Éditeur(s) : Université des Antilles Études caribéennes
Résumé : Comme dans d’autres régions du monde, la croissance démographique et l’accentuation des activités côtières au Canada entraînent une dégradation continue des écosystèmes et de la biodiversité. L’aménagement côtier contribue essentiellement à la vulnérabilité et à la détérioration des littoraux. Ce constat concerne le littoral acadien du Nouveau-Brunswick. Au-delà de ces pressions démographiques et de l’urbanisation sur les zones littorales, l'élévation du niveau marin et l'augmentation des températures (effets du changement et des variations climatiques) provoquent des impacts vérifiables : l’intensité des ondes de tempêtes, la dégradation des sols par l’érosion, etc. Ainsi, l’adaptation au changement climatique constitue un enjeu de taille pour la province du Nouveau-Brunswick. C’est pourquoi cet article propose d’étudier les impacts de ces changements auprès de deux régions côtières du littoral acadien et d’apprendre des expériences de chacun pour renforcer leur résilience. La recherche souhaite s’inscrire dans une nouvelle forme d’engagement communautaire qui prend en compte des aspects de la « gouvernance », de l’« aménagement du territoire » et de la « cohésion sociale ». L’article tente d’avoir une meilleure compréhension de l’enchâssement des aspects économiques et sociétaux dans les enjeux environnementaux.
As in other parts of the world, demographic growth and an increased use of coastal zones in Canada lead to a degradation of coastal ecosystems and a loss of biodiversity. Coastal development contributes in large part to the vulnerability and deterioration of coastal zones. This is very clearly seen in the case of the Acadian coast of New Brunswick. In addition to stresses from demographic growth and urbanization, the coastal zone is affected by sea level rise, temperature increases and other impacts of climate change such as increased climate variability, which lead to measurable effects such as an increase in storm intensity or increased coastal erosion. Thus, adaptation to climate change constitutes a major challenge for the province of New Brunswick. It is in this context that we propose to analyze the impacts of climate change in two sites on the Acadian coast and to profit from both experiences in order to increase the resilience of the communities through mutual learning. The research undertaken here aims at contributing to a new form of community engagement that takes “governance”, “land use planning” and “social cohesion” into account. The article aims at a better understanding of the interplay of social and economic aspects in this environmental problem.
Canada
Nouveau-Brunswick

Droits : info:eu-repo/semantics/openAccess
urn:doi:10.4000/etudescaribeennes.6970
http://journals.openedition.org/etudescaribeennes/6970

Éditeur(s) : HAL CCSD
Résumé : International audience
In this paper we propose a hybrid approach using mutual information and multi-objective optimization for feature subset selection problem. The hybrid aspect is due to the sequence of a filter method and a wrapper method in order to take advantages of both. The filter method reduces the exploration space by keeping subsets having good internal properties and the wrapper method chooses among the remaining subsets with a classification performances criterion. In the filter step, the subsets are evaluated in a multi-objective way to ensure diversity within the subsets. The evaluation is based on the mutual information to estimate the dependency between features and classes and the redundancy between features within the same subset. We kept the non-dominated (Pareto optimal) subsets for the second step. In the wrapper step, the selection is made according to the stability of the subsets regarding classification performances during learning stage on a set of classifiers to avoid the specialization of the selected subsets for a given classifiers. The proposed hybrid approach is experimented on a variety of reference data sets and compared to the classical feature selection methods FSDD and mRMR. The resulting algorithm outperforms these algorithms and the computation complexity remains acceptable even if it increases with regards to these two fast selection methods.
Journal of Informatics and Mathematical Sciences

hal-01375982
https://hal.archives-ouvertes.fr/hal-01375982