machine learning

Bahn-Vorhersage - The best Train Delay Prediction System.

Extract video representations (semantic, geometric, deep features) for the frames of any video.

A landcover classification tool based for humans. Classifier does "traditional" supervised and unsupervised learning. Image segmentation and soon also object detection

Resources for interns and new team members at Tangible AI

Pulmo is a web-based application that provides an easy-to-use interface for users to input their medical history and other relevant data to get a prediction of their risk of developing lung cancer. The project has also highlighted the importance of data preprocessing and feature selection in improving the performance of machine learning algorithms. Exploratory data analysis was also useful in identifying the most relevant features for predicting lung cancer.

Python software for identifying dynamical systems and hidden patterns from time series data

Series of simulations to replicate laboratory experiments as part of a 'digital twin' initiative between Swansea University and the UK Atomic Energy Authority. Scripts are mostly in python to run the various modules which this platform integrates together (e.g., Salome, Code_Aster, ERMES, CAD2Vox, gvxr, CIL).

63-51 : Emerging Technologies / Benoit, Nohen, Thaddée

Convenient training of linear models

El proyecto se orienta hacia el desarrollo de una herramienta predictiva para el ajedrez, empleando modelos de red neuronal recurrente (RNN) implementados en TensorFlow. La recopilación de datos se realizó mediante técnicas de web scraping desde la página https://www.chess-poster.com.

Simulation of a real hospital scenario with a ML model in production

This repository showcases an end-to-end machine learning project implemented with a focus on MLOps.

This repository holds code for the AskAnna Backend. Our backend stack primarily uses Django and the Django REST Framework.

Eumap is a library to enable easier access to several spatial layers prepared for Continental Europe, as well the source code used to produce them (http://eumap.readthedocs.org).

Code for Graph Representation of 3D CAD models for Machining Feature Recognition with Deep Learning paper. This is an approach using graph neural networks to learning from planar B-Rep CAD models.

Docker build of postgresql changing the dimension limit for the cube extension, raising it to 350

Nous avons entrepris un projet d'apprentissage automatique pour prédire des maladies en analysant les données symptomatiques et médicales. Notre modèle sophistiqué, basé sur des techniques d'apprentissage automatique avancées, évalue les symptômes pour fournir des prédictions précises. Avec une interface API développée avec Django et un déploiement sur Microsoft Azure via Terraform, notre solution est conviviale et évolutive.Découvrez notre projet ici :https://apipharma-app-service.azurewebsites.net/

Détection de tweets haineux par apprentissage automatique (NLP)) Nous avons developpé un modèle d'apprentissage automatique pour détecter efficacement les tweets contenant des contenus haineux/offensants, dans le but de lutter contre les comportements nuisibles en ligne. En parallèle, nous avons conçu une interface API avec Django et optimisé le déploiement en utilisant Docker et Azure via Terraform, assurant ainsi une mise en œuvre fluide et évolutive de notre solution: https://apitweet-app-service.azurewebsites.net/