Agnès Braud

A Platform for Spatial Data Labeling in an Urban Context

This chapter presents a platform for classifying urban areas, improved by a machine learning framework able to ease this classification. We propose thanks to this platform an iterative procedure for geographic experts that have to define classes or “labels” and then classify in a semi-automated way. This work is part of the GeOpenSim project and has been developed within the Geoxygene framework.

Identifying Ecological Traits: A Concrete FCA-Based Approach

This paper describes a method to identify so-called ecological traits of species based on the analysis of their biological characteristics. This biological dataset has a complex structure that can be formalized as a fuzzy many-valued context and transformed into a binary context through histogram scaling . The core of the method relied on the construction and interpretation of formal concepts and was used on a 50 species × 124 histogram attributes table. The concepts were analyzed with the help of an hydrobiologist, leading to a set of ecological traits which were inserted in the original context for validation.

Mining closed partially ordered patterns, a new optimized algorithm

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 from a sequence database. It combines well-known properties of prefixes and suffixes. Furthermore, we extend OrderSpan by adapting efficient optimizations used in sequential pattern mining domain. Indeed, the proposed method is flexible and follows the sequential pattern paradigm. It is more efficient in the search space exploration, as it skips redundant branches. Experiments were performed on different real datasets to show (1) the effectiveness of the optimized approach and (2) the benefit of closed partially ordered patterns with respect to closed sequential patterns.

Flexible propositionalization of continuous attributes in relational data mining

Our approach can handle thresholds on attributes and on the number of objects.Tackling numeric attributes with both absolute and relative numbers efficiently.Selecting the optimal combination of propositionalizer and classifier effectively.The proposed approach is flexible to be applied over different contexts.Experiments show the effectiveness and efficiency of the proposed approach. In a relational database, data are stored in primary and secondary tables. Propositionalization can transform a relational database into a single attribute-value table, and hence becomes a useful technique for mining relational databases. However, most of the existing propositionalization approaches deal with categorical attributes, and cannot handle a threshold on an attribute and a threshold on the number of objects satisfying the condition on the attribute at the same time. In this paper, we propose a new propositionalization technique called Cardinalization to solve these problems. In order to handle relative numbers, we propose a second variant of our approach called Quantiles which can discretize the cardinality of Cardinalization and achieve a fixed number of features. Therefore, the Quantiles method can be tuned to different deployment contexts. Additionally, we often observe that the best combination of propositionalization and classification methods depends on the new context (e.g., online/incremental learning). One effective solution could be to predict the optimal combination at training time and use it in different deployment contexts. Here we also propose an effective wrapping algorithm, called WPC (Wrapper to combine Propositionalizer and Classifier) to select the best combination of propositionalization and classification methods to address this task. Extensive performance analyses in synthetic and real-life datasets show that our approach is very effective and efficient in relational data mining.

Conception of a GIS-Platform to simulate urban densification based on the analysis of topographic data

The aim of our research is to analyze the evolution of urbanization and to simulate it on specific areas. We focus on the evolution between 1950 and now. We analyse the densification by means of comparing temporal topographic data bases created from existing topographic data base and maps and photo from 1950. In this paper we present how a simulation works - which input data are used, which functions are used to densify the space and how the simulation works, is tuned and run - the densification method for each urban block illustrated with results, the method used during the project to build the required knowledge for simulation and we conclude and present the main research perspectives. The methods are implemented on a dedicated open source software named GeOpenSim.

OrderSpan: Mining Closed Partially Ordered Patterns

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. Our work consists in providing a simple and flexible framework to directly mine complex sequences of itemsets, by combining well-known properties on prefixes and suffixes. Experiments were performed on different real datasets to show the benefit of partially ordered patterns.

Neuronal clustering of brain fMRI images

Functional Magnetic Resonance Imaging (fMRI) allows the neuroscientists to observe the human brain in vivo. The current approach consists in statistically validating their hypotheses. Data mining techniques provide an opportunity to help them in making up their hypotheses. This paper shows how a neuronal clustering technique can highlight active areas thanks to an appropriate distance between fMRI image sequences. This approach has been integrated into an interactive environment for knowledge discovery in brain fMRI. Its results on a typical dataset validate the approach and open further developments in this direction.

A Genetic Algorithm for Propositionalization

Nowadays, propositionalization is an important method that aims at reducing the complexity of Inductive Logic Programming, by transforming a learning problem expressed in a first order formalism into an attribute-value representation. This implies a two steps process, namely finding an interesting pattern and then learning relevant constraints for this pattern. This paper describes a novel genetic approach for handling the second task. The main idea of our approach is to consider the set of variables appearing in the pattern, and to learn a partition of this set. Numeric constraints are directly put on the equivalence classes involved by the partition rather than on variables. We have proposed an encoding for representing a partition by an individual, and general set-based operators to alter one partition or to mix two ones. For propositionalization, operators are extended to change not only the partition but also the associated numeric constraints.

Propositionalisation of Continuous Attributes beyond Simple Aggregation

Existing propositionalisation approaches mainly deal with categorical attributes. Few approaches deal with continuous attributes. A first solution is then to discretise numeric attributes to transform them into categorical ones. Alternative approaches dealing with numeric attributes consist in aggregating them with simple functions such as average, minimum, maximum, etc. We propose an approach dual to discretisation that reverses the processing of objects and thresholds, and whose discretisation corresponds to quantiles. Our approach is evaluated thoroughly on artificial data to characterize its behaviour with respect to two attribute-value learners, and on real datasets.

Extracting Hierarchies of Closed Partially-Ordered Patterns Using Relational Concept Analysis

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 partially-ordered patterns (cpo-patterns), that are synthetic and easy to read for experts. Each cpo-pattern is associated to a concept extent which is a set of temporal objects. Moreover, RCA allows to build hierarchies of cpo-patterns with two generalisation levels, regarding the structure of cpo-patterns and the items. The benefits of our approach are discussed with respect to pattern structures.