Search

Your search keyword '"Jean-François Mari"' showing total 92 results
Start Over "Jean-François Mari"

Refine your results

more »

more »

more »

more »
92 results on '"Jean-François Mari"'

2. Characterizing historical (1992–2010) transitions between grassland and cropland in mainland France through mining land-cover survey data

Author

Ying Xiao, Catherine Mignolet, Jean-François Mari, and Marc Benoît

Subjects
conversion, crop sequence patterns, land-cover survey, agricultural land-use change, Agriculture (General), S1-972
Abstract

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.

Published
2015
Full Text
View/download PDF

26. Simulation temporelle et spatiale des changements d'occupation du sol par modélisation stochastique

Author

Marc Benoit, Jean-François Mari, Arnaud Gobillot, Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Unité de recherche SAD ASTER - Station de Mirecourt (INRA SAD), Agrivair, AGREV 3, Nestle-water, Centre National de la Recherche Scientifique (CNRS), Cyril De Runz, Éric Kergosien, Christian Sallaberry, Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)

Subjects
0106 biological sciences, land use change, protection de l’eau, 010504 meteorology & atmospheric sciences, [SDV]Life Sciences [q-bio], prospective simulation, LUCC, General Medicine, modèle neutre, 15. Life on land, landscape, 010603 evolutionary biology, 01 natural sciences, neutral model, 6. Clean water, [SHS]Humanities and Social Sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 13. Climate action, water protection, simulation prospective, HMM, paysage, protection de l'eau, hmm, lucc, 0105 earth and related environmental sciences
Abstract

The landscape patterns are the results of the human activity that adapts the land cover and its use (LUC) to economic and social constraints/opportunities encountered by various actors. The temporal and spatial arrangement of LUC has a strong influence on environmental risks. This paper presents a methodology based on stochastic models to identify, locate and simulate the temporal LUCC of regions differentiated by their successions by means of “neutral” models. The differences between simulated and observed data make it possible to detect breaks in land-use development and planning. We assess our method on data that come from surveys in the Vittel-Contrexéville watershed (East of France) which is subject to water quality issues., L’organisation d’un territoire est le reflet de l’activité humaine qui y adapte la couverture du sol et son usage en fonction des contraintes ou opportunités techniques, économiques et sociétales. L’arrangement temporel et spatial des occupations du sol a une forte influence sur les risques environnementaux. Cet article présente une méthodologie à base de modèles stochastiques pour identifier, localiser et simuler les occupations temporelles des régions différenciées par leurs successions de culture dans la perspective de construction d’un modèle « neutre ». L’écart entre données simulées et observées permet de déceler des ruptures dans le processus de mise en valeur du territoire. Les données utilisées dans cette étude proviennent d’enquêtes effectuées sur l’impluvium de Vittel-Contrexéville concernant la qualité des eaux souterraines.

Published
2018
Full Text
View/download PDF

30. Characterizing historical (1992–2010) transitions between grassland and cropland in mainland France through mining land-cover survey data

Author

Jean-François Mari, Catherine Mignolet, Marc Benoit, Ying Xiao, Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)

Subjects
Agriculture (General), [SDV.SA.AGRO]Life Sciences [q-bio]/Agricultural sciences/Agronomy, agricultural land-use change, Plant Science, Land cover, Biochemistry, Grassland, S1-972, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Food Animals, Agricultural land, Sustainable agriculture, media_common.cataloged_instance, conversion, European union, Agricultural productivity, media_common, 2. Zero hunger, geography.geographical_feature_category, Ecology, land-cover survey, Agroforestry, business.industry, crop sequence patterns, 15. Life on land, Geography, 13. Climate action, Agriculture, Animal Science and Zoology, "crop sequence patterns", business, Agronomy and Crop Science, Common Agricultural Policy, Food Science
Abstract

International audience; 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.

Published
2015
Full Text
View/download PDF

31. Studying crop sequences with CarrotAge, a HMM-based data mining software

Author

Catherine Mignolet, F. Le Ber, Jean-François Mari, Marc Benoit, Céline Schott, Centre d'Ecologie Végétale et d'Hydrologie (CEVH), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université Louis Pasteur - Strasbourg I, Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP), Unité expérimentale SAD - Station de Mirecourt (MIRECOURT), Institut National de la Recherche Agronomique (INRA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and Unité expérimentale SAD - Station de Mirecourt (INRA SAD)

Subjects
[SDV.OT]Life Sciences [q-bio]/Other [q-bio.OT], 010504 meteorology & atmospheric sciences, Computer science, computer.software_genre, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Set (abstract data type), Software, Knowledge extraction, Agricultural land, Hidden Markov models, Hidden Markov model, Data mining, 0105 earth and related environmental sciences, 2. Zero hunger, Land use, business.industry, Ecological Modeling, 04 agricultural and veterinary sciences, 15. Life on land, Partition (database), Crop sequences, 040103 agronomy & agriculture, 0401 agriculture, forestry, and fisheries, business, computer, Row
Abstract

We have developed a knowledge discovery system based on high-order hidden Markov models for analyzing spatio-temporal data bases. This system, named CarrotAge , takes as input an array of discrete data – the rows represent the spatial sites and the columns the time slots – and builds a partition together with its a posteriori probability. CarrotAge has been developed for studying the cropping patterns of a territory. It uses therefore an agricultural drench database, named Ter-Uti , which records every year the land-use category of a set of sites regularly spaced. The results of CarrotAge are interpreted by agronomists and used in research works linking agricultural land use and water management. Moreover, CarrotAge can be used to find out and study crop sequences in large territories, that is a main question for agricultural and environmental research, as discussed in this paper.

