The goal of our proposal is to develop three automated processes in the field of construction using artificial intelligence. The first process is to develop a method that can convert two-dimensional drawings into three-dimensional models that can be further manipulated on a computer. The second process is to optimize the cutting of raw materials-- such as panels and stiffeners-- to reduce the overall wastage, as well as optimize the transportation process of these materials to the resulting construction site.
Le nombre d’espèces qui nous entourent est si important qu’il peut être ardu, même pour les spécialistes, de toutes les identifier. Cela est particulièrement vrai pour les insectes. De plus, avec l’avènement des technologies mobiles de l’information, la quantité et la qualité des images disponibles n’a jamais été aussi importante. Grâce aux appareils photos numérique et aux téléphones intelligents, virtuellement n’importe qui peut générer des données d’observations qui peuvent être utilisées pour le suivi de la biodiversité.
Canadian Communities are facing a tidal wave of physical infrastructure debt as their physical assets deteriorate due to age. This project aims to use urban LiDAR data ("streetscapes") and computer vision to identify key physical assets such as (signs, curbs, centerline roads, streetlights, and other features) by there location (latitude / longitude) and key physical characteristics (size (height, width, length, thickness) and other characteristics.
This project is the extension project of the previous Tele-rheumatology project. In the previous project, we have designed and developed three components: hardware platform, which is the capturing device for rheumatoid arthritis patience movements by using both 2D and 3D cameras; the capture system, which is used by general practitioners to control the hardware platform; and the physician portal, which provides all the captured information from patience to rheumatologists for diagnose purpose.
There is growing evidence that e-cigarettes, also known as vaping, have led to an upsurge health risk to young people in Canada, including long-term harm to brain development and respiratory health. Due to such adverse effects, more and more young people indicate a desire to quit. However, such desires often become unsuccessful due to the lack of resources available to assist young people in reducing and quitting e-cigarettes.
The objective of this research project is to explore young people’s perceptions of the “QUIT smartcase” for reducing and stop using e-cigarettes.
Numerous studies in the application of Machine Learning to mental health have demonstrated a range of benefits in the areas of diagnosis, treatment and support, research, and clinical administration. COVID-19 is an unprecedented health crisis causing a great deal of stress in populations in Canada. In this project, our aim is to apply practical machine learning approaches to study whether the effects of medical cannabis can help address anxiety, depression and sleep challenges exacerbated by COVID-19.
The main focus of this research is to develop representation learning architectures and algorithms that can help perform various multimodal understanding tasks, and at the same time reduce the need for human supervision in the form of costly annotations.
When utilizing and implementing ML for prediction using administrative health data, two key issues are ML algorithm evaluation and generalizability21. Current approaches evaluate model performance by quantifying how closely the prediction made by the model matches known health outcomes. Evaluation metrics include sensitivity, specificity, and positive predictive value, as well as measures such as the area under the receiver operating characteristic (ROC) curve, the area under the precision-recall curve, and calibration.
Radio Frequency Identification (RFID) technology has received extensive interests due to its low cost, battery-free, and small size. Many exciting applications based on RFID have been developed in recent years, such as localization, gesture sensing, and health monitoring, etc. However, none of these systems are widely in real-world use. The reason is that most existing systems assume a static communication environment, while a small environmental variation or tag geometrical condition change will cause a large accuracy decrease.
This project/research is based on creating AI models that assist in determining blood glucose levels in individuals that have been diagnosed with Diabetes and classify changes in their risk-levels over a period of time. This research will be carried out by Ian Ho, student at Queen’s University pursuing his Bachelor’s in Applied Science – BASc, Applied Mathematics and Computer Engineering. He will research and develop predictive algorithms and analytical models for early diagnosis and risk assessment for Diabetes, under the supervision and advisory of QMind and Dr.