Les enjeux éthiques et juridiques en intelligence artificielle appliquée à la santé

De nombreuses questions éthiques, juridiques et de politique publique en matière de régulation se posent dans le domaine de l’intelligence artificielle et restent encore sans réponse, celles qui nous intéressent s’énoncent dans le domaine de la santé mentale. En effet, la création des machines d’apprentissage se fait par l’entrée de données massives traduites en algorithme […]

Read More
Securing Enterprises with Social Network Analysis

Computer administrators defend enterprises using tools that do not scale to the size of modem networks. As a result, malicious behavior in enterprise networks generally is W1detected, even when attackers do not attempt to be stealthy. One way to improve this situation may be through the application of social network analysis to the computer sectrrity […]

Read More
A melanoma diagnosis and prognosis framework with human readable explanation

Melanoma is the most lethal skin cancer, accounting for 2% of all skin cancer types, yet approximately 75% of skin cancer deaths. It often evolves from clear skin or existing moles, making it difficult to diagnose at early stage. Besides, the treatment of melanoma is a complex decision making process, which is affected by a […]

Read More
Better predictions of employee events

Machine learning can be used to predict employee events around retention, promotion or movement. This project explores how to generate better predictions by exploring correlations and exploiting them through features that increase predictive strength. Furthermore, the project explores how to reliably fine-tune the predictive model to a particular data set in the presence of interdependence […]

Read More
Data Poverty Project

In many developing countries, it is very difficult to survey vulnerable groups in a way that provides reliable research findings. These surveys also only give limited insights into the experiences of these populations. This project will develop a software program that can be used to model the probability of events occurring given the estimated probability […]

Read More
Detection, characterization and analysis of unsafe video content on YouTube

A safe video platform can provide a healthy and suitable environment for users in general and children in particular. This project aims to utilize machine learning and deep learning techniques to identify and flag sensitive and questionable content (e.g., content related to violence, sexuality, etc.). The algorithm will leverage video frames extracted from the database […]

Read More
A Framework for Assessing Regulations and Initiatives with Goals and Watson Analytics

Regulations are introduced to ensure the well-being, safety, and other societal needs of citizens and organizations. Yet, regulators often have difficulties assessing the performance of their regulations, and whether regulatory initiatives actually improve compliance. This project’s main objective is to investigate the suitability of a framework combining a standardized goal modeling notation with an existing […]

Read More
Automating Cloud Data Center Operation

Manual performance, configuration and fault management of Cloud Data Centers is vulnerable to human intervention and therefore subject to human errors. One way to circumvent this problem is to use automation of the Cloud Data Center operations based on advanced technologies which may include Machine Intelligence. As it is known in mobile industry applications/systems are […]

Read More
Automating Cloud Data Center Operation – Year two

Manual performance, configuration and fault management of Cloud Data Centers is vulnerable to human intervention and therefore subject to human errors. One way to circumvent this problem is to use automation of the Cloud Data Center operations based on advanced technologies which may include Machine Intelligence. As it is known in mobile industry applications/systems are […]

Read More
A novel cost-effective skin-tone detector for consumer devices

Skin-tone detection has received considerable attention in recent years and applied in wide range of image processing and computer vision applications. The objective of this research project is to develop a real-time skin-tone detection solution optimized for consumer devices, allows for a deliverance of high detection performance at minimal computational costs. The proposed solution will […]

Read More