Published
2006
Full Text
View/download PDF

32. Probabilistic and Statistical Methods in Computer Science

Author

Jean-François Mari, René Schott, Jean-François Mari, and René Schott

Subjects
Computer science--Mathematics, Computer science--Statistical methods, Probabilities
Abstract

Probabilistic and Statistical Methods in Computer Science presents a large variety of applications of probability theory and statistics in computer science and more precisely in algorithm analysis, speech recognition and robotics. It is written on a self-contained basis: all probabilistic and statistical tools needed are introduced on a comprehensible level. In addition all examples are worked out completely. Most of the material is scattered throughout available literature. However, this is the first volume that brings together all of this material in such an accessible format. Probabilistic and Statistical Methods in Computer Science is intended for students in computer science and applied mathematics, for engineers and for all researchers interested in applications of probability theory and statistics. It is suitable for self study as well as being appropriate for a course or seminar.

Published
2013

33. Modeling the spatial distribution of crop sequences at a large regional scale using land-cover survey data: A case from France

Author

Ying Xiao, Jean-François Mari, Marc Benoit, Catherine Mignolet, Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Inria-Inria, and Université de Lorraine (UL)

Subjects
[SDV]Life Sciences [q-bio], Cropping systems, Land management, [SDV.SA.AGRO]Life Sciences [q-bio]/Agricultural sciences/Agronomy, Land cover, Agricultural engineering, Horticulture, cropping system, Agricultural land-use, [SHS]Humanities and Social Sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Agricultural land, Hidden Markov models, Agricultural productivity, 2. Zero hunger, hidden markov model, business.industry, Agroforestry, crop sequence, Forestry, 15. Life on land, Teruti survey, Computer Science Applications, Cropping patterns, Geography, Crop sequences, Agriculture, cropping pattern, Monoculture, Scale (map), business, Agronomy and Crop Science, Cropping
Abstract

International audience; Assessing the environmental impacts of agricultural production systems requires spatially explicit information regarding cropping systems. Projecting changes in agricultural land use that are caused by changes in land management practices for analyzing the performance of land activity-related policies, such as agricultural policies, also requires this type of data for model inputs. Crop sequences, which are vital and widely adopted agricultural practices, are difficult to directly detect at a regional scale. This study presents innovative stochastic data mining that was aimed at describing the spatial distribution of crop sequences at a large regional scale. The data mining is performed by hidden Markov models and an unsupervised clustering analysis that processes sequentially observed (from 1992 to 2003) land-cover survey data on the French mainland named Teruti. The 2549 3-year crop sequences were first identified as major crop sequences across the entire territory, which included 406 (merged) agricultural districts, using hidden Markov models. The 406 (merged) agricultural districts were then grouped into 21 clusters according to the similarity of the probabilities of occurrences of major 3-year crop sequences using hierarchical clustering analysis. Four cropping systems were further identified: vineyard-based cropping systems, maize monoculture and maize/wheat-based cropping systems, temporary pasture and maize-based cropping systems and wheat and barley-based cropping systems. The modeling approach that is presented in this study provides a tool to extract large-scale cropping patterns from increasingly available time series data on land-cover and land-use. With this tool, users can (a) identify the homogeneous zones in terms of fixed-length crop sequences across a large territory, (b) understand the characteristics of cropping systems within a region in terms of typical crop sequences, and (c) identify the major crop sequences of a region according to the probabilities of occurrences.; L'évaluation des impacts des systèmes de production agricole requiert une information spatiale explicite sur les système de culture. Les successions de culture sont des pratiques largement adoptées mais difficiles à détecter. Cette étude présente une nouvelle méthode de fouille de données pour décrire la distribution spatiale des successions de cultures à grande échelle. La fouille de données s'appuie sur des modèles de Markov cachés du second ordre qui effectuent une classification non supervisée des successions de cultures pratiquées sur la totalité du territoire national de 1992 à 2003. 2549 triplets de cultures ont été tout d'abord identifiés en tant que successions principales sur 406 petites régions agricoles. 21 classes ont été dégagées par une classification ascendante hiérarchique. 4 systèmes de cultures ont été mis en lumière: Vignoble, prairies temporaires, système centré maïs, système centré blé - orge.

Published
2014
Full Text
View/download PDF

34. Time space stochastic modelling of agricultural landscapes for environmental issues

Author

El Ghali Lazrak, Marc Benoit, Jean-François Mari, Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), and Unité de recherche SAD ASTER - Station de Mirecourt (INRA SAD)

Subjects
Environmental Engineering, Geographic information system, Stochastic modelling, Computer science, Markov process, 02 engineering and technology, Machine learning, computer.software_genre, temporal GIS, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], symbols.namesake, Multiple time dimensions, 0202 electrical engineering, electronic engineering, information engineering, Cluster analysis, ACM: J.: Computer Applications/J.0: GENERAL, Hierarchical Hidden Markov Model, second-order HMM, Markov random field, land-use successions, business.industry, Ecological Modeling, Hierarchical hidden Markov model, 04 agricultural and veterinary sciences, data mining, 15. Life on land, Temporal database, landscape organization, 040103 agronomy & agriculture, symbols, 0401 agriculture, forestry, and fisheries, 020201 artificial intelligence & image processing, Artificial intelligence, Data mining, business, MRF, computer, Software
Abstract

Since the initial point of Langran (1993) saying that Geographic Information Systems (GIS) were poorly equipped to handle temporal data, many researchers have sought to integrate the time dimension into GIS (Roddick et?al., 2001). We present a time space modelling approach - and a generic software named ARPEnTAge - capable of clustering a territory based on its pluri-annual land-use organization. By adding the ability to represent, locate and visualize temporal changes in the territory, ARPEnTAge provides tools to build a Time-Dominant GIS. One main Markovian assumption is stated: the land-use succession in a given place depends only on the land-use successions in neighbouring plots. By means of stochastic models such as a Hierarchical Hidden Markov Model and a Markov random field, ARPEnTAge performs an unsupervised clustering of a territory in order to reveal patches characterized by time space regularities in the land-use successions. Two case studies are developed involving two territories carrying environmental issues. Those territories have various sizes and are parameterized using long term surveys and/or remote sensing data. In both cases, ARPEnTAge detects, locates and displays in a GIS the temporal changes. This gives valuable information on the spatial and time dynamics of the land-use organization of those territories. Provide an unsupervised time space clustering software to mining land use dynamics.Provide a new way of estimating a class assignment in K-color Potts model based on the mean field paradigm.Implement a time dominant approach in a GIS.

