This project focuses on enhancing agricultural resilience to climate change by incorporating neural network-based optimization into weather index insurance designs. By utilizing advanced machine learning techniques, the initiative aims to improve the accuracy and appeal of insurance products for the agricultural sector, which is highly vulnerable to climate-induced weather unpredictability. The collaboration involves academia and […]

The project involves the development of a machine learning model which can predict targeted properties of materials from their band structure. Computational modeling methods, such as ab initio (quantum chemistry) calculations, Density Functional Theory and Molecular Dynamics, enable us to calculate properties of materials from their crystalline structure. The band structure is a representation of […]

This project aims to benefit society by improving accessibility for viewers who may not be able to receive sound information well from the media content, including DHH viewers. To develop and research for the project, it is necessary to reflect an in-depth and multi-faceted case analysis on the topic of improving sound accessibility. To fulfil […]

Our goal is to uncover patterns and structures hidden in complex biological data measured at the single-cell resolution. We propose to incorporate multiscale information, comprising both local and global information, to describe the shape of datasets as a whole. Current work typically only focuses on local structures, like groups of similar cells and transitions between […]

This project is dedicated to unveiling how proteins within cell membranes adapt to their surroundings, particularly the lipid environment. Employing computer simulations and machine learning (ML), we focus on RAS signaling proteins and Mga2 transcription factors. RAS proteins, crucial for cell growth and division, are anchored to the cellular membrane and often exhibit mutations in […]

Most computers and materials work on scales such that quantum effects can be comfortably ignored. But as we aim to make computers ever smaller, quantum effects will cause difficulties; however, they also provide opportunities. Spin-crossover (SCO) materials are molecules that can “Flip” between two states: either high or low spin binary states, making them essentially […]

This project aims to simulate the melting of clusters that are important in the field of nanotechnology and catalysis. We will improve the computational efficiency of Parallel Tempering Monte Carlo (PTMC) simulations by integrating GPU capabilities and interfacing with Gaussian software for energy calculations. The project is an essential part of a Ph.D. thesis that […]

THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW

Au cours des dernières années, la recherche en reconnaissance gestuelle a connu une forte effervescence, principalement appuyée sur la démocratisation de l’intelligence artificielle. Cependant, les approches actuelles rencontrent souvent des défis en termes de robustesse et demandent un grand effort de calibration. Pour remédier à ces limitations, ce projet propose d’employer la fusion de signaux […]

Our project emphasizes the integration of advanced artificial intelligence techniques with traditional diagnostic methods, fostering a synergy that enhances the accuracy and efficiency of cardiac health assessments. By leveraging the power of Artificial intelligence, specifically through the utilization of a Convolutional Neural Network (CNN), we can discern subtle patterns and nuances in ECG data that […]

La physique des particules se concentre sur l’étude des éléments fondamentaux constitutifs de la matière et des forces qui régissent leurs interactions. Les recherches dans ce domaine sont menées à l’aide d’accélérateurs de particules. De plus, le Modèle Standard de la physique des particules est le cadre théorique principal décrivant les interactions entre ces particules […]

The central idea of this project is the observation that publications using systematic time series feature extraction from the Open Source machine learning library tsfresh, always need to visualize and explain the extracted features. Due to the fact that tsfresh uses 168 algorithms to compute up to 800 time series features, this process can be […]