A
Arlindo L. Oliveira
Researcher at University of Lisbon
Publications - 167
Citations - 7790
Arlindo L. Oliveira is an academic researcher from University of Lisbon. The author has contributed to research in topics: Compressed suffix array & Sequential logic. The author has an hindex of 34, co-authored 154 publications receiving 6991 citations. Previous affiliations of Arlindo L. Oliveira include Technical University of Lisbon & University of California, Berkeley.
Papers
More filters
Towards Automatic Learning of a Structure Ontology For Technical Articles
TL;DR: A method that combines an hand-crafted ontology with a robust inductive inference method to assign semantic labels to pieces of technical articles available on the Web, together with a query language developed for the purpose, supports queries that cannot be resolved using currently available tools.
Proceedings ArticleDOI
Haplotype Inference with Boolean Constraint Solving: An Overview
TL;DR: This paper provides an overview of SAT-based approaches for solving the HIPP problem and identifies current research directions.
Proceedings ArticleDOI
Probabilistic Testability Analysis and DFT Methods at RTL
TL;DR: This work presents probabilistic methods for testability analysis at RTL and their use to guide DFT techniques like partial-scan and TPI and an approach that takes into account correlations within pre-defined groups formed based on an originally proposed heuristic.
Journal ArticleDOI
Development of deep learning segmentation models for coronary X-ray angiography: Quality assessment by a new global segmentation score and comparison with human performance.
Miguel Nobre Menezes,João Lourenço-Silva,B Silva,Oliveira Rodrigues,Ana Rita G. Francisco,Pedro Carrilho Ferreira,Arlindo L. Oliveira,Fausto J. Pinto +7 more
TL;DR: In this article , the authors proposed a method for automatic artificial intelligence (AI) coronary angiography (CAG) segmentation using similarity scores and a set of criteria defined by expert physicians.
Posted Content
Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation.
João Lourenço Silva,Miguel Nobre Menezes,Tiago Rodrigues,Beatriz Silva,Fausto J. Pinto,Arlindo L. Oliveira +5 more
TL;DR: Based on the EfficientNet and the UNet++ architectures, this article proposed a line of efficient and high-performance segmentation models using a new decoder architecture, whose best-performing version achieved average dice scores of 0.8904 and 0.7526 for the artery and catheter classes, respectively, and an average generalized dice score of0.9234.