Search

Supersaturation of total dissolved gas (TDG) is mainly produced by high dam discharge, excess oxygen production by plant photosynthesis, and a sharp increase in water temperature, which may directly lead to fish and aquatic organisms suffering from “gas bubble disease” (GBD) or death. Aeration was one of the methods used to solve the dissipation of supersaturated TDG. In this paper, aeration had an obvious promotion effect on the dissipation of supersaturated TDG. For the calculation and analysis of supersaturated TDG dissipation coefficient, the aeration rate was proportional to TDG dissipation coefficient and had a promoting effect on it, while the aeration depth and aeration aperture were inversely proportional to TDG dissipation coefficient and played an inhibitory effect on it. The supersaturated TDG dissipation coefficient was affected by a factor of KTDG,Q> KTDG,D> KTDG,H. A quantitative relationship between the supersaturated TDG dissipation coefficient and aeration rate, aeration depth, and aeration aperture was obtained, respectively, as well as important expressions with comprehensive effect factors; their margins of error average within 10%. This research method has an important guiding significance for improving the living environment of fish and other aquatic organisms, alleviating the adverse effects of supersaturated TDG.

Cyclospora cayetanensis, a protozoan that causes watery diarrhea, fatigue, abdominal pain, weight loss, and inappetence, is endemic to some nonindustrialized countries (1-4). In industrialized countries, the infection has been traditionally [...]

Accurate segmentation of retinal blood vessels is a key step in the diagnosis of fundus diseases, among which cataracts, glaucoma, and diabetic retinopathy (DR) are the main diseases that cause blindness. Most segmentation methods based on deep convolutional neural networks can effectively extract features. However, convolution and pooling operations also filter out some useful information, and the final segmented retinal vessels have problems such as low classification accuracy. In this paper, we propose a multi-scale residual attention network called MRA-UNet. Multi-scale inputs enable the network to learn features at different scales, which increases the robustness of the network. In the encoding phase, we reduce the negative influence of the background and eliminate noise by using the residual attention module. We use the bottom reconstruction module to aggregate the feature information under different receptive fields, so that the model can extract the information of different thicknesses of blood vessels. Finally, the spatial activation module is used to process the up-sampled image to further increase the difference between blood vessels and background, which promotes the recovery of small blood vessels at the edges. Our method was verified on the DRIVE, CHASE, and STARE datasets. Respectively, the segmentation accuracy rates reached 96.98%, 97.58%, and 97.63%; the specificity reached 98.28%, 98.54%, and 98.73%; and the F-measure scores reached 82.93%, 81.27%, and 84.22%. We compared the experimental results with some state-of-art methods, such as U-Net, R2U-Net, and AG-UNet in terms of accuracy, sensitivity, specificity, F-measure, and AUC R O C . Particularly, MRA-UNet outperformed U-Net by 1.51%, 3.44%, and 0.49% on DRIVE, CHASE, and STARE datasets, respectively. [ABSTRACT FROM AUTHOR]