Florence Le Ber

Ecole Nationale du Génie de l'Eau et de l'Environnement de Strasbourg | ENGEES · Recherche

This article presents a clustering-based process for analyzing temporal sequences of physico-chemical measurements from French river monotoring networks. The method was originally developed for processing satellite images and adapted for river data, that are characterized by sampling variability and a great number of parameters, monitored in differ...

Most of available data are inherently relational, with e.g. temporal, spatial, causal or social relations. Besides, many datasets involve complex and voluminous data. Therefore, the exploration of relational data is a major challenge for Formal Concept Analysis (FCA). Relational Concept Analysis (RCA) is specifically designed to investigate the rel...

Natural convection in porous media (NCPM) is governed by highly nonlinear dynamics due to the dependence of fluid density and viscosity to temperature. Given the high computational cost associated with numerical modeling of NCPM, data-driven metamodels are commonly used to reduce the computational time in applications that require repetitive model...

Deep learning has become increasingly prevalent in a wide range of engineering contexts. In this work, we tried to make a connection between the groundwater engineering community and the field of deep learning. Natural convection in porous media is usually simulated using common numerical modeling tools with high computational costs. In this work,...

In this paper, we focus on the exploration of multi-relational datasets, and the various ways they can be analyzed using Relational Concept Analysis (RCA), an extension of Formal Concept Analysis (FCA). RCA uses several scaling operators that make the process highly tunable, allowing a high flexibility in the exploration and in the results. In retu...

Most of available data are inherently relational, with e.g. temporal, spatial, causal or social relations. Besides, many datasets involve complex and voluminous data. Therefore, the exploration of relational data is a major challenge for Formal Concept Analysis (FCA). Relational Concept Analysis (RCA) is specifically designed to investigate the rel...

We have implemented a specific data mining process to explore the relationship between biological indices and physico-chemical pressures in rivers. Data were collected in the framework of the French National monitoring network set up to assess the ecological status of rivers under the European Water Framework Directive (WFD). Chemical parameters an...

In this paper, an original approach, for the generation of locally coherent spatio-temporal graphs embeddding frequent inexact patterns, is presented. This approach is based on a work carried out previously, in which a configurable generator for spatio-temporal graphs has been implemented. These graphs contain spatial and spatio-temporal edges that...

In this chapter, we discuss two research areas related to qualitative reasoning: firstly, qualitative reasoning about dynamical systems, or qualitative physics, that aims at providing qualitative descriptions of processes in the sense that they are characterized regardless of quantitative data (for instance, “the tank overflows”, “temperature incre...

This chapter describes the basic principles of spatial reasoning processes based on algebras, independently of the imperfect dimension of spatial data. After putting forward some definitions, it also describes temporal and spatial models funded on algebras, especially RCC8 (Region Connection Calculus) for topological relations. The chapter presents...

Today pesticides, antimicrobials and other pest control products used in conventional agriculture are questioned and alternative solutions are searched out. Scientific literature and local knowledge describe a significant number of active plant-based products used as bio-pesticides. The Knomana (KNOwledge MANAgement on pesticide plants in Africa) p...

Methods for analysing sequential data generally produce a huge number of sequential patterns that have then to be evaluated and interpreted by domain experts. To diminish this number and thus the difficulty of the interpretation task, methods that directly extract a more compact representation of sequential patterns, namely closed partially-ordered...

Characterizing the spatial distribution of hedgerows over landscapes is important for understanding the effects of this distribution on the dynamics of plant and animal populations. Because hedgerows are planted or managed, the authors hypothesized that their distribution depends on the presence of other linear landscape elements, namely, roads and...

Characterizing the spatial distribution of hedgerows over landscapes is important for understanding the effects of this distribution on the dynamics of plant and animal populations. Because hedgerows are planted or managed, the authors hypothesized that their distribution depends on the presence of other linear landscape elements, namely, roads and...

Context Agroecosystems produce food and many other services that are crucial for human well-being. Given the scales at which the processes underlying these services take place, agricultural landscapes appear as appropriate spatial units for their evaluation and management. The design of sustainable agricultural landscapes that value these services...

