scholarly journals Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition

2012 ◽  
Author(s):  
Jia Deng ◽  
J. Krause ◽  
A. C. Berg ◽  
Li Fei-Fei
Keyword(s):  
Large Scale ◽  
Visual Recognition ◽  
Trade Offs

scholarly journals Mapping the adaptive landscape of a major agricultural pathogen reveals evolutionary constraints across heterogeneous environments

2021 ◽  
Author(s):  
Anik Dutta ◽  
Fanny E. Hartmann ◽  
Carolina Sardinha Francisco ◽  
Bruce A. McDonald ◽  
Daniel Croll
Keyword(s):  
Life History ◽  
Large Scale ◽  
Life History Traits ◽  
Genetic Correlations ◽  
Stress Factors ◽  
Life History Trait ◽  
Adaptive Landscape ◽  
Heterogeneous Environments ◽  
Growth Responses ◽  
Trade Offs

AbstractThe adaptive potential of pathogens in novel or heterogeneous environments underpins the risk of disease epidemics. Antagonistic pleiotropy or differential resource allocation among life-history traits can constrain pathogen adaptation. However, we lack understanding of how the genetic architecture of individual traits can generate trade-offs. Here, we report a large-scale study based on 145 global strains of the fungal wheat pathogen Zymoseptoria tritici from four continents. We measured 50 life-history traits, including virulence and reproduction on 12 different wheat hosts and growth responses to several abiotic stressors. To elucidate the genetic basis of adaptation, we used genome-wide association mapping coupled with genetic correlation analyses. We show that most traits are governed by polygenic architectures and are highly heritable suggesting that adaptation proceeds mainly through allele frequency shifts at many loci. We identified negative genetic correlations among traits related to host colonization and survival in stressful environments. Such genetic constraints indicate that pleiotropic effects could limit the pathogen’s ability to cause host damage. In contrast, adaptation to abiotic stress factors was likely facilitated by synergistic pleiotropy. Our study illustrates how comprehensive mapping of life-history trait architectures across diverse environments allows to predict evolutionary trajectories of pathogens confronted with environmental perturbations.

scholarly journals An integrated life cycle and water footprint assessment of nonfood crops based bioenergy production

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jun Li ◽  
Fengyin Xiong ◽  
Zhuo Chen
Keyword(s):  
Life Cycle ◽  
Environmental Sustainability ◽  
Large Scale ◽  
Water Footprint ◽  
Arable Land ◽  
Integrated Analysis ◽  
Actual Performance ◽  
Bioenergy Production ◽  
Trade Offs ◽  
Hybrid Pennisetum

AbstractBiomass gasification, especially distribution to power generation, is considered as a promising way to tackle global energy and environmental challenges. However, previous researches on integrated analysis of the greenhouse gases (GHG) abatement potentials associated with biomass electrification are sparse and few have taken the freshwater utilization into account within a coherent framework, though both energy and water scarcity are lying in the central concerns in China’s environmental policy. This study employs a Life cycle assessment (LCA) model to analyse the actual performance combined with water footprint (WF) assessment methods. The inextricable trade-offs between three representative energy-producing technologies are explored based on three categories of non-food crops (maize, sorghum and hybrid pennisetum) cultivated in marginal arable land. WF results demonstrate that the Hybrid pennisetum system has the largest impact on the water resources whereas the other two technology options exhibit the characteristics of environmental sustainability. The large variances in contribution ratio between the four sub-processes in terms of total impacts are reflected by the LCA results. The Anaerobic Digestion process is found to be the main contributor whereas the Digestate management process is shown to be able to effectively mitigate the negative environmental impacts with an absolute share. Sensitivity analysis is implemented to detect the impacts of loss ratios variation, as silage mass and methane, on final results. The methane loss has the largest influence on the Hybrid pennisetum system, followed by the Maize system. Above all, the Sorghum system demonstrates the best performance amongst the considered assessment categories. Our study builds a pilot reference for further driving large-scale project of bioenergy production and conversion. The synergy of combined WF-LCA method allows us to conduct a comprehensive assessment and to provide insights into environmental and resource management.

scholarly journals System design for inferring colony-level pollination activity through miniature bee-mounted sensors

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Haron M. Abdel-Raziq ◽  
Daniel M. Palmer ◽  
Phoebe A. Koenig ◽  
Alyosha C. Molnar ◽  
Kirstin H. Petersen
Keyword(s):  
Data Acquisition ◽  
Honey Bees ◽  
Large Scale ◽  
Physical World ◽  
Cluttered Environments ◽  
Robotic Mapping ◽  
Large Scale Data ◽  
Trade Offs ◽  
Large Numbers ◽  
Engineered Systems

