The present study evaluates effectiveness of up-flow anaerobic sludge blanket (UASB) reactor followed by two post-anaerobic treatment options, namely free-surface, up-flow constructed wetland (FUP-CW) and oxygen-limited anaerobic nitrification/denitrification (OLAND) processes in treating sewage from the peri-urban areas in India receiving illegal industrial infiltrations. The UASB studies yielded robust results towards fluctuating strength of sewage and consistently removed 87-98% chemical oxygen demand (COD) at a hydraulic retention time of 1.5-2 d. The FUP-CW removed 68.5±13% COD, 68±3% NH4+-N, 38±5% PO4(3-)-P, 97.6±5% suspended particles and 97±13% fecal coliforms. Nutrient removal was found to be limiting in FUP-CW, especially in winter. Nitrogen removal in the OLAND process were 100 times higher than the FUP-CW process. Results show that UASB followed by FUP-CW can be an excellent, decentralized sewage treatment option, except during winter when nutrient removal is limited in FUP-CW. Hence, the study proposes bio-augmentation of FUP-CW with OLAND biomass for overall improvement in the performance of UASB followed by FUP-CW process.
Learning High-Resolution representations is essential for semantic segmentation. Convolutional neural network (CNN) architectures with downstream and upstream propagation flow are popular for segmentation in medical diagnosis. However, due to performing spatial downsampling and upsampling in multiple stages, information loss is inexorable. On the contrary, connecting layers densely on high spatial resolution is computationally expensive. In this work, we devise a Loose Dense Connection Strategy to connect neurons in subsequent layers with reduced parameters. On top of that, using a m-way Tree structure for feature propagation we propose Receptive Field Chain Network (RFC-Net) that learns high-resolution global features on a compressed computational space. Our experiments demonstrates that RFC Net achieves state-of-the-art performance on Kvasir and CVC-ClinicDB benchmarks for Polyp segmentation. Our code is publicly available at github.com/sourajitcs/RFC-NetAAAI23.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.