Search Results for author: Carlotta Orsenigo

Found 3 papers, 1 papers with code

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery

no code implementations9 Feb 2022 Masoud Jalayer, Amin Kaboli, Carlotta Orsenigo, Carlo Vercellis

In many real applications of fault detection and diagnosis, data tend to be imbalanced, meaning that the number of samples for some fault classes is much less than the normal data samples.

Data Augmentation Fault Detection

Automatic Visual Inspection of Rare Defects: A Framework based on GP-WGAN and Enhanced Faster R-CNN

no code implementations2 May 2021 Masoud Jalayer, Reza Jalayer, Amin Kaboli, Carlotta Orsenigo, Carlo Vercellis

The proposed augmentation algorithm extracts objects from the real samples and blends them randomly, to generate new samples and enhance the performance of the image processor.

object-detection Object Detection

ELECTRAMed: a new pre-trained language representation model for biomedical NLP

1 code implementation19 Apr 2021 Giacomo Miolo, Giulio Mantoan, Carlotta Orsenigo

The overwhelming amount of biomedical scientific texts calls for the development of effective language models able to tackle a wide range of biomedical natural language processing (NLP) tasks.

Ranked #4 on Drug–drug Interaction Extraction on DDI extraction 2013 corpus (Micro F1 metric, using extra training data)

Drug–drug Interaction Extraction Language Modelling +4

Cannot find the paper you are looking for? You can Submit a new open access paper.