Aerial inspection of agricultural regions can provide crucial information to safeguard from numerous obstacles to efficient farming. Farmland anomalies such as standing water, weed clusters, hamper ...the farming practices, which causes improper use of farm area and disrupts agricultural planning. Monitoring of farmland and crops through Internet-of-Things (IoT)-enabled smart systems has potential to increase the efficiency of modern farming techniques. Unmanned Aerial Vehicle (UAV)-based remote sensing is a powerful technique to acquire farmland images on a large scale. Visual data analytics for automatic pattern recognition from the collected data is useful for developing Artificial intelligence (AI)-assisted farming models, which holds great promise in improving the farming outputs by capturing the crop patterns, farmland anomalies and providing predictive solutions to the inherent challenges faced by farmers. In this work, we propose a deep learning framework AgriSegNet for automatic detection of farmland anomalies using multiscale attention semantic segmentation of UAV acquired images. The proposed model is useful for monitoring of farmland and crops to increase the efficiency of precision farming techniques.
Deriving mechanisms of immune‐mediated disease from GWAS data remains a formidable challenge, with attempts to identify causal variants being frequently hampered by strong linkage disequilibrium. To ...determine whether causal variants could be identified from their functional effects, we adapted a massively parallel reporter assay for use in primary CD4 T cells, the cell type whose regulatory DNA is most enriched for immune‐mediated disease SNPs. This enabled the effects of candidate SNPs to be examined in a relevant cellular context and generated testable hypotheses into disease mechanisms. To illustrate the power of this approach, we investigated a locus that has been linked to six immune‐mediated diseases but cannot be fine‐mapped. By studying the lead expression‐modulating SNP, we uncovered an NF‐κB‐driven regulatory circuit which constrains T‐cell activation through the dynamic formation of a super‐enhancer that upregulates TNFAIP3 (A20), a key NF‐κB inhibitor. In activated T cells, this feedback circuit is disrupted—and super‐enhancer formation prevented—by the risk variant at the lead SNP, leading to unrestrained T‐cell activation via a molecular mechanism that appears to broadly predispose to human autoimmunity.
Synopsis
Little progress has been made in resolving causal SNPs, genes and disease mechanisms at GWAS loci. An adapted massively‐parallel reporter assay (MPRA) allows to study immune‐mediated disease loci in CD4 T cells, the cell‐type whose regulatory DNA is most highly enriched for disease‐associated SNPs.
Adapted MPRA identifies putative causal SNPs based on their functional effects within primary CD4 T cells—key effectors of immune‐mediated disease.
These effects differ from those detected in the Jurkat cell‐line, reinforcing the importance of an appropriate cellular context in disease‐related studies.
The results provide a focus for mechanistic studies to resolve the downstream consequences of expression‐modulating variants at multiple loci.
At a gene‐desert linked to multiple diseases, the lead MPRA SNP is shown to abrogate NF‐κB binding, disrupt super‐enhancer formation, and reduce TNFAIP3 expression, leading to unrestrained T cell‐driven inflammation.
This provides mechanistic insights into disease biology at a locus that cannot be fine‐mapped and illustrates the potential of this method to uncover genetic mechanisms of immune‐mediated disease.
Little progress has been made in resolving causal SNPs, genes and disease mechanisms at GWAS loci. An adapted massively‐parallel reporter assay (MPRA) allows to study immune‐mediated disease loci in CD4 T cells, the cell‐type whose regulatory DNA is most highly enriched for disease‐associated SNPs.
Semantic dementia (SD) is characterized by progressive impairment in conceptual knowledge due to anterior temporal lobe (ATL) neurodegeneration. Extended neuropsychological assessments can ...quantitatively demonstrate the semantic impairment, but this graded loss of knowledge can also be readily observed in the qualitative observation of patients' recall of single concepts. Here, we present the results of a simple task of object drawing-from-name, by patients with SD (N = 19), who have isolated atrophy of the ATL bilaterally. Both cross-sectionally and longitudinally, patient drawings demonstrated a pattern of degradation in which rare and distinctive features (such as the hump on a camel) were lost earliest in disease course, and there was an increase in the intrusion of prototypical features (such as the typical small ears of most mammals on an elephant) with more advanced disease. Crucially, patient drawings showed a continuum of conceptual knowledge loss rather than a binary 'present' or 'absent' state. Overall, we demonstrate that qualitative evaluation of line drawings of animals and objects provides fascinating insights into the transmodal semantic deficit in SD. Our results are consistent with a distributed-plus-hub model of semantic memory. The graded nature of the deficit in semantic performance observed in our subset of longitudinally observed patients suggests that the temporal lobe binds feature-based semantic attributes in its central convergence zone.
The problem faced by one farmer can also be the problem of some other farmer in other regions. Providing information to farmers and connecting them has always been a challenge. Crowdsourcing and ...community building are considered as useful solutions to these challenges. However, privacy concerns and inactivity of users can make these models inefficient. To tackle these challenges, we present a cost-efficient and blockchain-based secure framework for building a community of farmers and crowdsourcing the data generated by them to help the farmers’ community. Apart from ensuring privacy and security of data, a revenue model is also incorporated to provide incentives to farmers. These incentives would act as a motivating factor for the farmers to willingly participate in the process. Through integration of a deep neural network-based model to our proposed framework, prediction of any abnormalities present within the crops and their predicted possible solutions would be much more coherent. The simulation results demonstrate that the prediction of plant pathology model is highly accurate.