Published
2013
Full Text
View/download PDF

35. Combining farmers' decision rules and landscape stochastic regularities for landscape modelling

Author

Noémie Schaller, El Ghali Lazrak, Jean-François Mari, Philippe Martin, Christine Aubry, Marc Benoit, Sciences pour l'Action et le Développement : Activités, Produits, Territoires (SADAPT), Institut National de la Recherche Agronomique (INRA)-AgroParisTech, Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), ANR BioDivAgri M project, and AgroParisTech-Institut National de la Recherche Agronomique (INRA)

Subjects
Landscape epidemiology, conceptual model, Geography, Planning and Development, 0211 other engineering and technologies, 02 engineering and technology, landscape patterns, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], spatiotemporal analysis, landscape agronomy, Nature and Landscape Conservation, 2. Zero hunger, Sustainable landscaping, Ecology, business.industry, on-farm survey, Environmental resource management, Conceptual model (computer science), Land-use dynamic, 021107 urban & regional planning, crop allocation, 04 agricultural and veterinary sciences, Decision rule, data mining, 15. Life on land, Geography, 13. Climate action, Landscape assessment, 040103 agronomy & agriculture, Spatial ecology, 0401 agriculture, forestry, and fisheries, Landscape ecology, [SDE.BE]Environmental Sciences/Biodiversity and Ecology, Scale (map), business, crop succession
Abstract

International audience; Landscape spatial organization (LSO) strongly impacts many environmental issues. Modelling agricultural landscapes and describing meaningful landscape patterns are thus regarded as key-issues for designing sustainable landscapes. Agricultural landscapes are mostly designed by farmers. Their decisions dealing with crop choices and crop allocation to land can be generic and result in landscape regularities, which determine LSO. This paper comes within the emerging discipline called "landscape agronomy", aiming at studying the organization of farming practices at the landscape scale. We here aim at articulating the farm and the landscape scales for landscape modelling. To do so, we develop an original approach consisting in the combination of two methods used separately so far: the identification of explicit farmer decision rules through on-farm surveys methods and the identification of landscape stochastic regularities through data-mining. We applied this approach to the Niort plain landscape in France. Results show that generic farmer decision rules dealing with sunflower or maize area and location within landscapes are consistent with spatiotemporal regularities identified at the landscape scale. It results in a segmentation of the landscape, based on both its spatial and temporal organization and partly explained by generic farmer decision rules. This consistency between results points out that the two modelling methods aid one another for land-use modelling at landscape scale and for understanding the driving forces of its spatial organization. Despite some remaining challenges, our study in landscape agronomy accounts for both spatial and temporal dimensions of crop allocation: it allows the drawing of new spatial patterns coherent with land-use dynamics at the landscape scale, which improves the links to the scale of ecological processes and therefore contributes to landscape ecology.; L'organisation du paysage influe sur les problèmes environnementaux. Modéliser les paysages pour les décrire à l'aide de formes significatives est une étage clé. Les paysages agricoles sont principalement construits par les agriculteurs dont les décision d'assolement peuvent être génériques et déterminer des régularités dans l'organisation du paysage. Cet article contribue à l'agronomie des paysage qui est une discipline émergente. Nous cherchons à articuler les échelles du paysage et de l'exploitation agricole en développant deux méthodes : l'une consiste à identifier les décisions des agriculteurs par le bais d'enquêtes, l'autre consiste à retrouver des régularités stochastiques dans le paysage par le bais de fouille de données. Nous avons appliqué cette approche au paysage de la plaine de Niort en France. Les résultats montrent que les décisions des agriculteurs en matière de tournesol et maïs sont génériques et ont des effets sur le paysages que des méthodes de fouille de données révèlent et quantifient.

Published
2012
Full Text
View/download PDF

36. In silico prediction of horizontal gene transfer in Streptococcus thermophilus

Author

Thomas Bovbjerg Rasmussen, Annabelle Thibessard, Morten Danielsen, Jean-François Mari, Catherine Eng, Pierre Leblond, Laboratoire de génétique et microbiologie (LGM), Institut National de la Recherche Agronomique (INRA)-Université Henri Poincaré - Nancy 1 (UHP), Department of Assays (Chr. Hansen A/S), Chr. Hansen, Department of Physiology, innovation, Chr. Hansen A/S, Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Streptococcus thermophilus, Gene Transfer, Horizontal, Genomic Islands, In silico, Biology, Biochemistry, Microbiology, Genome, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Evolution, Molecular, 03 medical and health sciences, Genome mining, Databases, Genetic, Genetics, Recombinase, Data Mining, Molecular Biology, Gene, Gene transfer, Phylogeny, 030304 developmental biology, 0303 health sciences, Stochastic Processes, 030306 microbiology, Genetic transfer, Molecular Sequence Annotation, General Medicine, Gene Annotation, biology.organism_classification, [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM], Markov Chains, Genes, Bacterial, Horizontal gene transfer, bacteria, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], Algorithms, Genome, Bacterial
Abstract

International audience; A combination of gene loss and acquisition through horizontal gene transfer (HGT) is thought to drive Streptococcus thermophilus adaptation to its niche, i.e. milk. In this study, we describe an in silico analysis com- bining a stochastic data mining method, analysis of homologous gene distribution and the identification of features frequently associated with horizontally transferred genes to assess the proportion of the S. thermophilus gen- ome that could originate from HGT. Our mining approach pointed out that about 17.7% of S. thermophilus genes (362 CDSs of 1,915) showed a composition bias; these genes were called 'atypical'. For 22% of them, their functional annotation strongly support their acquisition through HGT.; Une combinaison de perte / acquisition de gènes dans un processus de transfert horizontal (HGT) a conduit le Streptococcus thermophilus à s'adapter dans sa niche écologique, c-a-d le lait. Dans ce travail, nous décrivons une méthode de fouille de donnéeS fondée sur la modélisation stochastique, l'analyse de la distribution des gènes homologues et l'identification de traits fréquemment associés à des gènes transférés horizontalement afin d'évaluer quelle proportion du génome a été acquise par HGT. Nous approche montre que 17,7% approximativement des gènes de S. thermophilus (362 CDSs des 1915) ont un biais de composition; ces gènes sont dits "atypiques" . Pour 22% d'entre eux, leur annotation fonctionnelle laisse supposer fortement une acquisition par HGT.

