Euranova has 3 fundamental pillars: explore, craft and serve. The explore pillar of Euranova is an independent research centre dedicated to data science, software engineering and AI.
Through the exploration of tomorrow’s engineering and data science to answer today’s problems, our research centre is dedicated to anticipating the challenges that European businesses face. We find solutions to current and future digital challenges with passion, creativity and integrity.
Euranova has 3 fundamental pillars: explore, craft and serve. The explore pillar of Euranova is an independent research centre dedicated to data science, software engineering and AI.
Through the exploration of tomorrow’s engineering and data science to answer today’s problems, our research centre is dedicated to anticipating the challenges that European businesses face. We find solutions to current and future digital challenges with passion, creativity and integrity.
Multimodal Classifier For Space Target Recognition
We propose a multi-modal framework to tackle the SPARK Challenge by classifying satellites using RGB and depth images. Our framework is mainly based on Auto-Encoders to embed the two modalities in a common latent space in order to exploit redundant and complementary information between the two types of data.
Advancing Innovation in Data Management
To build a data-driven economy across Europe and create a significant competitive advantage for European industry, companies will have to address the challenges in the data engineering and management domain. We are proud to partner with four top-class European institutions.
We Join The Stream Reasoning Workshop 2021
The research community at its best!
This week, our research director Sabri Skhiri flew to Milan with other leaders in stream reasoning. They meet to push further efficient decision-making and context detection over rapidly changing data.
AMI-Class: Towards a Fully Automated Multi-view Image Classifier
In this paper, we propose an automated framework for multi-view image classification tasks. The proposed framework is able to, all at once, train a model to find a common latent representation and perform data imputation, choose the best classifier and tune all necessary hyper-parameters.
Policy-based Automated Compliance Checking
Under the GDPR requirements and privacy-by-design guidelines, access control for personal data should not be limited to a simple role-based scenario. For the processing to be compliant, additional attributes, such as the purpose of processing or legal basis, should be verified against an established data processing agreement or policy.
Anomaly Detection: How to Artificially Increase your F1-Score with a Biased Evaluation Protocol
Anomaly detection is a widely explored domain in machine learning. Many models are proposed in the literature, and compared through different metrics measured on various datasets.
The most popular metrics used to compare performances are F1-score, AUC and AVPR.
DAEMA: Denoising Autoencoder with Mask Attention
Missing data is a recurrent and challenging problem, especially when using machine learning algorithms for real-world applications. For this reason, missing data imputation has become an active research area, in which recent deep learning approaches have achieved state-of-the-art results. We propose DAEMA: Denoising Autoencoder with Mask Attention.
Estimating Expected Calibration Errors
Uncertainty in probabilistic classifiers predictions is a key concern when models are used to support human decision making, in broader probabilistic pipelines or when sensitive automatic decisions have to be taken.
Studies have shown that most models are not intrinsically well calibrated, meaning that their decision scores are not consistent.
10 Papers in 2021
To answer today’s problems, our research centre is dedicated to anticipating the challenges that European businesses face. Find out the impacts of our latest published papers.
A Framework Using Contrastive Learning for Classification with Noisy Labels
We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies, such as pseudo-labelling, sample selection with Gaussian Mixture models, and weighted supervised contrastive learning have been combined into a fine-tuning phase following the pre-training.
AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT
This paper explains our participation in task 1of the CASE 2021 shared task. This task is about multilingual event extraction from the news. We focused on sub-task 4, event information extraction. This sub-task has a small training dataset, and we fine-tuned a multilingual BERT to solve this sub-task.
Our Research Director Invited as PC Member at IEEE Big Data
We are very proud of our research director Sabri Skhiri for joining the program committee of IEEE Big Data 2021!
He will be the only Belgian and one of the few Europeans to be on the program committee of this top tier research conference in Big Data.
Congratulation Sabri!