200 research outputs found
Human Body Shape Classification Based on a Single Image
There is high demand for online fashion recommender systems that incorporate
the needs of the consumer's body shape. As such, we present a methodology to
classify human body shape from a single image. This is achieved through the use
of instance segmentation and keypoint estimation models, trained only on
open-source benchmarking datasets. The system is capable of performing in noisy
environments owing to to robust background subtraction. The proposed
methodology does not require 3D body recreation as a result of classification
based on estimated keypoints, nor requires historical information about a user
to operate - calculating all required measurements at the point of use. We
evaluate our methodology both qualitatively against existing body shape
classifiers and quantitatively against a novel dataset of images, which we
provide for use to the community. The resultant body shape classification can
be utilised in a variety of downstream tasks, such as input to size and fit
recommendation or virtual try-on systems
Surveying the deep: A review of computer vision in the benthos
The analysis of image data for benthic biodiversity monitoring is now commonplace within the domain of marine ecology. Whilst advances in imaging technologies have allowed for the collection of vast quantities of data, the curation of this has traditionally been performed manually, resulting in a bottleneck whereby data is collected faster than it can be processed. Recent years have seen marine ecologists turn to the domain of computer vision to help automate this curation process. However, as the knowledge required to build such systems spans both domains, there is a high barrier to entry. To help reduce this barrier, this paper aims to provide an introduction to computer vision-based benthic biodiversity monitoring via a comprehensive literature review. To aid ecologists, key computer vision concepts are described and example use-cases highlighted. The major challenges inherent to benthic imagery for computer vision systems are explored, alongside a discussion of how current systems attempt to mitigate against these. To aid computer scientists wishing to enter the domain, an exploration of currently available open-source benthic datasets is also provided. Recommendations for future research are explored, including a move towards human-centric techniques, committing to ablation studies, reaching community agreement on open-source benchmarking datasets, and an increased use of innovative methods to allow for improved answering of key benthic ecology questions
A 10-point plan to scale up renewable energy in the Global South
The parties to the Paris Agreement have a new ambition: Tripling renewable energy capacity by 2030. We investigate this pledge from the point of view of renewable energy operators in developing countries, where future energy needs are largest. We identify the key risks and barriers operators face. As renewable energy technology has matured, these risks have evolved. Operators are now much more concerned about market (e.g. tariff levels), macroeconomic (e.g. exchange rates) and governance (e.g. administrative hurdles) risks than technology risks per se. We put forward 10 concrete, actionable measures to accelerate renewable energy deployment. The measures are well understood, and if they are scaled up determinedly the 2030 target is achievable
Data Study Group Final Report: UK Centre for Ecology & Hydrology (UKCEH) - Advancing Insect Biodiversity Monitoring through Automated Sensors, Deep Learning, and Citizen Science Data
Executive Summary. The overarching goal in this Alan Turing Institute Data Study Group(DSG) was to advance understanding and support conservation efforts related to insect populations and biodiversity monitoring. This was achieved through the integration of reliable and trustworthy machine learning applications, with datasets provided by the UK Centre for Ecology & Hydrology (UKCEH).Our objectives were twofold:• Develop advanced analytical techniques for generating biodiversity metrics and interactive data visualisations. These tools aim to promote stakeholder engagement and interest in biodiversity monitoring.• Enhance the transparency of decision-making in machine learning models and increase the trustworthiness of subsequent biodiversity monitoring results. Our work ultimately contributes to global biodiversity protection by providing tangible, reliable insights and a comprehensive understanding of ecosystem dynamics