Published
2011
Full Text
View/download PDF

37. Using Markov models to mine temporal and spatial data

Author

Florence Le Ber, Pierre Leblond, Catherine Eng, Jean-François Mari, Marc Benoit, Annabelle Thibessard, El Ghali Lazrak, Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Institut National de Recherche en Informatique et en Automatique (Inria), Biostatistique et Processus Spatiaux (BIOSP), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES), Dynamique des Génomes et Adaptation Microbienne (DynAMic), Institut National de la Recherche Agronomique (INRA)-Université de Lorraine (UL), Université Henri Poincaré - Nancy 1 (UHP), Kimito Funatsu (Editeur), Kiyoshi Hasegawa (Editeur), Mari, Jean-François, Biodiversité - Conservation de la biodiversité dans les agro-écosystèmes une modélisation spatialement explicite des paysages - - BIODIVAGRIM2007 - ANR-07-BDIV-0002 - BDIV - VALID, Kimito Funatsu and Kiyoshi Hasegawa, Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Hydrologie et de Géochimie de Strasbourg (LHyGeS), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Unité de recherche SAD ASTER - Station de Mirecourt (INRA SAD), Laboratoire de génétique et microbiologie (LGM), Institut National de la Recherche Agronomique (INRA)-Université Henri Poincaré - Nancy 1 (UHP), BIODIVAGRIM, ANR 07 BDIV 02,BIODIVAGRIM, ANR 07 BDIV 02, École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), ANR-07-BDIV-0002,BIODIVAGRIM,Conservation de la biodiversité dans les agro-écosystèmes une modélisation spatialement explicite des paysages(2007), Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS), and Institut national des sciences de l'Univers (INSU - CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer science, [SDV]Life Sciences [q-bio], CLASSIFICATION SPATIO-TEMPORELLE, computer.software_genre, Markov model, Machine learning, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], DATA MINING, [SHS]Humanities and Social Sciences, 010104 statistics & probability, 03 medical and health sciences, Software, HIDDEN MARKOV MODEL, [INFO]Computer Science [cs], 0101 mathematics, [MATH]Mathematics [math], Hidden Markov model, Spatial analysis, Hidden Markov Models, 030304 developmental biology, SPATIO-TEMPORAL CLASSIFICATION, 0303 health sciences, Markov chain, business.industry, MODÈLE MARKOV, Data mining, Artificial intelligence, business, computer, ACM: H.: Information Systems/H.2: DATABASE MANAGEMENT/H.2.8: Database Applications/H.2.8.0: Data mining, METHODOLOGIE
Abstract

Markov models represent a powerful way to approach the problem of mining time and spatial signals whose variability is not yet fully understood. In this chapter, we will present a general methodology to mine different kinds of temporal and spatial signals having contrasting properties: continuous or discrete with few or many modalities. This methodology is based on a high order Markov modelling as implemented in a free software: carottAge (Gnu GPL), Les modèles de Markov sont des modèles puissants pour analyser des signaux temporels et spatiaux dont la variabilité n'est pas entièrement comprise. Dans ce chapitre, nous présentons notre méthodologie pour fouiller différentes sortes de signaux ayant des propriétés différentes: signaux continus ou discrets, simples ou composites. Cette méthodologie s'appuie sur des modèles de Markov cachés du second-ordre tels qu'implantés dans la boîte à outils CarottAge (licence Gnu-GPL).

Published
2011

38. A new data mining approach for the detection of bacterial promoters combining stochastic and combinatorial methods

Author

Charu Asthana, Sébastien Hergalant, Pierre Leblond, Catherine Eng, Bertrand Aigle, Jean-François Mari, Laboratoire de génétique et microbiologie (LGM), Institut National de la Recherche Agronomique (INRA)-Université Henri Poincaré - Nancy 1 (UHP), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and Région Lorraine, CPER-MBI

Subjects
second-order hidden markov models, transcription factor binding site, Streptomyces coelicolor, Bacterial genome size, computer.software_genre, Genome, STOCHASTIC MODEL, COMBINATORIAL METHODS, SECOND-ORDER HIDDEN MARKOV MODELS, BACTERIAL PROMOTERS, TRANSCRIPTION FACTOR BINDING SITE, STREPTOMYCES COELICOLOR, DNA sequencing, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], modèle stochastique, 03 medical and health sciences, modèle mathématique, modèle de markov caché, Intergenic region, Sigma factor, Genetics, Hidden Markov model, Promoter Regions, Genetic, Molecular Biology, stochastic model, bacterial promoters, 030304 developmental biology, combinatorial methods, 0303 health sciences, Binding Sites, biology, Models, Genetic, 030302 biochemistry & molecular biology, biology.organism_classification, Streptomyces, Markov Chains, fouille de données, DNA binding site, Computational Mathematics, Computational Theory and Mathematics, Modeling and Simulation, Data mining, ACM: J.: Computer Applications/J.3: LIFE AND MEDICAL SCIENCES/J.3.0: Biology and genetics, computer, Genome, Bacterial
Abstract

International audience; We present a new data mining method based on stochastic analysis (HMM for Hidden Markov Model) and combinatorial methods for discovering new transcriptional factors in bacterial genome sequences. Sigma factor binding sites (SFBSs) were described as patterns of box1 - spacer - box2 corresponding to the -35 and -10 DNA motifs of bacterial promoters. We used a high-order Hidden Markov Model in which the hidden process is a second-order Markov chain. Applied on the genome of the model bacterium Streptomyces coelicolor (2), the a posteriori state probabilities revealed local maxima or peaks whose distribution was enriched in the intergenic sequences (``iPeaks'' for intergenic peaks). Short DNA sequences underlying the iPeaks were extracted and clustered by a hierarchical classification algorithm based on the SmithWaterman local similarity. Some selected motif consensuses were used as box1 (-35 motif) in the search of a potential neighbouring box2 (-10 motif) using a word enumeration algorithm. This new SFBS mining methodology applied on Streptomyces coelicolor was successful to retrieve already known SFBSs and to suggest new potential transcriptional factor binding sites (TFBSs). The well defined SigR regulon (oxidative stress response) was also used as a test quorum to compare first and second-order HMM. Our approach also allowed the preliminary detection of known SFBSs in Bacillus subtilis.

