Link predicting in court

The company Lexum is an undisputed leader in the development of information retrieval tools for the law - statutes, regulations and decisions of courts and tribunals. The project is to improve a new tool offer by the company. The tool is used to retrieve a list of legal subjects from a factual description. With that list extract, the tool provides a list of potential related document.

Simplification of long sentences

The task of sentence simplification can present itself in multiple forms. It could consist in correcting the punctuation of a sentence like so:
Avant : J’ai acheté un bateau je l’aime beaucoup.
Après : J’ai acheté un bateau. Je l’aime beaucoup.
However, a sentence can be both long and written correctly. In this case, it would require a reformulation in multiple sentences like so:

Electrical Load Forecasting

Load forecasting is an essential activity for a company like Hydro-Québec. It is necessary for objectives as varied as the management of production or the management and maintenance of the electricity network. Any significant forecasting error can result in reliability issues, loss of opportunity, or additional costs to the business. On the other hand, a good prediction would allow Hydro-Québec to generate additional sales in neighboring markets. With the deployment of its Advanced Measurement Infrastructure (AMI), Hydro-Québec now has a significant amount of new consumption data.

Real-time object recognition on wearable devices

The goal of the project is to implement real-time state of the art object recognition models on wearable devices. These devices aim to help people living with a visual disability by providing a description of their outdoor environment and offer navigation guidance. This would improve the experience of the users by allowing them to perform usual day-to-day tasks with much more ease and safety.

Low data drug modeling

The project aims to facilitate the research and development of new drugs by exploring Machine Learning methodology useful for both the generation of new molecules and the prediction of molecule properties. Doing so will involve training deep learning models on a large number of small, heterogeneous datasets, with the objective of transferring learned representations quickly when faced with a new drug-discovery or drug optimization objectives.

Super resolution for MRI scans

Brain MRI scans are a critical component in the diagnosis of neurodegenerative disorders. However, there is a wide diversity in terms of the image quality and resolution obtained from different MRI scanner. In particular, it is common to find coarse resolution MRI scans (e.g. every axial slice is 3-5 mm thick), which limit the type of anatomical analysis that can be performed. The goal of this project is to develop and validate the performance of state-of-the-art super-resolution methods in 3D MRI scans, which generate high resolution MRI scans from low resolution scans.

Speaker Diarization

Machine-transcription of speech into text is very helpful in many scenarios. Consider the case of machine-transcription of conversation between a Doctor and a patient. If we are able partition and identify the segments of patient’s speech from those of doctor’s, then the transcribed text is more structured and can be more helpful for further use. The process of partitioni a given input audio stream into homogeneous segments according to speaker identity is called Speaker Diarization. In this project, we want to implement and improve the state-of-art method for speaker-diarization.

Time-series forecasting

The Internet of things is a global infrastructure that enables advanced services by interconnecting physical and virtual things like smartphones, sensors, computers, machines or buildings. These devices typically create enormous amounts of data that can be used to create business value. Mnubo offers a software dubbed Smart Objects that is a comprehensive, full stack IoT data platform, which allows enterprises to transform IoT data into critical insights that can be used for maximizing their profit (e.g. In agriculture, one could optimize the irrigation rate to maximize crop production).

Readmission AI: a predictive tool to assess patient risk of hospital readmission

Logibec Readmission AI is a predictive intelligence tool that accurately identifies the patient’s likelihood of being readmitted within 45 days of discharge. Rigorously and ethically developed with machine learning techniques in partnership with three large healthcare organizations in Québec, the predictive model uses reliable, accessible and timely clinical-administrative and sociodemographic data to provide clinically relevant stratification of readmission risk.

Impact of Repeated Vaccination on 2017-2018 Influenza Vaccines Effectiveness – A Retrospective Study

Influenza causes seasonal illness characterized by fever, myalgia and respiratory symptoms which can lead to hospitalization and death. Although it is a vaccine preventable disease, influenza contributes directly and indirectly to a large number of hospitalizations and outpatient visits. More specifically, influenza causes every year approximately 12,000 hospitalizations and 3,500 deaths in Canada, of which 90% occur in people 65 years and older. Recently, numerous studies have investigated the impact of repeated vaccination on its effectiveness reporting a large variety of results.