1

Addressing Common Inconsistencies in Sewer Networks Data

In sewer networks, adding a new element involves multiple phases, including planning, installation, and ongoing maintenance. At each stage of the element's lifecycle—whether it is a pipe, a structure, or an apparatus—different stakeholders and …

Propagation-Based Domain-Transferable Gradual Sentiment Analysis

We propose a novel refinement of a gradual polarity propagation method to learn the polarities of concepts and their uncertainties with respect to various domains from a labeled corpus. Our contribution consists of introducing a positive correction …

From Standards to an Ontology-Based Data Access System for Sewer Networks

As cities worldwide experience rapid growth, the demand for a robust infrastructure to support the evolving needs of urban residents becomes increasingly important. Managing urban water networks requires accurate and standardized data which is …

A Machine Learning Approach to Predict Weaning Outcome among Ventilated Patients in Intensive Care Unit

Rationale: Machine learning has been illustrated in various medical fields, such as fluid management in sepsis, prediction of renal failure and others. The weaning period is the key to the management of a patient on mechanical ventilation. Weaning …

Extending a Fuzzy Polarity Propagation Method for Multi-Domain Sentiment Analysis with Word Embedding and POS Tagging

Within multi-domain sentiment analysis, we study how different domain-dependent polarities can be learned for the same concepts. To this aim, we extend an existing approach based on the propagation of fuzzy polarities over a semantic graph capturing …

Population-Based Meta-Heuristic for Active Modules Identification

The identification of condition specific gene sets from transcrip- tomic experiments has important biological applications, ranging from the discovery of altered pathways between different phe- notypes to the selection of disease-related biomarkers. …

Improving Pattern Discovery Relevancy by Deriving Constraints from Expert Models

To support knowledge discovery from data, many pattern mining techniques have been proposed. One of the bottlenecks for their dissemination is the number of computed patterns that appear to be either trivial or uninteresting with respect to available …

Les modèles des experts au service de l’extraction de motifs pertinents

Pour assister la découverte de connaissances à partir de données, de nombreuses techniques de calcul de motifs ont été proposées. L’un des verrous à leurs disséminations est que nombre des motifs extraits apparaissent triviaux et/ou inintéressants au …

Extraction de motifs dans des graphes orientés attribués en présence d’automorphisme

Les graphes orientés attribués sont des graphes orientés dans lesquels les nœuds sont associés à un ensemble d’attributs. De nombreuses données, is- sues du monde réel, peuvent être représentées par ce type de structure, mais encore peu d’algorithmes …

Weighted Path as a Condensed Pattern in a Single Attributed DAG

Directed acyclic graphs can be used across many application domains. In this paper, we study a new pattern domain for supporting their analy- sis. Therefore, we propose the pattern language of weighted paths, primitive constraints that enable to …