Published
2009
Full Text
View/download PDF

39. Landscape regularity modelling for environmental challenges in agriculture

Author

El Ghali Lazrak, Marc Benoit, Jean-François Mari, Agro-Systèmes Territoires Ressources Mirecourt (ASTER Mirecourt), Institut National de la Recherche Agronomique (INRA), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), CNRS Centre d'études biologiques de Chizé, INRA SAD, ANR-07-BDIV-0002,BIODIVAGRIM,Conservation de la biodiversité dans les agro-écosystèmes une modélisation spatialement explicite des paysages(2007), Unité de recherche SAD ASTER - Station de Mirecourt (INRA SAD), and ANR: BiodivAgrim,BiodivAgrim

Subjects
0106 biological sciences, Stochastic modelling, Cropping System, Ecology (disciplines), Geography, Planning and Development, Ecological succession, 010603 evolutionary biology, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], HMM, Hidden Markov model, Data mining, Nature and Landscape Conservation, 2. Zero hunger, Sustainable development, Ecology, Land use, business.industry, Environmental resource management, 04 agricultural and veterinary sciences, 15. Life on land, stochastic Modelling, Landscape Ecology, Geography, 040103 agronomy & agriculture, 0401 agriculture, forestry, and fisheries, Spatial variability, Landscape ecology, business
Abstract

International audience; In agricultural landscapes, methods to identify and describe meaningful landscape patterns play an important role to understand the interaction between landscape organization and ecological processes. We propose an innovative stochastic modelling method of agricultural landscape organization where the temporal regularities in land-use are first identified through recognized Land-Use Successions (LUS) before locating these successions in landscapes. These time-space regularities within landscapes are extracted using a new data mining method based on Hidden Markov Models. We applied this methodological proposal to the Niort Plain (West of France). We built a temporo-spatial analysis for this case study through spatially explicit analysis of Land Use Succession (LUS) dynamics. Implications and perspectives of such an approach, which links together the temporal and the spatial dimensions of the agricultural organization, are discussed by assessing the relationship between the agricultural landscape patterns defined using this approach and ecological data through an illustrative example of bird nests.

Published
2009
Full Text
View/download PDF

40. Neutral modelling of agricultural landscapes by tessellation methods—Application for gene flow simulation

Author

F. Le Ber, Jean-François Mari, Hervé Monod, Nathalie Colbach, Katarzyna Adamczyk, Claire Lavigne, Frédérique Angevin, Laboratoire d'Hydrologie et de Géochimie de Strasbourg (LHyGeS), Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Centre National de la Recherche Scientifique (CNRS), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Unité de recherche Plantes et Systèmes de Culture Horticoles (PSH), Institut National de la Recherche Agronomique (INRA), INRA - Mathématiques et Informatique Appliquées (Unité MIAJ), Unité Impacts Ecologiques des Innovations en Production Végétale (ECO-INNOV), Biologie et Gestion des Adventices (BGA), Etablissement National d'Enseignement Supérieur Agronomique de Dijon (ENESAD)-Institut National de la Recherche Agronomique (INRA)-Université de Bourgogne (UB), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Université de Bourgogne (UB)-Institut National de la Recherche Agronomique (INRA)-Etablissement National d'Enseignement Supérieur Agronomique de Dijon (ENESAD), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Hydrologie et de Géochimie de Strasbourg ( LHyGeS ), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg ( ENGEES ) -Université de Strasbourg ( UNISTRA ) -Institut national des sciences de l'Univers ( INSU - CNRS ) -Centre National de la Recherche Scientifique ( CNRS ), Knowledge representation, reasonning ( ORPAILLEUR ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Institut National de Recherche en Informatique et en Automatique ( Inria ) -Laboratoire Lorrain de Recherche en Informatique et ses Applications ( LORIA ), Institut National de Recherche en Informatique et en Automatique ( Inria ) -Université Henri Poincaré - Nancy 1 ( UHP ) -Université Nancy 2-Institut National Polytechnique de Lorraine ( INPL ) -Centre National de la Recherche Scientifique ( CNRS ) -Université Henri Poincaré - Nancy 1 ( UHP ) -Université Nancy 2-Institut National Polytechnique de Lorraine ( INPL ) -Centre National de la Recherche Scientifique ( CNRS ), Unité de recherche Plantes et Systèmes de Culture Horticoles ( PSH ), Institut National de la Recherche Agronomique ( INRA ), INRA - Mathématiques et Informatique Appliquées ( Unité MIAJ ), Unité Impacts Ecologiques des Innovations en Production Végétale ( ECO-INNOV ), Biologie et Gestion des Adventices ( BGA ), Etablissement National d'Enseignement Supérieur Agronomique de Dijon ( ENESAD ) -Institut National de la Recherche Agronomique ( INRA ) -Université de Bourgogne ( UB ), and Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)

Subjects
0106 biological sciences, [SDV.SA]Life Sciences [q-bio]/Agricultural sciences, Tessellation (computer graphics), field pattern, 010504 meteorology & atmospheric sciences, Computer science, 010603 evolutionary biology, 01 natural sciences, Domain (software engineering), [ SDV.EE ] Life Sciences [q-bio]/Ecology, environment, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], agricultural landscapes, genexp-landsites, neutral landscape models, [ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI], [ SDV.SA ] Life Sciences [q-bio]/Agricultural sciences, 0105 earth and related environmental sciences, 2. Zero hunger, [SDV.EE]Life Sciences [q-bio]/Ecology, environment, spatial point process, Orientation (computer vision), Ecological Modeling, Simulation modeling, Diagram, Process (computing), voronoi diagrams, 15. Life on land, rectangular tessellation, Field (geography), Voronoi diagram, Biological system, gene flow
Abstract

