-grade glioma. Methods: Spatial transcriptomics was conducted on two cases of isocitrate dehydrogenase (IDH) wild-type diffuse high-grade glioma (Glio-IDH-wt) and two cases of IDH-mutant diffuse high-grade glioma (Glio-IDH-mut). Gene set enrichment analysis and clustering analysis were employed to pinpoint differentially expressed genes (DEGs) involved in the progression of diffuse high-grade gliomas. The spatial distribution of DEGs in the spatially defined regions of human glioma tissues was overlaid in the t-distributed stochastic neighbor embedding (t-SNE) plots. Results: We identified a total of 10,693 DEGs, with 5,677 upregulated and 5,016 downregulated, in spatially defined regions of diffuse high-grade gliomas. Specifically, SPP1 , IGFBP2 , CALD1 , and TMSB4X exhibited high expression in carcinoma regions of both Glio-IDH-wt and Glio-IDH-mut, and 3 upregulated DEGs (SMOC1 , APOE , and HIPK2) and 4 upregulated DEGs (PPP1CB , UBA52 , S100A6 , and CTSB) were only identified in tumor regions of Glio-IDH-wt and Glio-IDH-mut, respectively. Moreover, Kyoto Encyclopedia of Genes and Genomes (KEGG) and gene ontology (GO) enrichment analyses revealed that upregulated DEGs were closely related to PI3K/Akt signaling pathway, virus infection, and cytokine-cytokine receptor interaction. Importantly, the expression of these DEGs was validated using GEPIA databases. Furthermore, the study identified spatial expression patterns of key regulatory genes, including those involved in protein post-translational modification and RNA binding protein-encoding genes, with spatially defined regions of diffuse high-grade glioma. Discussion: Spatial transcriptome analysis is one of the breakthroughs in the field of medical biotechnology as this can map the analytes such as RNA information in their physical location in tissue sections. Our findings illuminate previously unexplored spatial expression profiles of key biomarkers in diffuse high-grade glioma, offering novel insight for the development of therapeutic strategies in glioma. [ABSTRACT FROM AUTHOR]