Meeting Report: The Dallas Consensus Conference on Liver Transplantation for Alcohol Associated Hepatitis
Peer Reviewedhttps://deepblue.lib.umich.edu/bitstream/2027.42/153137/1/lt25681.pdfhttps://deepblue.lib.umich.edu/bitstream/2027.42/153137/2/lt25681_am.pd
UKMenCar4: A cross-sectional survey of asymptomatic meningococcal carriage amongst UK adolescents at a period of low invasive meningococcal disease incidence
Carriage of Neisseria meningitidis , the meningococcus, is a prerequisite for invasive meningococcal disease (IMD), a potentially devastating infection that disproportionately afflicts infants and children. Humans are the sole known reservoir for the meningococcus, and it is carried asymptomatically in the nasopharynx of ~10% of the population. Rates of carriage are dependent on age of the host and social and behavioural factors. In the UK, meningococcal carriage has been studied through large, multi-centre carriage surveys of adolescents in 1999, 2000, and 2001, demonstrating carriage can be affected by immunisation with the capsular group C meningococcal conjugate vaccine, inducing population immunity against carriage. Fifteen years after these surveys were carried out, invasive meningococcal disease incidence had declined from a peak in 1999. The UKMenCar4 study was conducted in 2014/15 to investigate rates of carriage amongst the adolescent population during a period of low disease incidence. The protocols and methodology used to perform UKMenCar4, a large carriage survey, are described here
Soluble non-starch polysaccharides from plantain (Musa x paradisiaca L.) diminish epithelial impact of clostridioides difficile
© 2021 The Authors. Published by Frontiers Media. This is an open access article available under a Creative Commons licence.
The published version can be accessed at the following link on the publisher’s website: https://doi.org/10.3389/fphar.2021.766293Clostridioides difficile infection (CDI) is a leading cause of antibiotic-associated diarrhoea. Adhesion of this Gram-positive pathogen to the intestinal epithelium is a crucial step in CDI, with recurrence and relapse of disease dependent on epithelial interaction of its endospores. Close proximity, or adhesion of, hypervirulent strains to the intestinal mucosa are also likely to be necessary for the release of C. difficile toxins, which when internalized, result in intestinal epithelial cell rounding, damage, inflammation, loss of barrier function and diarrhoea. Interrupting these C. difficile-epithelium interactions could therefore represent a promising therapeutic strategy to prevent and treat CDI. Intake of dietary fibre is widely recognised as being beneficial for intestinal health, and we have previously shown that soluble non-starch polysaccharides (NSP) from plantain banana (Musa spp.), can block epithelial adhesion and invasion of a number of gut pathogens, such as E. coli and Salmonellae. Here, we assessed the action of plantain NSP, and a range of alternative soluble plant fibres, for inhibitory action on epithelial interactions of C. difficile clinical isolates, purified endospore preparations and toxins. We found that plantain NSP possessed ability to disrupt epithelial adhesion of C. difficile vegetative cells and spores, with inhibitory activity against C. difficile found within the acidic (pectin-rich) polysaccharide component, through interaction with the intestinal epithelium. Similar activity was found with NSP purified from broccoli and leek, although seen to be less potent than NSP from plantain. Whilst plantain NSP could not block the interaction and intracellular action of purified C. difficile toxins, it significantly diminished the epithelial impact of C. difficile, reducing both bacteria and toxin induced inflammation, activation of caspase 3/7 and cytotoxicity in human intestinal cell-line and murine intestinal organoid cultures. Dietary supplementation with soluble NSP from plantain may therefore confer a protective effect in CDI patients by preventing adhesion of C. difficile to the mucosa, i.e. a “contrabiotic” effect, and diminishing its epithelial impact. This suggests that plantain soluble dietary fibre may be a therapeutically effective nutritional product for use in the prevention or treatment of CDI and antibiotic-associated diarrhoea.HS was supported by a Biotechnology and Biological Sciences Research Council (BBSRC) Industrial CASE studentship to BC
and JR (BB/I016783/1) investigating the role of soluble dietary plant fibre in maintenance of intestinal health and prevention of
diarrheal disease. CR was supported by a University of Liverpool Reach Out Growth Fund award (ROGF-N0306).Published onlin
- …