International audience; Neutral landscape models are not frequently used in the agronomical domain, whereas they would be very useful for studying given agro-ecological or physical processes. Contrary to ecological neutral landscape models, agricultural models have to represent and manage geometrical patches and thus should rely on tessellation methods. We present a three steps approach that aimed at simulating such landscapes. Firstly, we characterized the geometry of three real field patterns; secondly, we generated simulated field patterns with two tessellation methods attempting to control the value of some of the observed characteristics and, thirdly, we evaluated the simulated field patterns. For this evaluation, we considered that good simulated field patterns should capture characteristics of real landscapes that are important for the targeted agro-ecological process. Real landscapes and landscapes simulated using either a Voronoi or a rectangular tessellation were thus compared when used as input data within a gene flow model. The results showed that neither tessellation method captured field shapes correctly, thus leading to over or (small) under estimation of gene flow. The Voronoi tessellation, though, performed better than the rectangular tessellation. Possible research directions are proposed to improve the simulated patterns, including the use of post processing, the control of cell orientation or the implementation of other tessellation techniques.

Published
2009
Full Text
View/download PDF

41. Relative impacts of closest fields and background pollen on GM adventitious presence rates in non-GM harvests

Author

Frédérique Angevin, Klein, Etienne K., Jean-François Mari, Florence Le Ber, Katarzyna Adamczyk, Hervé Monod, Claire Lavigne, Unité Impacts Ecologiques des Innovations en Production Végétale (ECO-INNOV), Institut National de la Recherche Agronomique (INRA), Biostatistique et Processus Spatiaux (BIOSP), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Hydrologie et de Géochimie de Strasbourg (LHyGeS), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), INRA - Mathématiques et Informatique Appliquées (Unité MIAJ), Unité de recherche Plantes et Systèmes de Culture Horticoles (PSH), Biostatistique et Processus Spatiaux (BioSP), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Ecole et Observatoire des Sciences de la Terre (EOST), Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Ecole et Observatoire des Sciences de la Terre (EOST), and Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)

Subjects
[SDV.EE]Life Sciences [q-bio]/Ecology, environment, [SDV.SA]Life Sciences [q-bio]/Agricultural sciences, ComputingMilieux_MISCELLANEOUS, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience

Published
2009

42. How do genetically modified (GM) crops contribute to background levels of GM pollen in an agricultural landscape?

Author

Florence Le Ber, Etienne K. Klein, Frédérique Angevin, Katarzyna Adamczyk, Claire Lavigne, Hervé Monod, Jean-François Mari, Unité de recherche Plantes et Systèmes de Culture Horticoles (PSH), Institut National de la Recherche Agronomique (INRA), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Centre d'Ecologie Végétale et d'Hydrologie (CEVH), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université Louis Pasteur - Strasbourg I, INRA - Mathématiques et Informatique Appliquées (Unité MIAJ), and Unité Impacts Ecologiques des Innovations en Production Végétale (ECO-INNOV)

Subjects
0106 biological sciences, CORN, [SDV.SA]Life Sciences [q-bio]/Agricultural sciences, SPATIAL DISTRIBUTION, Pollination, Allogamy, Genetically modified crops, Biology, medicine.disease_cause, Spatial distribution, 010603 evolutionary biology, 01 natural sciences, Gene flow, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Crop, COEXISTENCE, Pollen, medicine, LANSCAPE, 2. Zero hunger, [SDV.EE]Life Sciences [q-bio]/Ecology, environment, Ecology, MODEL, TRANSGENIC, Biological dispersal, UPSCALING, CROSS POLLINATION, POLLEN DISPERSAL, 010606 plant biology & botany
Abstract

http://www3.interscience.wiley.com/cgi-bin/fulltext/120696197/HTMLSTART; International audience; It is well established that pollen-mediated gene flow among natural plant populations depends on a complex interaction between the spatial distribution of pollen sources and the short- and long-distance components of pollen dispersal. Despite this knowledge, spatial isolation strategies proposed in Europe to ensure the harvest purity of conventional crops are based on distance from the nearest genetically modified (GM) crop and on empirical data from two-plot experiments. Here, we investigate the circumstances under which the multiplicity of pollen sources over the landscape should be considered in strategies to contain GM crops. We simulated pollen dispersal over eighty 6 × 6 km simulated landscapes differing in field characteristics and in amount of GM and conventional maize. Pollen dispersal was modelled either via a Normal Inverse Gaussian (NIG, currently used for European coexistence studies) or a bivariate Student (2Dt) kernel. These kernels differ in their amount of short- and long-distance dispersal. We used linear models to analyse the impact of local and landscape variables on impurity rates (i.e. proportion of seeds sired by pollen from a transgenic crop) in conventional fields and quantified their increase due to dispersal from other than the closest GM crops. The average impurity rate over a landscape increased linearly with the proportion of GM maize over that landscape. The increase was twice as fast using the NIG kernel and was governed by the short-distance dispersal component. Variation in impurity rates largely depended on the distance to the closest GM crop and the size of the receptor field. However, impurity rates were generally underestimated when only dispersal from the closest GM field was considered. Synthesis and applications. Distance to the closest GM crop had most impact on impurity rates in conventional fields. However, impurity rates also depended on intermediate- to long-distance dispersal from distant GM crops. Therefore, isolation distances as currently defined will probably not allow long-term coexistence of GM and conventional crops, especially as the proportion of GM crops grown increases. We suggest strategies to account for this impact of long-distance dispersal.

