Grassland, as one of the largest ecosystems on the earth, supports various goods and services to humanity.Historically, humans have increased agricultural output primarily by cropland expansion and agricultural intens...Grassland, as one of the largest ecosystems on the earth, supports various goods and services to humanity.Historically, humans have increased agricultural output primarily by cropland expansion and agricultural intensification.The cropland area was primarily gained at the expense of grassland and forests.Apart from grassland conversion, increasing consumption of calorie- and meat-intensive diets drives the intensification of livestock systems, which is shifting steadily from grazing to feeding with crops.To cope with the environmental degradation due to agriculture, various forms of ‘green payment' were implemented to promote the adoption of sustainable farming practices over the last two decades in the European Union.The aim of this study is to monitor the recent transitions(1992–2010) between grassland and cropland during two Common Agricultural Policy(CAP) reforms at the French mainland scale.We proposed an innovative approach to link grassland conversion to agricultural commodities and farming systems practices.We first assessed the grassland-to-cropland conversion and further investigated the crop sequence patterns that were observed to be dominant after the conversion through mining land-cover survey data Teruti and Teruti-Lucas.We found the trends of the transitions between grassland and cropland over the two time intervals: The loss of grassland(1992–2003) and restoration or re-expansion of grassland(2006–2010) in mainland France.Our finding on the crop sequence patterns after the grassland conversion reveals two notable evolutions of agricultural production systems.These evolutions were related to the increase in the proportion of cropland in the total agricultural land use.One evolution was most likely influenced by the demand for fodder: The conversion from grazing livestock to feeding livestock.Another evolution was the conversion from livestock production to field crop production.Our results indicate that the intensification of livestock farming systems continued over the last two decades in France.We conclude that, the approach developed in this study can be considered as a generic method for monitoring the transitions between grassland and cropland and further identifying the crop sequence patterns after the grassland conversion from time-series land cover data.展开更多
Industrial woven meshes are composed of metal materials and are often used in construction,industrial and residential activities or applications.The objective of this work is defect detection in industrial fabrics in ...Industrial woven meshes are composed of metal materials and are often used in construction,industrial and residential activities or applications.The objective of this work is defect detection in industrial fabrics in the quality control stage.In order to overcome the limitations of manual methods,which are often tedious and time-consuming,we propose a strategy that can automatically detect defects in micrometric steel meshes by means of a Convolutional Neural Network.The database used for such a purpose comes from real problem data for anomaly detection in micrometric woven meshes.This detection is performed through supervised classification with a Convolutional Neural Network using a VGG19 architecture.We define a pipeline and a strategy to tackle the related small amount of data.It includes i)augmenting the database with translation,rotation and symmetry,ii)using pre-trained weights and iii)checking the learning curve behaviour through cross-validation.The obtained results show that,despite the small size of our databases,detection accuracy of 96%was reached.展开更多
Fusarium head blight (FHB) is a destructive disease of wheat and other cereals. FHB occurs in Europe, North America and around the world causing significant losses in production and endangers human and animal health. ...Fusarium head blight (FHB) is a destructive disease of wheat and other cereals. FHB occurs in Europe, North America and around the world causing significant losses in production and endangers human and animal health. In this article, we provide the strategic steps for the specific target selection for the phytopathogen system wheat-Fusarium graminearum. The economic impact of FHB leads to the need for innovation. Currently used fungicides have been shown to be effective over the years, but recently cereal infecting Fusaria have developed resistance. Our work presents a new perspective on target selection to allow the development of new fungicides. We developed an innovative approach combining both genomic analysis and molecular modeling to increase the discovery for new chemical compounds with both safety and low environmental impact. Our protein targets selection revealed 13 candidates with high specificity, essentiality and potentially assayable with a favorable accessibility to drug activity. Among them, three proteins: trichodiene synthase, endoglucanase-5 and ERG6 were selected for deeper structural analyses to identify new putative fungicides. Overall, the bioinformatics filtering for novel protein targets applied for agricultural purposes is a response to the demand for chemical crop protection. The availability of the genome, secretome and PHI-base allowed the enrichment of the search that combined experimental data in planta. The homology modeling and molecular dynamics simulations allowed the acquisition of three robust and stable conformers. From this step, approximately ten thousand compounds have been virtually screened against three candidates. Forty-five top-ranked compounds were selected from docking results as presenting better interactions and energy at the binding pockets and no toxicity. These compounds may act as inhibitors and lead to the development of new fungicides.展开更多
