I
Ioana Barbantan
Researcher at Technical University of Cluj-Napoca
Publications - 12
Citations - 55
Ioana Barbantan is an academic researcher from Technical University of Cluj-Napoca. The author has contributed to research in topics: Knowledge extraction & Identification (information). The author has an hindex of 5, co-authored 12 publications receiving 52 citations.
Papers
More filters
Proceedings ArticleDOI
An offline system for handwritten signature recognition
TL;DR: A new offline signature verification system is presented, which considers a new combination of previously used features and introduces two new distance-based ones and a new feature grouping.
Journal ArticleDOI
Feature Engineered Relation Extraction – Medical Documents Setting
TL;DR: This paper aims to define the knowledge flow for a medical assistive decision support system by structuring raw medical data and leveraging the knowledge contained in the data proposing solutions for efficient data search, medical investigation or diagnosis and medication prediction and relationship identification.
Proceedings ArticleDOI
REMed: automatic relation extraction from medical documents
TL;DR: It is determined that the performance of the REMed solution is comparable with similar solutions, and outperforms the best solution reported in the similar systems with 1.2%.
Proceedings ArticleDOI
Exploiting word meaning for negation identification in electronic health records
Ioana Barbantan,Rodica Potolea +1 more
TL;DR: This work is an attempt of automated negation identification in unstructured health records, and proposes the PreNex algorithm that consists in breaking down the terms into prefix and root word and the analysis of the root's validity using additional available resources (WordNet).
Proceedings ArticleDOI
Enhancements on a signature recognition problem
Ioana Barbantan,Rodica Potolea +1 more
TL;DR: An enhanced method of partitioning a dataset into clusters when dealing with the handwritten signature recognition problem and applied the feature selection method on each of the clusters with the previously determined classifiers to improve the recognition rate and reduce the time required to build a model.