Published
2008
Full Text
View/download PDF

43. GENEXP, un logiciel pour simuler des paysages agricoles

Author

Florence Le Ber, Claire Lavigne, Jean-François Mari, Katarzyna Adamczyk, Frédérique Angevin, Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP), Centre d'Ecologie Végétale et d'Hydrologie (CEVH), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université Louis Pasteur - Strasbourg I, Unité de recherche Plantes et Systèmes de Culture Horticoles (PSH), Institut National de la Recherche Agronomique (INRA), INRA - Mathématiques et Informatique Appliquées (Unité MIAJ), Unité Impacts Ecologiques des Innovations en Production Végétale (ECO-INNOV), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
modèles de Markov cachés, pavage, flux de gènes, succession de cultures, diagrammes de Voronoï, simulation, paysage agricole, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

National audience; Dans cet article, nous présentons un simulateur de paysages agricoles bidimensionnels, GenExP, qui engendre des découpages parcellaires à partir des paramètres statistiques de paysages réels, en utilisant une géométrie algorithmique classique. L'originalité de GenExP est d'être couplé d'une part avec le logiciel R -- qui autorise les paramétrages et traitements statistiques des parcellaires générés -- et d'autre part avec le logiciel de fouille de données CarottAge -- afin d'intégrer des successions de culture construites à partir de bases de données agricoles. Finalement, GenExP fournit des cartes pluriannuelles de paysages agricoles, qui peuvent être utilisées dans le cadre de nombreuses applications. Ainsi, les résultats des logiciels Mapod et GeneSys, qui sont utilisés par les agronomes et écologues pour simuler la dispersion des pollens et des graines d'OGM à l'échelle d'une ou quelques parcelles, peuvent être étendus dans le temps et l'espace et permettre une meilleure estimation des risques.

Published
2006

44. GenExP, un logiciel pour simuler des paysages agricoles en vue de l'étude de la diffusion de transgènes

Author

Florence Le Ber, Claire Lavigne, Jean-François Mari, Katarzyna Adamczyk, Frédérique Angevin, École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES), Unité de recherche Plantes et Systèmes de Culture Horticoles (PSH), Institut National de la Recherche Agronomique (INRA), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Unité de biométrie et intelligence artificielle de jouy, Unité Impacts Ecologiques des Innovations en Production Végétale (ECO-INNOV), and Unité de biométrie et intelligence artificielle de Jouy (MIA-JOUY)

Subjects
MODÈLES DE MARKOV CACHES, PAVAGE, HIDDEN MARKOV MODELS, DIAGRAMME DE VORONOI, [SDV]Life Sciences [q-bio], [SDE]Environmental Sciences, VORONOI TESSELLATION, [INFO]Computer Science [cs], [MATH]Mathematics [math], TESSELLATION, COLZA, [SHS]Humanities and Social Sciences
Abstract

CD Rom disponible sur HAL; International audience; Dans cet article, nous présentons un simulateur de paysages agricoles bidimensionnels, GENEXP, qui engendre des découpages parcellaires à partir des paramètres statistiques de paysages réels, en utilisant une géométrie algorithmique classique. L'originalité de GENEXP est d'être couplé d'une part avec le logiciel R qui autorise les paramétrages et traitements statistiques des parcellaires générés et d'autre part avec le logiciel de fouille de données CARROTAGE afin d'intégrer des successions de culture construites à partir de bases de données agricoles. Finalement, GENEXP fournit des cartes pluriannuelles de paysages agricoles, qui peuvent être utilisées dans le cadre de nombreuses applications. Ainsi, les résultats des logiciels MAPOD-maïs et GENESYS-colza, qui sont utilisés par les agronomes pour simuler la dispersion des pollens et des graines d'OGM à l'échelle d'une ou quelques parcelles, peuvent être étendus dans le temps et l'espace et permettre une meilleure estimation des risques.

Published
2006

45. Interaction between stochastic modeling and knowledge-based techniques in acoustic-phonetic decoding of speech

Author

Noëlle Carbonell, Jean-Paul Haton, Dominique Fohr, Jean-François Mari, and A. Kriouille

Subjects
Computer science, Stochastic process, business.industry, media_common.quotation_subject, Speech recognition, computer.software_genre, Field (computer science), Quality (business), Artificial intelligence, Hidden Markov model, business, computer, Decoding methods, Natural language processing, media_common
Abstract

We present in this paper a new approach to acoustic-phonetic decoding of continuous speech that consists of integrating the two most promising present techniques in the field, i.e. stochastic modeling and knowledge-based expert systems. Our group has been developing several systems based on these two techniques during the past 15 years or so. Our present goal is to mix both in order to improve the overall quality of automatic phonetic decoding. This paper is concerned with the first developments of the project. We first present the main characteristics of the components of the system and its general architecture. We also present and discuss preliminary results concerning the segmentation of the speech wave into phonetic units and the gross labeling of these segments.

Published
2005
Full Text
View/download PDF

46. Anticiper l'assolement pour mieux gérer les ressources en eau : comment valoriser des données d'occupation du sol ?

Author

Delphine Leenhardt, Flavie Cernesson, Jean-François Mari, Delphine Mesmin, AGroécologie, Innovations, teRritoires (AGIR), Institut National de la Recherche Agronomique (INRA)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-AgroParisTech-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Université de Toulouse (UT)-Université de Toulouse (UT), and Ecole Nationale du Génie Rural, des Eaux et des Forêts (ENGREF)-Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF)

Subjects
télédétection, [SDE]Environmental Sciences, gestion de l'eau, assolement, occupation du sol, modélisation
Abstract

[Departement_IRSTEA]DS [TR1_IRSTEA]METHODO / SYNERGIE; La connaissance de l'assolement d'une région constitue un enjeu important pour les gestionnaires de la ressource en eau, car cette information est un facteur clé de l'estimation des prélèvements en eau d'irrigation. Cet article restitue une expérience exploratoire basée sur le croisement de données d'occupation du sol échantillonnées dans le cadre de l'enquête Ter-Uti et de données d'occupation du sol acquises de manière exhaustive par enquête de terrain et sur une modélisation stochastique des règles de successions culturales. La discussion qui s'ensuit évalue la portée de cette étude exploratoire en fonction des premiers résultats et présente les possibilités qu'offre la télédétection. / Knowing the land use of a region is an important issue for water managers since it is a key factor for estimating irrigation withdrawals. This paper presents an exploratory work which involves sampled land use data from the Ter-Uti survey, exhaustive land use date from land survey and stochastic modelling of crop rotation rules. The limits of the present study, due to few case studies, are discussed, as well as the potentialities of the approach for managers and the opportunity offered by remote-sensing for improving the proposed methodology.

