Karst wetlands are being seriously damaged, and protecting it has become an important matter. Karst vegetation is the essential component of wetland and plays an important role in in the ecological functions of wetland ecosystems. Classifying karst vegetation is important for karst wetlands protection and management. This paper addressed to classify karst vegetation in Huixian National Wetland Park, located in China using the improved SegNet Deep-Learning Algorithm and UAV images. This study proposed a method to fuse single-class SegNet models using the maximum probability algorithm for karst vegetation classification, and compared with object-based RF classification and multi-class SegNet classification, respectively. This paper evaluated the performance of multi-class SegNet model and fusion of single-class SegNet model with different EPOCH values for mapping karst vegetation. A new optimized post-classification algorithm was proposed to eliminate the stitching traces caused by SegNet model prediction. The specific conclusions of this paper include the followings:(1) fusion of four single-class SegNet models produced better classification for karst wetland vegetation than multi-class SegNet model, and achieved the highest overall classification accuracy (87.34%); (2) The optimized post-classification algorithm was able to improve prediction accuracy of SegNet model, and it could eliminate splicing traces; (3) The karst wetland vegetation classifications produced by single-class SegNet model outperformed multi-class SegNet model, and improved classification accuracy(F1-Score) between 10%~25%;(4)The EPCOH values and textural feature important impact on karst wetland vegetation classifications. The SegNet model with EPCOH 15 achieved greater classification accuracy(F1-Score) than the model with EPOCH 5 or 10. The textural feature improved improves the capability of the SegNet model for mapping karst vegetation;(5) Fusion of single-class SegNet models and object-based RF model could provide high classifications results for karst wetland vegetation, and both achieved greater 87% overall accuracy.

Glioblastoma (GBM) is a major type of primary brain tumors without ideal prognosis and it’s necessary to find novel compound possessing therapeutic effect. Chrysomycin A (Chr-A) has been reported to inhibit the proliferation, migration and invasion of U251 and U87-MG cells, but the mechanism of Chr-A against glioblastoma in vivo and whether Chr-A modulates apoptosis of neuroglioma cells is unclear.The present study was to elucidate the potential of Chr-A against glioblastoma in vivo and how Chr-A modulates apoptosis of neuroglioma cells. Briefly, The an-ti-glioblastoma activity was assessed in human glioma U87 xenografts nude mice. Chr-A-related targets were identified by RNA-seq. Apoptotic ratio and caspase 3/7 activity of U251 and U87-MG cells were assayed by flow cytometry. Apoptosis-related proteins and possible molecular mecha-nism were validated via Western blotting. The results showed that Chr-A treatment significantly inhibits glioblastoma progression in xenografts nude mice, and enrichment analysis suggested that apoptosis, PI3K-Akt and Wnt signaling pathway were involved in the possible mechanism. Chr-A increased apoptotic ratio and the activity of caspase 3/7 in U251 and U87-MG cells. Western blot revealed that Chr-A broke the balance between Bax and Bcl-2 activating caspase cascade re-action and downregulated the expression of p-Akt and p-GSK-3β, suggesting that Chr-A may contribute to glioblastoma regression modulating Akt/GSK-3β signaling pathway to promote apoptosis of neuroglioma cells in vivo and in vitro. Therefore, Chr-A may hold therapeutic promise for glioblastoma.