Julien Ah-Pine
Université Lyon, Informatique et Statistique, Faculty Member
- Data Mining, Information Retrieval, Graph Theory, Knot Theory, Machine Learning, Statistics, and 10 moreSocial Choice Theory, Data Analysis, Computational Statistics, Clustering Algorithms, Recommender Systems, Multicriteria Decision Analysis, Logistic Regression, K-means, Clustering Initialization and Robustness, and Regularization Parameter Tuningedit
Research Interests:
Research Interests:
ABSTRACT In some multi-criteria decision-making problems, it is more convenient to express the decision maker (DM) preferences in bipolar scales. In such cases, the bipolar Choquet integral with respect to bi-capacities was introduced as... more
ABSTRACT In some multi-criteria decision-making problems, it is more convenient to express the decision maker (DM) preferences in bipolar scales. In such cases, the bipolar Choquet integral with respect to bi-capacities was introduced as a versatile tool to model these kind of preferences. However, this aggregation function is useful in practice only if its parameters can be set up easily. To this end, elicitation techniques aim at finding the parameters values that best fit some given examples. In this paper, we address the problem of eliciting a bipolar Choquet integral with respect to a 2-additive bi-capacity. We present several techniques based on solving an optimization problem, taking into account the possible interaction, or not, with the DM. We deal with possible inconsistencies in the observed preferences and we also discuss the parsimonious character of the different models to favor simple models when several solutions exist.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract. Our main goal is to introduce three clustering functions based on the central tendency deviation principle. According to this ap-proach, we consider to cluster two objects together providing that their similarity is above a... more
Abstract. Our main goal is to introduce three clustering functions based on the central tendency deviation principle. According to this ap-proach, we consider to cluster two objects together providing that their similarity is above a threshold. However, how to set this threshold ? This paper ...
Research Interests:
In this paper, we address the problem of unsupervised rank aggregation in the context of meta-searching in infor-mation retrieval field. The first goal of this paper is to apply aggregation operators that are defined in information fusion... more
In this paper, we address the problem of unsupervised rank aggregation in the context of meta-searching in infor-mation retrieval field. The first goal of this paper is to apply aggregation operators that are defined in information fusion domain to the particular issue mentioned ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Association criteria used for measuring the relationship between categorical variables or partitions are mainly applied and studied using contingency tables. There is another way for representing categorical variables: the Relational... more
Association criteria used for measuring the relationship between categorical variables or partitions are mainly applied and studied using contingency tables. There is another way for representing categorical variables: the Relational Analysis representation which uses binary pairwise ...
Research Interests:
Abstract. This paper is concerned with the problem of unsupervised rank aggregation in the context of metasearch in information retrieval. In such tasks, we are given many partial ordered lists of retrieved items provided by many search... more
Abstract. This paper is concerned with the problem of unsupervised rank aggregation in the context of metasearch in information retrieval. In such tasks, we are given many partial ordered lists of retrieved items provided by many search engines and we want to define a way for ...
Research Interests:
Abstract. Measuring similarity between objects is a fundamental issue for numerous applications in data-mining and machine learning domains. In this paper, we are interested in kernels. We particularly focus on kernel normalization... more
Abstract. Measuring similarity between objects is a fundamental issue for numerous applications in data-mining and machine learning domains. In this paper, we are interested in kernels. We particularly focus on kernel normalization methods that aim at designing proximity ...
Research Interests:
Abstract. Information seeking in a multimedia database very often im-plies a search process that is complex, dynamic and multi-faceted. More-over the information need with respect to a topic is likely to evolve during the same search... more
Abstract. Information seeking in a multimedia database very often im-plies a search process that is complex, dynamic and multi-faceted. More-over the information need with respect to a topic is likely to evolve during the same search session, going from a simple lookup ...