Relational Concept Analysis (RCA) has been designed to classify sets of objects described by attributes and relations between these objects. This is achieved by iterating on Formal Concept Analysis (FCA). It can be used to discover knowledge patterns and implication rules in multi-relational datasets. The classification output by RCA is a family of...

A farmer's decision to plant new perennial biomass crops is a complex process that involves numerous parameters and can change the food / non-food balance. The paradigm of case-based reasoning is able to deal with the kind of complex and sparse information that is available in this situation, to model and forecast the allocation of these crops.

Nowadays, many heterogeneous relational data are stored in databases to be further explored for discovering meaningful patterns. Such databases exist in various domains and we focus here on river monitoring. In this paper, a limited number of river sites that make up a river network (seen as a directed graph) is given. Periodically, for each river...

This article describes a prototype of case-based reasoning, built for the agronomical domain. Its aim is to forecast the location of a new energy crop, the miscanthus. Interviews were conducted with farmers in order to know how they make their decisions. Nevertheless, few experiences were available for building this model, and we therefore introduc...

Cet article présente un prototype de raisonnement à partir de cas développé dans le cadre d'une application en agronomie, pour prévoir l'implantation dans les exploitations agricoles d'une nouvelle culture énergétique, le miscanthus. Des enquêtes ont été réalisées pour accéder au mode de décision des agriculteurs. Néanmoins, peu d'expériences étaie...

L’objet de ce colloque est de partager des connaissances, expériences et outils autour de la modélisation des paysages agricoles, de leur structure et de leur dynamique en considérant la modélisation de la structure physique du paysage agricole et celle des processus socio-techniques qui gouvernent les usages des éléments le constituant (parcelles,...

This paper presents a prototype of case-based reasoning, built for the agricultural domain. Its aim is to forecast the allocation of a new energy crop, the miscanthus. Interviews were conducted with french farmers in order to know how they make their decisions. Based on interview analysis, a case base and a rule base have been formalized, together...

Discovering sequential patterns in sequence databases is an important data mining task. Recently, hierarchies of closed partially-ordered patterns (cpo-patterns), built directly using Relational Concept Analysis (RCA), have been proposed to simplify the interpretation step by highlighting how cpo-patterns relate to each other. However, there are pr...

25th International Conference, ICCBR 2017, Trondheim, Norway, June 26-28, 2017, Proceedings

Chemical and biological assessments of waterbodies are required to fulfil the objectives of the European Water Framework Directive (EU Off J 327:1–72, 2000). Many past studies have been focused on water chemistry uncertainties, but few have been carried out on the hydrobiological aspects. Considerable research on macroinvertebrates has highlighted...

This paper presents a theoretical framework for exploring temporal data, using Relational Concept Analysis (RCA), in order to extract frequent sequential patterns that can be interpreted by domain experts. Our proposal is to transpose sequences within relational contexts, on which RCA can be applied. To help result analysis, we build closed partial...

Characterizing the spatial distribution of hedgerows over landscapes is important for understanding the effects of this distribution on the dynamics of plant and animal populations. Because hedgerows are planted or managed, the authors hypothesized that their distribution depends on the presence of other linear landscape elements, namely, roads and...

In this paper, we consider data analysis methods for knowledge extraction from large water data-sets. More specifically, we try to connect physico-chemical parameters and the characteristics of taxons living in sample sites. Among these data analysis methods, we consider formal concept analysis (FCA), which is a recognized tool for classification a...

Cet article décrit un système décisionnel développé pour permettre l'analyse des don-nées concernant le fonctionnement des hydro-écosystèmes ; ces données sont nombreuses, di-verses et issues de sources variées. Le système mis en place comporte une base de données intégrée, un entrepôt permettant l'exploration des dimensions associées aux données,...