This paper explores the question of how we can know if Artificial Intelligence(AI)systems have become or are becoming sentient.After an overview of some arguments regarding AI sentience,it proceeds to an outline of th...This paper explores the question of how we can know if Artificial Intelligence(AI)systems have become or are becoming sentient.After an overview of some arguments regarding AI sentience,it proceeds to an outline of the notion of negation in the philosophy of Josiah Royce,which is then applied to the arguments already presented.Royce’s notion of the primitive dyadic and symmetric negation relation is shown to bypass such arguments.The negation relation and its expansion into higher types of order are then considered with regard to how,in small variations of active negation,they would disclose sentience in AI systems.Finally,I argue that the much-hyped arguments and apocalyptic speculations regarding Artificial General Intelligence(AGI)takeover and similar scenarios,abetted by the notion of unlimited data,are based on a fundamental misunderstanding of how entities engage their experience.Namely,limitation,proceeding from the symmetric negation relation,expands outward into higher types of order in polyadic relations,wherein the entity self-limits and creatively moves toward uniqueness.展开更多
According to the industry,the value of wood logs is heavily influenced by their internal structure,particularly the distribution of knots within the trees.Nowadays,CT scanners combined with classical computer vision a...According to the industry,the value of wood logs is heavily influenced by their internal structure,particularly the distribution of knots within the trees.Nowadays,CT scanners combined with classical computer vision approach are the most common tool for obtaining reliable and accurate images of the interior structure of trees.Knowing where the tree semantic features,especially knots,contours and centers are within a tree could improve the efficiency of the overall tree industry by minimizing waste and enhancing the quality of wood-log by-products.However,this requires to automatically process the CT-scanner images so as to extract the different elements such as tree centerline,knot localization and log contour,in a robust and efficient manner.In this paper,we propose an effective methodology based on deep learning for performing these different tasks by processing CTscanner images with deep convolutional neural networks.To meet this objective,three end-to-end trainable pipelines are proposed.The first pipeline is focused on centers detection using CNNs architecture with a regression head,the second and the third one address contour estimation and knot detection as a binary segmentation task based on an Encoder-Decoder architecture.The different architectures are tested on several tree species.With these experiments,we demonstrate that our approaches can be used to extract the different elements of trees in a precise manner while preserving good performances of robustness.The main objective was to demonstrate that methods based on deep learning might be used and have a relevant potential for segmentation and regression on CT-scans of tree trunks.展开更多
The open science movement has gained significant momentum within the last few years.This comes along with the need to store and share research artefacts,such as publications and research data.For this purpose,research...The open science movement has gained significant momentum within the last few years.This comes along with the need to store and share research artefacts,such as publications and research data.For this purpose,research repositories need to be established.A variety of solutions exist for implementing such repositories,covering diverse features,ranging from custom depositing workflows to social media-like functions.In this article,we introduce the FAIREST principles,a framework inspired by the well-known FAIR principles,but designed to provide a set of metrics for assessing and selecting solutions for creating digital repositories for research artefacts.The goal is to support decision makers in choosing such a solution when planning for a repository,especially at an institutional level.The metrics included are therefore based on two pillars:(1)an analysis of established features and functionalities,drawn from existing dedicated,general purpose and commonly used solutions,and(2)a literature review on general requirements for digital repositories for research artefacts and related systems.We further describe an assessment of 11 widespread solutions,with the goal to provide an overview of the current landscape of research data repository solutions,identifying gaps and research challenges to be addressed.展开更多
Current applications using single unmanned vehicle have been gradually extended to multiple ones due to their increased efficiency in mission accomplishment, expanded coverage areas and ranges, as well as enhanced sys...Current applications using single unmanned vehicle have been gradually extended to multiple ones due to their increased efficiency in mission accomplishment, expanded coverage areas and ranges, as well as enhanced system reliability. This paper presents a flocking control method with application to a fleet of unmanned quadrotor helicopters (UQHs). Three critical characteristics of formation keeping, collision avoidance, and velocity matching have been taken into account in the algorithm development to make it capable of accomplishing the desired objectives (like forest/pipeline surveillance) by safely and efficiently operating a group of UQHs. To achieve these, three layered system design philosophy is considered in this study. The first layer is the flocking controller which is designed based on the kinematics of UQH. The modified Cucker and Smale model is used for guaranteeing the convergence of UQHs to flocking, while a repelling force between each two UQHs is also added for ensuring a specified safety distance. The second layer is the motion controller which is devised based on the kinetics of UQH by employing the augmented state-feedback control approach to greatly minimize the steady-state error. The last layer is the UQH system along with its actuators. Two primary contributions have been made in this work: first, different from most of the existing works conducted on agents with double integrator dynamics, a new flocking control algorithm has been designed and implemented on a group of UQHs with nonlinear dynamics. Furthermore, the constraint of fixed neighbouring distance in formation has been relaxed expecting to significantly reduce the complexity caused by the increase of agents number and provide more flexibility to the formation control. Extensive numerical simulations on a group of UQH nonlinear models have been carried out to verify the effectiveness of the proposed method.展开更多
