Vignette d'image

Stoffel, Kilian

Nom
Stoffel, Kilian
Affiliation principale
Fonction
Professeur.e ordinaire
Email
Kilian.STOFFEL@unine.ch
Identifiants
https://libra.unine.ch/handle/123456789/593
_
0000-0002-9486-7769

Résultat de la recherche

Filtres

24
177
Réinitialiser les filtres

Paramètres

Voici les éléments 1 - 10 sur 24
  • Publication
    Accès libre
    Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach
    (2024-08)
    Claret, Romain 
    ;
    Michael O'Neill
    ;
    Cotofrei, Paul 
    ;
    Stoffel, Kilian 
    Neuroevolution of Augmenting Topologies (NEAT) and its advanced version, Evolvable-Substrate HyperNEAT (ES-HyperNEAT), have shown great potential in developing neural networks. However, their effectiveness heavily depends on the selection of hyperparameters. This study investigates the optimization of ES-HyperNEAT hyperparameters using the Tree-structured Parzen Estimator (TPE) on the MNIST classification task, exploring a search space of over 3 billion potential combinations. TPE effectively navigates this vast space, significantly outperforming random search in terms of mean, median, and best accuracy. During the validation process, the best hyperparameter configuration found by TPE achieves an accuracy of 29.00% on MNIST, surpassing previous studies while using a smaller population size and fewer generations. The transferability of the optimized hyperparameters is explored in logic operations and Fashion-MNIST tasks, revealing successful transfer to the more complex Fashion-MNIST problem but limited to simpler logic operations. This study emphasizes a method to unlock the full potential of neuroevolutionary algorithms and provides insights into the hyperparameters’ transferability across tasks of varying complexity.
  • Publication
    Accès libre
    Swiss health metadata repository : implementation recommendations - requirements, recommended architecture and prototype implementation
    (Université de Neuchâtel Institut du management de l'information, 2021-6-1)
    Cotofrei, Paul 
    ;
    De Santo, Alessio 
    ;
    Maalouf, Eliane 
    ;
    Stoffel, Kilian 
    In the context of a decentralized approach for health data resources, a central metadata repository becomes essential for the identification/description of the necessary resources. A Swiss Health Metadata Repository is expected to enable multiple advantages, namely: to provide a single entry point for searching/retrieving health-related resources; to help identify possible semantic linking between data sources; to provide a consistent data catalog ensured by the use of standardized vocabularies/ontologies; to enable potential exchange of experience and know-how between health data-related projects in Switzerland; and to increase the capacity of research groups to share/access/analyse health related data. This policy brief focuses on the implementation aspects of a proof-of-concept proto-type for Swiss Health Metadata Repository.
  • Publication
    Accès libre
    Design principles of a central metadata repository as a key element of an integrated health information system
    (Université de Neuchâtel Institut du management de l'information, 2020-1-31)
    Cotofrei, Paul 
    ;
    Maalouf, Eliane 
    ;
    De Santo, Alessio 
    ;
    Stoffel, Kilian 
    The Swiss Health System is a complex system with different groups of actors for which data is collected and analyzed using various methods, leading to a large heterogeneity and dispersion of available data. The specificities of a Swiss Health System favor a hybrid infrastructure to manage the heterogeneity and dispersion of Swiss health-related data. This policy brief shows the importance of a metadata management infrastructure to identify and describe health data resources and highlights several essential key elements for the design of a metadata repository and also raises important practical questions.
  • Publication
    Accès libre
    The CriLiM Methodology: Crime Linkage with a Fuzzy MCDM Approach
    (: IEEE, 2013-8-12)
    Albertetti, Fabrizio 
    ;
    Cotofrei, Paul 
    ;
    Grossrieder, Lionel
    ;
    Ribaux, Olivier
    ;
    Stoffel, Kilian 
    Grouping events having similarities has always been interesting for analysts. Actually, when a label is put on top of a set of events to denote they share common properties, the automation and the capability to conduct reasoning with this set drastically increase. This is particularly true when considering criminal events for crime analysts; conjunction, interpretation and explanation can be key success factors to apprehend criminals. In this paper, we present the CriLiM methodology for investigating both serious and high-volume crime. Our artifact consists in implementing a tailored computerized crime linkage system, based on a fuzzy MCDM approach in order to combine spatio-temporal, behavioral, and forensic information. As a proof of concept, series in burglaries are examined from real data and compared to expert results.
  • Publication
    Accès libre
    Crime Linkage: a Fuzzy MCDM Approach
    (: IEEE, 2013-6-4)
    Albertetti, Fabrizio 
    ;
    Cotofrei, Paul 
    ;
    Grossrieder, Lionel
    ;
    Ribaux, Olivier
    ;
    Stoffel, Kilian 
    Grouping crimes having similarities has always been interesting for analysts. Actually, when a set of crimes share common properties, the capability to conduct reasoning and the automation with this set drastically increase. Conjunction, interpretation and explanation based on similarities can be key success factors to apprehend criminals. In this paper, we present a computerized method for high-volume crime linkage, based on a fuzzy MCDM approach in order to combine situational, behavioral, and forensic information. Experiments are conducted with series in burglaries from real data and compared to expert results.
  • Publication
    Métadonnées seulement
    Fuzzy Extended BPMN for Modelling Crime Analysis Processes
    (2011-5)
    Cotofrei, Paul 
    ;
    Stoffel, Kilian 
    In the frame of an overall project concerning the development of an intelligent process-driven framework for crime analysis, the modelling phase of crime analysis processes requires formal approaches being able to capture both the vague nature of forensic data and the uncertainties and conjectures characterizing the inference structures of this domain. In this context, a first analysis on the feasibility of a fuzzy embedded BPMN using the extensibility mechanism introduced by BPMN 2.0 specification is considered.