With the prevalence of deep learning (DL) in many applications, researchers are investigating different ways of optimizing FPGA architecture and CAD to achieve better quality-of-results (QoR) on ...DL-based workloads. In this optimization process, benchmark circuits are an essential component; the QoR achieved on a set of benchmarks is the main driver for architecture and CAD design choices. However, current academic benchmark suites are inadequate, as they do not capture any designs from the DL domain. This work presents the second version of our suite of DL acceleration benchmark circuits for FPGA architecture and CAD research, called Koios. This suite of 40 circuits covers a wide variety of accelerated neural networks, design sizes, implementation styles, abstraction levels, and numerical precisions. These benchmarks include 32 DL designs and 8 synthetic (proxy) benchmarks. The Koios benchmarks are larger, more data parallel, more heterogeneous, more deeply pipelined, and utilize more FPGA architectural features compared to existing open-source benchmarks. This enables researchers to pinpoint architectural inefficiencies for this class of workloads and optimize CAD tools on more representative benchmarks that stress the CAD algorithms in different ways. In this paper, we describe the Koios designs, compare their characteristics to prior FPGA benchmark suites, and present results of running them through the Verilog-to-Routing (VTR) flow using a recent FPGA architecture model. Finally, we present case studies showing how exploration of DL-optimized FPGA architecture and CAD algorithms can be performed using our new benchmark suite.
Travel has individual, societal and planetary health implications. We explored socioeconomic and gendered differences in travel behaviour in Africa, to develop an understanding of travel-related ...inequity. We conducted a mixed-methods systematic review (PROSPERO CRD42019124802). In 2019, we searched MEDLINE, TRID, SCOPUS, Web of Science, LILACS, SciELO, Global Health, Africa Index Medicus, CINAHL and MediCarib for studies examining travel behaviour by socioeconomic status and gender in Africa. We appraised study quality using Critical Appraisal Skills Programme checklists. We synthesised qualitative data using meta-ethnography, followed by a narrative synthesis of quantitative data, and integrated qualitative and quantitative strands using pattern matching principles. We retrieved 103 studies (20 qualitative, 24 mixed-methods, 59 quantitative). From the meta-ethnography, we observed that travel is: intertwined with social mobility; necessary to access resources; associated with cost and safety barriers; typified by long distances and slow modes; and dictated by gendered social expectations. We also observed that: motorised transport is needed in cities; walking is an unsafe, ‘captive’ mode; and urban and transport planning are uncoordinated. From these observations, we derived hypothesised patterns that were tested using the quantitative data, and found support for these overall. In lower socioeconomic individuals, travel inequity entailed reliance on walking and paratransit (informal public transport), being unable to afford travel, travelling less overall, and travelling long distances in hazardous conditions. In women and girls, travel inequity entailed reliance on walking and lack of access to private vehicles, risk of personal violence, societally-imposed travel constraints, and household duties shaping travel. Limitations included lack of analytical rigour in qualitative studies and a preponderance of cross-sectional quantitative studies (offering a static view of an evolving process). Overall, we found that travel inequity in Africa perpetuates socioeconomic and gendered disadvantage. Proposed solutions focus on improving the safety, efficiency and affordability of public transport and walking.
•Utilised meta-ethnography and pattern-matching principles.•Revealed travel patterns differed by socioeconomic status and gender.•Travel inequity compounded disadvantage.•Females and poor people more likely to rely on walking.•Cost, safety and cultural factors were barriers to travel.
The Human Mobility Transition model describes shifts in mobility dynamics and transport systems. The aspirational stage, ‘human urbanism’, is characterised by high active travel, universal public ...transport, low private vehicle use and equitable access to transport. We explored factors associated with travel behaviour in Africa and the Caribbean, investigating the potential to realise ‘human urbanism’ in this context. We conducted a mixed-methods systematic review of ten databases and grey literature for articles published between January 2008 and February 2019. We appraised study quality using Critical Appraisal Skills Programme checklists. We narratively synthesized qualitative and quantitative data, using meta-study principles to integrate the findings. We identified 39,404 studies through database searching, mining reviews, reference screening, and topic experts’ consultation. We included 129 studies (78 quantitative, 28 mixed-methods, 23 qualitative) and 33 grey literature documents. In marginalised groups, including the poor, people living rurally or peripheral to cities, women and girls, and the elderly, transport was poorly accessible, travel was characterised by high levels of walking and paratransit (informal public transport) use, and low private vehicle use. Poorly controlled urban growth (density) and sprawl (expansion), with associated informality, was a salient aspect of this context, resulting in long travel distances and the necessity of motorised transportation. There were existing population-level assets in relation to ‘human urbanism’ (high levels of active travel, good paratransit coverage, low private vehicle use) as well as core challenges (urban sprawl and informality, socioeconomic and gendered barriers to travel, poor transport accessibility). Ineffective mobility systems were a product of uncoordinated urban planning, unregulated land use and subsequent land use conflict. To realise ‘human urbanism’, integrated planning policies recognising the linkages between health, transport and equity are needed. A shift in priority from economic growth to a focus on broader population needs and the rights and wellbeing of ordinary people is required. Policymakers should focus attention on transport accessibility for the most vulnerable.