Published
2005

47. Learning to automatically detect features for mobile robots using second-order Hidden Markov Models

Author

Richard Washington, Jean-François Mari, Olivier Aycard, Geometry and Probability for Motion and Action (E-MOTION), Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble (GRAVIR - IMAG), Université Joseph Fourier - Grenoble 1 (UJF)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National Polytechnique de Grenoble (INPG)-Centre National de la Recherche Scientifique (CNRS)-Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria), Knowledge representation, reasonning (ORPAILLEUR), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), NASA Ames Research Center (ARC), Automatic Programming and Decisional Systems in Robotics (SHARP), INRIA, Laugier, Christian, and Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)

Subjects
FOS: Computer and information sciences, 0209 industrial biotechnology, Computer science, Computer Science - Artificial Intelligence, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], lcsh:TK7800-8360, 02 engineering and technology, lcsh:QA75.5-76.95, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Computer Science::Robotics, 020901 industrial engineering & automation, Artificial Intelligence, mobile robots, 0202 electrical engineering, electronic engineering, information engineering, Computer Science::Networking and Internet Architecture, sensor data interpretation, Computer vision, robot mobile, Hidden Markov model, interprétation de données, Interpretation (logic), Artificial neural network, business.industry, Maximum-entropy Markov model, lcsh:Electronics, hidden markov models, Pattern recognition, Mobile robot, Computer Science Applications, [INFO.INFO-OH] Computer Science [cs]/Other [cs.OH], Artificial Intelligence (cs.AI), Order (business), Pattern recognition (psychology), 020201 artificial intelligence & image processing, Artificial intelligence, lcsh:Electronic computers. Computer science, hmm, business, Software
Abstract

In this paper, we propose a new method based on Hidden Markov Models to interpret temporal sequences of sensor data from mobile robots to automatically detect features. Hidden Markov Models have been used for a long time in pattern recognition, especially in speech recognition. Their main advantages over other methods (such as neural networks) are their ability to model noisy temporal signals of variable length. We show in this paper that this approach is well suited for interpretation of temporal sequences of mobile-robot sensor data. We present two distinct experiments and results: the first one in an indoor environment where a mobile robot learns to detect features like open doors or T-intersections, the second one in an outdoor environment where a different mobile robot has to identify situations like climbing a hill or crossing a rock., 2004

Published
2003

48. A second-order HMM for high performance word and phoneme-based continuous speech recognition

Author

Jean-François Mari, J.-C. Junqua, and D. Fohr

Subjects
Computer science, business.industry, Speech recognition, Maximum likelihood, Word error rate, Markov process, Pattern recognition, Context (language use), Speaker recognition, Viterbi algorithm, Markov model, symbols.namesake, Phone, symbols, Artificial intelligence, Hidden Markov model, business
Abstract

In the field of speech recognition by stochastic methods, it is conventional to pursue approaches using first-order-hidden Markov models (HMM1s). Despite the success of this approach, it is still worth investigating if some of the drawbacks of HMM1s can be overcome, e.g. by using higher-order Markov processes. In this paper, we show that second-order hidden Markov models (HMM2s) can yield high performances in the context of continuous speech recognition. We first present the underlying equations and complexity of HMM2s in the maximum likelihood estimation (MLE) paradigm. Then, we show that in a connected word recognition task, such as spelled name recognition over the telephone, HMM2s outperform HMM1s. In the field of phoneme-based continuous speech recognition, we show that context-independent HMM2s can achieve more than 69% phone accuracy.

Published
2002
Full Text
View/download PDF

49. A recombination model for multi-band speech recognition

Author

Dominique Fohr, Jean-François Mari, Christophe Cerisara, and Jean-Paul Haton

Subjects
Audio mining, Noise, Voice activity detection, business.industry, Computer science, Speech recognition, Classifier (linguistics), Pattern recognition, Segmentation, Artificial intelligence, Speaker recognition, business, Speech processing
Abstract

We describe a continuous speech recognition system that uses the multi-band paradigm. This principle is based on the recombination of several independent sub-recognizers, each one assigned to a specific frequency band. The major issue of such systems consists of deciding at which time the recombination must be done. Our algorithm lets each band be totally independent from the others, and uses the different solutions to resegment the initial sentence. Finally, the bands are synchronously merged together, according to this new segmentation. The whole system is too complex to be entirely described here, and, in this paper, we concentrate on the synchronous recombination part, which is achieved by a classifier. The system has been tested in clean and noisy environments, and proved to be especially robust to noise.

Published
2002
Full Text
View/download PDF

50. An N-best strategy, dynamic grammars and selectively trained neural networks for real-time recognition of continuously spelled names over the telephone

Author

Jean-François Mari, J.-C. Junqua, Stéphane Valente, and Dominique Fohr

Subjects
Artificial neural network, Grammar, business.industry, Computer science, Speech recognition, media_common.quotation_subject, Speech processing, computer.software_genre, Rule-based machine translation, Feature (machine learning), Artificial intelligence, business, Hidden Markov model, computer, Natural language processing, media_common
Abstract

We introduce SmarTspelL, a new speaker-independent algorithm to recognize continuously spelled names over the telephone. Our method is based on an N-best multi-pass recognition strategy applying costly constraints when the number of possible candidates is low. This strategy outperforms an HMM recognizer using a grammar containing all the possible names. It is also more suitable to real-time implementation. For a 3388 name dictionary, a 95.3% name recognition rate is obtained. A real-time prototype has been implemented on a workstation. We also present comparisons of different feature sets for speech representation, and two speech recognition approaches based on first- and second-order HMMs.

Published
2002
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results