In this paper, we develop a qualitative spatial reasoning (QSR) applied to the interpretation of urban satellite images. This reasoning is integrated within an ontology of urban objects, which has been implemented in cooperation with expert geographers. The spatial concepts mainly include the set of topological relations of the Region Connection Ca...

The European Water Framework Directive has required chemical and biological assessments in waterbodies. While studies of water chemistry uncertainties have existed for a long time, few studies have been carried out in hydrobiology. Our aim was to study the role of uncertainties defined as any action that may cause a data error on the French index “...

Economic development based on industrialization, intensive agriculture expansion and population growth places greater pressure on water resources through increased water abstraction and water quality degradation [40], River pollution is now a visible issue, with emblematic ecological disasters following industrial accidents such as the pollution of...

We are involved in the building by several actors of the class model of an information system in the environment domain. Actor concerns are various and sometimes conflicting, and progressively designing the model during working group sessions is required. This progressive improvement relies on the emergence of more abstract classes and associations...

This article describes a temporal data mining method based on relational lattices. This method is applied on a sequence dataset, dealing with physico-chemical and biological parameters sampled in watercourses. Our aim is to reveal frequent sub-sequences linking the two parameter types. We use a small example to show that relational concept analysis...

Nowadays, sequence databases are available in several domains with increasing sizes. Exploring such databases with new pattern mining approaches involving new data structures is thus important. This paper investigates this data mining challenge by presenting OrderSpan, an algorithm that is able to extract a set of closed partially ordered patterns...

More and more agricultural and environmental data are now available. These data are produced by numerous methods: Terrestrial sensors, remote sensing systems, simulation models, Internet of things, etc. Agricultural and environmental Information Systems (IS) and Decision Support Systems (DSS) are two complementary approaches to use these data – the...

This paper presents the application of Data Warehouse (DW) and On-Line Analytical Processing (OLAP) technologies to the field of water quality assessment. The European Water Framework Directive (DCE, 2000) underlined the necessity of having operational tools to help in the interpretation of the complex and abundant information regarding running wat...

We propose a new data mining process to extract original knowledge from hydro-ecological data, in order to help the identification of pollution sources. This approach is based (1) on a domain knowledge discretization (quality classes) of physico-chemical and biological parameters, and (2) on an extraction of temporal patterns used as discriminant f...

Atelier AnaEnv "ANAlyse de données ENVironnementales" associé à la conférence RFIA, Rouen, 1er juillet 2014

This paper aims at comparing transformation-based approaches built to deal with relational data, and in particular two approaches which have emerged in two different communities: Relational Concept Analysis (RCA), based on an iterative use of the classical Formal Concept Analysis (FCA) approach, and Propositionalisation coming from the Inductive Lo...

Belief revision is an operation that aims at modifying old beliefs so that they become consistent with new ones. The issue of belief revision has been studied in various formalisms, in particular, in qualitative algebras (QAs) in which the result is a disjunction of belief bases that is not necessarily representable in a QA. This motivates the stud...

Atelier SI et Environnement - Conférence Inforsid - 21 mai 2014

Currently, in Madagascar, GIS maps are being increasingly produced and used by non-governmental organizations, regarding conservation local contracts. These maps are used by policy makers to determine forest enclosures and to support local development. However, farmers are poorly involved in the map building process and have difficulty to link the...

Atelier FST "fouille de données spatiales et temporelles" associé à la conférence EGC, Rennes, 28 janvier 2014

The ANR 11 MONU 14 Fresqueau project is an interdisciplinary project involving computer scientists and hydroecologists. Its aim is to collect a large dataset about watercourses, in two large French watersheds; and then to explore it with data mining methods for answering scientific questions. The collected data are numerous and have various origins...

Le projet ANR 11 MONU 14 Fresqeau est un projet interdisciplinaire associant informaticiens et hydroécologues. Il a pour but de collecter un ensemble de données concernant l’état des cours d’eau, à l’échelle de deux grands bassins versants français, puis d’exploiter ces données avec des méthodes de fouille afin de répondre à des questionnements sci...

