Application of LSTM architectures for next frame forecasting in Sentinel-1 images time series

L'analyse pr{\'e}dictive permet d'estimer les tendances des {\'e}v{\`e}nements futurs. De nos jours, les algorithmes Deep Learning permettent de faire de bonnes pr{\'e}dictions. Cependant, pour chaque type de probl{\`e}me donn{\'e}, il est n{\'e}cessaire de choisir l'architecture optimale. Dans cet article, les mod{\`e}les Stack-LSTM, CNN-LSTM et ConvLSTM sont appliqu{\'e}s {\`a} une s{\'e}rie temporelle d'images radar sentinel-1, le but {\'e}tant de pr{\'e}dire la prochaine occurrence dans une s{\'e}quence. Les r{\'e}sultats exp{\'e}rimentaux {\'e}valu{\'e}s {\`a} l'aide des indicateurs de performance tels que le RMSE et le MAE, le temps de traitement et l'index de similarit{\'e} SSIM, montrent que chacune des trois architectures peut produire de bons r{\'e}sultats en fonction des param{\`e}tres utilis{\'e}s.

Ontologies-based Architecture for Sociocultural Knowledge Co-Construction Systems

Considering the evolution of the semantic wiki engine based platforms, two main approaches could be distinguished: Ontologies for Wikis (OfW) and Wikis for Ontologies (WfO). OfW vision requires existing ontologies to be imported. Most of them use the RDF-based (Resource Description Framework) systems in conjunction with the standard SQL (Structured Query Language) database to manage and query semantic data. But, relational database is not an ideal type of storage for semantic data. A more natural data model for SMW (Semantic MediaWiki) is RDF, a data format that organizes information in graphs rather than in fixed database tables. This paper presents an ontology based architecture, which aims to implement this idea. The architecture mainly includes three layered functional architectures: Web User Interface Layer, Semantic Layer and Persistence Layer.