Binary segmentation in remote sensing aims to obtain binary prediction mask classifying each pixel in the given image. Deep learning methods have shown outstanding performance in this task. These existing methods in fully supervised manner need massive high-quality datasets with manual pixel-level annotations. However, the annotations are generally expensive and sometimes unreliable. Recently, using only image-level annotations, weakly supervised methods have proven to be effective in natural imagery, which significantly reduce the dependence on manual fine labeling. In this paper, we review existing methods and propose a novel weakly supervised binary segmentation framework, which is capable of addressing the issue of class imbalance via a balanced binary training strategy. Besides, a weakly supervised feature-fusion network (WSF-Net) is introduced to adapt to the unique characteristics of objects in remote sensing image. The experiments were implemented on two challenging remote sensing datasets: Water dataset and Cloud dataset. Water dataset is acquired by Google Earth with a resolution of 0.5 m, and Cloud dataset is acquired by Gaofen-1 satellite with a resolution of 16 m. The results demonstrate that using only image-level annotations, our method can achieve comparable results to fully supervised methods.
A novel method to prepare high-purity vanadium pentoxide (V2O5) was proposed, and V2O5 with a purity of above 99.95 wt %, in which the concentration of Fe was at 0.0060%, the concentration of Al was at 0.0040%, and Si, K, Na, and other impurities were under the determination limit, was obtained. In this method, anhydrous aluminum chloride (AlCl3) was adopted, which replaced toxic and corrosive Cl2 in the traditional chlorination method. Moreover, the reaction temperature was relatively low at 160 °C compared to Cl2 chlorination method. A novel method to prepare high-purity vanadium pentoxide (V2O5) was proposed. V2O5 with a high-purity of 99.95% was obtained. Anhydrous aluminium chloride (AlCl3) was adopted as chlorination agent to achieve the separation vanadium from impurities at low temperature of 160 °C. This method enables a lower cost, shortened process, a higher selectivity, and simpler and cleaner operation to prepare high-purity V2O5.
A copolymer system of 2-aminoethyl methacrylate and N-isopropylacrylamide comprises novel properties: changes in conformation and hydrophilicity upon heating influence the antibacterial activity and result in a switchable biocidal effect. The copolymers are characterized via NMR, MALDI-ToF MS, phase transition behavior, and antibacterial tests with E. coli or B. subtilis. MIC and MBC are determined using standard dilution methods, temperature-dependence via incubation at different temperatures and cytotoxicity by MTT tests. The copolymers exhibit lower MIC in globule than coil conformation, crosslinking on cotton results in non-leaching materials with better antibacterial activity above than below the phase-transition point.
Abstract Interactions between inorganic materials and living systems can be strongly influenced by the dimensional property of the materials, which can in turn impact biological activities. Although the role of biomaterials at the molecular and cellular scales has been studied, research investigating the effects of biomaterials across multiple dimensional scales is relatively scarce. Herein, comparing the effectiveness of two‐dimensional graphene oxide nanosheets (GOs) and three‐dimensional graphene oxide quantum dots (GOQDs) (though not zero‐dimensional because of their significant surface area) in cancer therapies, we have discovered that GOs, with the same mass concentration, exhibit stronger anti‐cancer and anti‐tumor metastasis properties than GOQDs. Our research, which employed liquid‐phase atomic force microscopy, revealed that lower‐dimensional GOs create a more extensive nano‐bio interface that impedes actin protein polymerization into the cytoskeleton, leading to the prevention of tumor metastasis. These results help to better understand the underlying mechanisms and offer a dimensional perspective on the potential of optimizing the properties of graphene‐based materials for clinical applications, e.g., cancer therapy.
Event Abstract Back to Event No Records Found Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Google Google Scholar PubMed Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)