基金Department SAD of INRA(French National Institute for Agricultural Research)and the Council of Lorraine for supporting the Ph D fellowship of the first author
文摘Grassland, as one of the largest ecosystems on the earth, supports various goods and services to humanity.Historically, humans have increased agricultural output primarily by cropland expansion and agricultural intensification.The cropland area was primarily gained at the expense of grassland and forests.Apart from grassland conversion, increasing consumption of calorie- and meat-intensive diets drives the intensification of livestock systems, which is shifting steadily from grazing to feeding with crops.To cope with the environmental degradation due to agriculture, various forms of ‘green payment' were implemented to promote the adoption of sustainable farming practices over the last two decades in the European Union.The aim of this study is to monitor the recent transitions(1992–2010) between grassland and cropland during two Common Agricultural Policy(CAP) reforms at the French mainland scale.We proposed an innovative approach to link grassland conversion to agricultural commodities and farming systems practices.We first assessed the grassland-to-cropland conversion and further investigated the crop sequence patterns that were observed to be dominant after the conversion through mining land-cover survey data Teruti and Teruti-Lucas.We found the trends of the transitions between grassland and cropland over the two time intervals: The loss of grassland(1992–2003) and restoration or re-expansion of grassland(2006–2010) in mainland France.Our finding on the crop sequence patterns after the grassland conversion reveals two notable evolutions of agricultural production systems.These evolutions were related to the increase in the proportion of cropland in the total agricultural land use.One evolution was most likely influenced by the demand for fodder: The conversion from grazing livestock to feeding livestock.Another evolution was the conversion from livestock production to field crop production.Our results indicate that the intensification of livestock farming systems continued over the last two decades in France.We conclude that, the approach developed in this study can be considered as a generic method for monitoring the transitions between grassland and cropland and further identifying the crop sequence patterns after the grassland conversion from time-series land cover data.
文摘Industrial woven meshes are composed of metal materials and are often used in construction,industrial and residential activities or applications.The objective of this work is defect detection in industrial fabrics in the quality control stage.In order to overcome the limitations of manual methods,which are often tedious and time-consuming,we propose a strategy that can automatically detect defects in micrometric steel meshes by means of a Convolutional Neural Network.The database used for such a purpose comes from real problem data for anomaly detection in micrometric woven meshes.This detection is performed through supervised classification with a Convolutional Neural Network using a VGG19 architecture.We define a pipeline and a strategy to tackle the related small amount of data.It includes i)augmenting the database with translation,rotation and symmetry,ii)using pre-trained weights and iii)checking the learning curve behaviour through cross-validation.The obtained results show that,despite the small size of our databases,detection accuracy of 96%was reached.
文摘Fusarium head blight (FHB) is a destructive disease of wheat and other cereals. FHB occurs in Europe, North America and around the world causing significant losses in production and endangers human and animal health. In this article, we provide the strategic steps for the specific target selection for the phytopathogen system wheat-Fusarium graminearum. The economic impact of FHB leads to the need for innovation. Currently used fungicides have been shown to be effective over the years, but recently cereal infecting Fusaria have developed resistance. Our work presents a new perspective on target selection to allow the development of new fungicides. We developed an innovative approach combining both genomic analysis and molecular modeling to increase the discovery for new chemical compounds with both safety and low environmental impact. Our protein targets selection revealed 13 candidates with high specificity, essentiality and potentially assayable with a favorable accessibility to drug activity. Among them, three proteins: trichodiene synthase, endoglucanase-5 and ERG6 were selected for deeper structural analyses to identify new putative fungicides. Overall, the bioinformatics filtering for novel protein targets applied for agricultural purposes is a response to the demand for chemical crop protection. The availability of the genome, secretome and PHI-base allowed the enrichment of the search that combined experimental data in planta. The homology modeling and molecular dynamics simulations allowed the acquisition of three robust and stable conformers. From this step, approximately ten thousand compounds have been virtually screened against three candidates. Forty-five top-ranked compounds were selected from docking results as presenting better interactions and energy at the binding pockets and no toxicity. These compounds may act as inhibitors and lead to the development of new fungicides.
基金funded by AI-PROFICIENT which has received funding from the European Union’s Horizon 2020 research and innovation program(No.957391).