L'objectif de nos travaux est de comparer et fusionner les points de vue de paysans malgaches sur leur territoire. Notre demarche de modelisation utilise le modele des graphes conceptuels afin de representer les connaissances spatiales exprimees par les paysans, et l'analyse formelle de concepts pour organiser la fusion de ces representations. L'in...

Due to the complexity of the task, partially ordered pattern mining of sequential data has not been subject to much study, despite its usefulness. This paper investigates this data mining challenge by describing OrderSpan, a new algorithm that extracts such patterns from sequential databases and overcomes some of the drawbacks of existing methods....

Relational Concept Analysis (RCA) is a useful tool for classification and rule discovery on sets of objects with relations. Based on FCA, it produces more results than the latter but also an increase in complexity. Besides, in numerous applications of FCA, AOC-posets are used rather than lattices in order to reduce combinatorial problems. An AOC-po...

This paper proposes an approach for the adaptation of spatial or temporal cases in a case-based reasoning system. Qualitative algebras are used as spatial and temporal knowledge representation languages. The intuition behind this adaptation approach is to apply a substitution and then repair potential inconsistencies, thanks to belief revision on q...

The Region Connection Calculus (RCC), and particularly its RCC8 subset, have been extensively studied and used for qualitative spatial reasoning. Some sets of computational operations have also been defined for topological relations, as the CM8 set, that allows to compute the RCC8 relationships on raster images. In this paper, we propose a reified...

The European Water Framework Directive (2000) imposed chemical and biological assessments in streams. If studies of chemistry uncertainties exist for a long time, few similar studies are still recent in hydrobiology. Our aim is to study impacts of uncertainties - understood as any action that may cause a data error - on biotic metrics (diversity, a...

To better understand hydrosystem functioning, we need to improve our knowledge of hydrobiological processes as well to identify and to quantify the associated pressures. In this context, the ANR11-MONU14 Fresqueau project associates data miners and hydrobiologists to define a new knowledge discovery process from datasets provided by public database...

Comme toutes les sciences du vivant, les sciences agronomiques et plus largement agro-environnementales font face à des problèmes qui impliquent des données complexes, souvent volumineuses et hétérogènes, parfois incomplètes et imprécises. Ces problèmes intègrent une composante humaine prépondérante et dessinent ainsi un terrain propice à la mise e...

This paper introduces a method for the automatic acquisition of a rich case representation from free text for process-oriented case-based reasoning. Case engineering is among the most complicated and costly tasks in implementing a case-based reasoning system. This is especially so for process-oriented case-based reasoning, where more expressive cas...

Requirements and challenges Solutions Conclusion Bibliography

Origin and motivations Major functionalities, fields, and reusability

Le Virus de l'Immunodéficience Humaine (VIH) est actuellement un problème majeur de santé publique. Depuis l'identification du VIH, plus de 20 millions de personnes ont été identifiées. Le VIH continue de ravager les populations dans le monde entier avec 3 millions de nouvelles infections par an. Con-trairement au cancer, les approches de biologie...

Relational Concept Analysis (RCA) is an extension to the Formal Concept Analysis (FCA) which is an unsupervised classification method producing concept lattices. In addition RCA considers relations between objects from different contexts that allow for the creation of links between lattices. This feature makes it more intuitive to extract knowledge...

Due to the complexity of the task, partially ordered pattern mining of sequential data has not been subject to much study, despite its usefulness. This paper investigates this data mining challenge by describing OrderSpan, a new algorithm that extracts such patterns from sequential databases and overcomes some of the drawbacks of existing methods....

Georeferenced databases contain a huge volume of temporal and spatial data. They are notably used in environmental analysis. Several works address the problem of mining those data, but none are able to take into account the richness of the data and especially their spatial and temporal dimensions. In this paper, we focus on the extraction of a new...

Taaable is a case-based reasoning system that adapts cooking recipes to user constraints. Within it, the preparation part of recipes is formalised as a graph. This graph is a semantic representation of the sequence of instructions composing the cooking process and is used to compute the procedure adaptation, conjointly with the textual adaptation....