A
Antoine J.-P. Tixier
Researcher at École Polytechnique
Publications - 40
Citations - 1281
Antoine J.-P. Tixier is an academic researcher from École Polytechnique. The author has contributed to research in topics: Automatic summarization & Convolutional neural network. The author has an hindex of 15, co-authored 39 publications receiving 828 citations. Previous affiliations of Antoine J.-P. Tixier include University of Colorado Boulder.
Papers
More filters
Journal ArticleDOI
Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports
TL;DR: The proposition that manual content analysis of injury reports can be eliminated using natural language processing (NLP) is tested and the results indicate that the NLP system is capable of quickly and automatically scanning unstructured injury reports for 101 attributes and outcomes with over 95% accuracy.
Journal ArticleDOI
Application of machine learning to construction injury prediction
TL;DR: Two state-of-the-art ML models, Random Forest and Stochastic Gradient Tree Boosting, were applied to a data set of carefully featured attributes and categorical safety outcomes, extracted from a large pool of textual construction injury reports via a highly accurate Natural Language Processing tool developed by past research.
Journal ArticleDOI
Psychological Antecedents of Risk-Taking Behavior in Construction
TL;DR: In this article, a controlled experiment was designed and conducted that induced various positive and negative emotions in 69 subjects using validated movie excerpts; measured emotional states using a validated post-film questionnaire; and exposed participants to construction hazards within a high fidelity virtual environment; and measured subjects' perceptions of the risk related to...
Journal ArticleDOI
Construction Safety Clash Detection: Identifying Safety Incompatibilities among Fundamental Attributes using Data Mining
TL;DR: A newly introduced conceptual framework and accompanying natural language processing system is used to extract standard information in the form of fundamental attributes from a set of raw accident reports, then applied state-of-the-art data mining techniques to discover attribute combinations that contribute to injuries.
Proceedings ArticleDOI
A Graph Degeneracy-based Approach to Keyword Extraction
TL;DR: It is hypothesized that keywords are more likely to be found among influential nodes of a graph-ofwords rather than among its nodes high on eigenvector-related centrality measures, and unsupervised techniques that capitalize on graph degeneracy are introduced to test this hypothesis.