文摘This paper explores the question of how we can know if Artificial Intelligence(AI)systems have become or are becoming sentient.After an overview of some arguments regarding AI sentience,it proceeds to an outline of the notion of negation in the philosophy of Josiah Royce,which is then applied to the arguments already presented.Royce’s notion of the primitive dyadic and symmetric negation relation is shown to bypass such arguments.The negation relation and its expansion into higher types of order are then considered with regard to how,in small variations of active negation,they would disclose sentience in AI systems.Finally,I argue that the much-hyped arguments and apocalyptic speculations regarding Artificial General Intelligence(AGI)takeover and similar scenarios,abetted by the notion of unlimited data,are based on a fundamental misunderstanding of how entities engage their experience.Namely,limitation,proceeding from the symmetric negation relation,expands outward into higher types of order in polyadic relations,wherein the entity self-limits and creatively moves toward uniqueness.
基金the support from the French National Research Agency,in the framework of the project WoodSeer,ANR-19-CE10-011.
文摘According to the industry,the value of wood logs is heavily influenced by their internal structure,particularly the distribution of knots within the trees.Nowadays,CT scanners combined with classical computer vision approach are the most common tool for obtaining reliable and accurate images of the interior structure of trees.Knowing where the tree semantic features,especially knots,contours and centers are within a tree could improve the efficiency of the overall tree industry by minimizing waste and enhancing the quality of wood-log by-products.However,this requires to automatically process the CT-scanner images so as to extract the different elements such as tree centerline,knot localization and log contour,in a robust and efficient manner.In this paper,we propose an effective methodology based on deep learning for performing these different tasks by processing CTscanner images with deep convolutional neural networks.To meet this objective,three end-to-end trainable pipelines are proposed.The first pipeline is focused on centers detection using CNNs architecture with a regression head,the second and the third one address contour estimation and knot detection as a binary segmentation task based on an Encoder-Decoder architecture.The different architectures are tested on several tree species.With these experiments,we demonstrate that our approaches can be used to extract the different elements of trees in a precise manner while preserving good performances of robustness.The main objective was to demonstrate that methods based on deep learning might be used and have a relevant potential for segmentation and regression on CT-scans of tree trunks.
基金supported by the Fundacao para a Ciencia e a Tecnologia through the LASIGE Research DB/00408/2020,UIDP/00408/2020supported by the Federal Ministry of Education and Research of Germany(BMBF)un no.16Dll128("Deutsches Internet-Institut").
文摘The open science movement has gained significant momentum within the last few years.This comes along with the need to store and share research artefacts,such as publications and research data.For this purpose,research repositories need to be established.A variety of solutions exist for implementing such repositories,covering diverse features,ranging from custom depositing workflows to social media-like functions.In this article,we introduce the FAIREST principles,a framework inspired by the well-known FAIR principles,but designed to provide a set of metrics for assessing and selecting solutions for creating digital repositories for research artefacts.The goal is to support decision makers in choosing such a solution when planning for a repository,especially at an institutional level.The metrics included are therefore based on two pillars:(1)an analysis of established features and functionalities,drawn from existing dedicated,general purpose and commonly used solutions,and(2)a literature review on general requirements for digital repositories for research artefacts and related systems.We further describe an assessment of 11 widespread solutions,with the goal to provide an overview of the current landscape of research data repository solutions,identifying gaps and research challenges to be addressed.
文摘Current applications using single unmanned vehicle have been gradually extended to multiple ones due to their increased efficiency in mission accomplishment, expanded coverage areas and ranges, as well as enhanced system reliability. This paper presents a flocking control method with application to a fleet of unmanned quadrotor helicopters (UQHs). Three critical characteristics of formation keeping, collision avoidance, and velocity matching have been taken into account in the algorithm development to make it capable of accomplishing the desired objectives (like forest/pipeline surveillance) by safely and efficiently operating a group of UQHs. To achieve these, three layered system design philosophy is considered in this study. The first layer is the flocking controller which is designed based on the kinematics of UQH. The modified Cucker and Smale model is used for guaranteeing the convergence of UQHs to flocking, while a repelling force between each two UQHs is also added for ensuring a specified safety distance. The second layer is the motion controller which is devised based on the kinetics of UQH by employing the augmented state-feedback control approach to greatly minimize the steady-state error. The last layer is the UQH system along with its actuators. Two primary contributions have been made in this work: first, different from most of the existing works conducted on agents with double integrator dynamics, a new flocking control algorithm has been designed and implemented on a group of UQHs with nonlinear dynamics. Furthermore, the constraint of fixed neighbouring distance in formation has been relaxed expecting to significantly reduce the complexity caused by the increase of agents number and provide more flexibility to the formation control. Extensive numerical simulations on a group of UQH nonlinear models have been carried out to verify the effectiveness of the proposed method.