AbstractIn digital agriculture, large-scale data acquisition and analysis can improve farm management by allowing growers to constantly monitor the state of a field. Deploying large autonomous robot teams to navigate and monitor cluttered environments, however, is difficult and costly. Here, we present methods that would allow us to leverage managed colonies of honey bees equipped with miniature flight recorders to monitor orchard pollination activity. Tracking honey bee flights can inform estimates of crop pollination, allowing growers to improve yield and resource allocation. Honey bees are adept at maneuvering complex environments and collectively pool information about nectar and pollen sources through thousands of daily flights. Additionally, colonies are present in orchards before and during bloom for many crops, as growers often rent hives to ensure successful pollination. We characterize existing Angle-Sensitive Pixels (ASPs) for use in flight recorders and calculate memory and resolution trade-offs. We further integrate ASP data into a colony foraging simulator and show how large numbers of flights refine system accuracy, using methods from robotic mapping literature. Our results indicate promising potential for such agricultural monitoring, where we leverage the superiority of social insects to sense the physical world, while providing data acquisition on par with explicitly engineered systems.

scholarly journals HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition

2017 ◽  
Vol 26 (4) ◽  
pp. 1923-1938 ◽  
Author(s):  
Jianping Fan ◽  
Tianyi Zhao ◽  
Zhenzhong Kuang ◽  
Yu Zheng ◽  
Ji Zhang ◽  
...  
Keyword(s):  
Large Scale ◽  
Visual Recognition ◽  
Task Learning

scholarly journals Reliability of a Visual Recognition System for Detection of Johnsongrass(Sorghum halepense) in Corn

2011 ◽  
Vol 25 (4) ◽  
pp. 645-651 ◽  
Author(s):  
Dionisio Andújar ◽  
Ángela Ribeiro ◽  
Cesar Fernández-Quintanilla ◽  
José Dorado
Keyword(s):  
Large Scale ◽  
Visual Recognition ◽  
Visual Detection ◽  
Cropping Systems ◽  
Experimental Period ◽  
Recognition System ◽  
Infested Area ◽  
Net Returns ◽  
Cropping Season ◽  
Combine Harvester

The feasibility of visual detection of weeds for map-based patch spraying systems needs to be assessed for use in large-scale cropping systems. The main objective of this research was to evaluate the reliability and profitability of using maps of Johnsongrass patches constructed at harvest to predict spatial distribution of weeds during the next cropping season. Johnsongrass patches visually were assessed from the cabin of a combine harvester in three corn fields and were compared with maps obtained in the subsequent year prior to postemergence herbicide application. There was a good correlation (71% on average) between the position of Johnsongrass patches on the two maps (fall vs. spring). The highest correlation (82%) was obtained with relatively large infestations, whereas the lowest (58%) was obtained when the infested area was smaller. Although the relative positions of the patches remained almost unchanged from 1 yr to the next, the infested area increased in all fields during the 4-yr experimental period. According to our estimates, using a strategy based on spraying full rates of herbicides to patches recorded in the map generated in the previous fall resulted in higher net returns than spraying the whole field, either at full or half rate. This site-specific strategy resulted in an average 65% reduction in the volume of herbicide applied to control this weed.

scholarly journals The PETLON Algorithm to Plan Efficiently for Task-Level-Optimal Navigation

2020 ◽  
Vol 69 ◽  
pp. 471-500
Author(s):  
Shih-Yun Lo ◽  
Shiqi Zhang ◽  
Peter Stone
Keyword(s):  
Mobile Robot ◽  
Motion Planning ◽  
Mobile Robots ◽  
Large Scale ◽  
Accurate Estimate ◽  
Indoor Environments ◽  
Task Planning ◽  
Trade Offs ◽  
High Level ◽  
Task Level

Intelligent mobile robots have recently become able to operate autonomously in large-scale indoor environments for extended periods of time. In this process, mobile robots need the capabilities of both task and motion planning. Task planning in such environments involves sequencing the robot’s high-level goals and subgoals, and typically requires reasoning about the locations of people, rooms, and objects in the environment, and their interactions to achieve a goal. One of the prerequisites for optimal task planning that is often overlooked is having an accurate estimate of the actual distance (or time) a robot needs to navigate from one location to another. State-of-the-art motion planning algorithms, though often computationally complex, are designed exactly for this purpose of finding routes through constrained spaces. In this article, we focus on integrating task and motion planning (TMP) to achieve task-level-optimal planning for robot navigation while maintaining manageable computational efficiency. To this end, we introduce TMP algorithm PETLON (Planning Efficiently for Task-Level-Optimal Navigation), including two configurations with different trade-offs over computational expenses between task and motion planning, for everyday service tasks using a mobile robot. Experiments have been conducted both in simulation and on a mobile robot using object delivery tasks in an indoor office environment. The key observation from the results is that PETLON is more efficient than a baseline approach that pre-computes motion costs of all possible navigation actions, while still producing plans that are optimal at the task level. We provide results with two different task planning paradigms in the implementation of PETLON, and offer TMP practitioners guidelines for the selection of task planners from an engineering perspective.

Sign in / Sign up

Export Citation Format

Share Document