Generalization in Deep Learning

In recent years, deep learning has led to unprecedented advances in a wide range of applications including natural language processing, reinforcement learning, and speech recognition. Despite the abundance of empirical evidence highlighting the success of neural networks, the theoretical properties of deep learning remain poorly understood and have been a subject of active investigation. One […]

Read More
Intégration de contraintes industrielles dans la recommandation de produits

Les systèmes de recommandation sont des outils qui permettent aux utilisateurs d’un système de trouver des items qui pourraient leur être d’intérêt. Ces outils permettent d’améliorer les performances marketing à travers l’amélioration de l’expérience client, et cela en limitant le temps de recherche liés à la surcharge d’information à travers une meilleure personnalisation. Les systèmes […]

Read More
Stage en robotique à l’université national de Colombie à Medellin

Le projet consiste à développer un robot fermier pour un système aéroponique. Le système devra être complètement autonome. Ainsi, il possédera différents capteurs qui devront être intégrés: caméra, capteur d’acidité, capteur de conductivité électrique dans l’eau, capteur d’humidité, etc. Grâce à ces informations, le robot devra se déplacer et effectuer différentes tâches: semence, transplantation, récolte, […]

Read More
Remote and local effect of vertical warming structure in the polar region

Recently, the near-surface temperature in the Arctic region has been increasing at a faster rate than the global average. Also, many studies show the distinct vertical profile of Arctic warming is determined by various driving mechanisms. Here, we will show how polar warming of different vertical structure affects the climate responses locally as well as […]

Read More
Acceptance Testing Framework for Robotic Software Solutions

Modern robots depend on numerous hardware devices and human interaction in order to perform their task. These dependencies, in addition to the distributed nature of these systems, make automated full-system testing difficult. Current testing practices are insufficient as they only test a single component of the system or require costly manual labor. Many companies have […]

Read More
Utilizing Virtual Reality as a Tool for Research on Environmental Behavior Study

My main field of interest is environmental behavior, which deals with interrelations between physical environments and human behaviors regarding urban- and architectural safety planning. I am currently planning to conduct an experimental research on public safety issues (fire/escape, terror/crimes) in urban- and architectural environments utilizing Virtual Reality technologies, and although I have recently acquired fundamental […]

Read More
Reversible assembly state of plasmonic nanoparticles driven by controlling liquid crystalline defect under multi-stimuli system

The main research theme of the project is to achieve reconfigurable assembly state of plasmonic NPs by controlling its trapping agent, LCs, under multi-stimuli system. There are two kinds of multi-stimuli LC control platform; one is static system in which anchoring, rubbing, and confinement can be modified, while the other is dynamic system which is […]

Read More
Mobile Beacon-based Localization with Motion Compensation for Underwater Acoustic Sensor Networks

The aim of this project is to propose an improved mobile-based localization scheme by considering a practical factor (i.e., ship-motion) in Underwater Acoustic Sensor Networks (UASNs). In the last decade, localization techniques associated with UASNs have been widely studied as a method to provide fundamental support for many location-based applications. In particular, mobile beacon-based localization […]

Read More
Deep learning-based steel corrosion and fatigue crack detection using a depth camera

In order to overcome the drawbacks of the traditional approaches to steel structure damage detection and to improve reliability and safety of existing steel structures, this research proposes to develop an innovative autonomous SHM system that offers transformative enhancements over existing steel structure monitoring systems. This will involve: 1. Collecting Collecting image data from various […]

Read More
Transitioning from Print to Interactive Digital Publishing

PUBLIC is an innovative print periodical with a 25 year history exploring the intersection between art, design, technology and contemporary culture. This Mitacs fellowship will develop the journal’s open access interactive web platform, PUBLIC:PORTAL, using information visualization and design to showcase the journal’s cutting-edge collaborative and cross-disciplinary work. This project designs and tests graphical user […]

Read More
Developpement de capteurs flexibles à base de polymère piezoelectrique

Le projet a pour objectif principal le développement de nanocapteurs piézoélectriques flexibles peu coûteux à base du polymère polyfluorure de vinylidène (PVDF) fabriqués par électrofilage. Ce polymère piézoélectrique, qui transforme une déformation mécanique en champ électrique, est un matériau chimiquement inerte qui peut être utilisé pour de nombreuses applications, Il a été montré dans la […]

Read More
Utilisation de l’intelligence artificielle pour détecter les intentions de mouvements chez un amputé.

Afin de remédier à la perte d’autonomie chez un amputé, l’utilisation d’une prothèse active, c’est-à-dire qui effectue des mouvements, est recommandée. Toutefois, leur contrôle peu naturel explique pourquoi les amputés adhèrent difficilement à cette solution. Or, un contrôle beaucoup plus intuitif pourrait être effectué en détectant en premier lieu le mouvement souhaité par l’amputé puis […]

Read More