Based on the userâs geo-location, timestamp and other attributes (eg. time of day, past visit history and app behavior categories, etc.), a machine learning algorithm can be developed to find which cluster the users belong to. Overall, the data of geo-location and timestamp are used to roughly locate the potential clusters. This project will involve some techniques and algorithms like cloud computing i.e Google Cloud Dataproc, sliding windows, histogram and machine learning algorithms. The challenge of first phase would be coming up with a good way of estimating the number of clusters.
Health disparities arise as a result of long-standing societal disadvantage and discrimination. As machine learning models become more popular in the healthcare sector, understanding of current health disparities becomes even more critical. Without careful management of existing biases, the models can inherit and amplify health disparities, leading to highly undesirable clinical outcomes. This project focuses on health disparities in access to preventive care services. Preventive care services such as screening and preventive medicine allows for early diagnosis and timely interventions.
This work aims to explore software and hardware co-optimization for deep neural network (DNN) inference applications. Once a model is trained to sufficient accuracy, the model is used to make inference or predictions based on this trained model. With increasing performance, more people are using these models for tasks such as translation, self-driving cars and speech recognition. This has greatly increased the demand for high performance inference hardware.
The rate at which chlorides from deicer salts penetrate into concrete towards the reinforcing steel has a strong influence on the time-to-corrosion and service life of concrete structures. Thus, the permeability of the concrete cover layer protecting the reinforcement has to be minimized especially in severe exposure conditions. In addition to the type of concrete, the permeability of the concrete cover is influenced by early-age curing (keeping the concrete warm and wet to maintain cement hydration that fills in pores).
Electronic assemblies are used to control various systems in an aircraft. Under normal operating conditions, these undergo vibration, and therefore have an expected life span. Different designs are analyzed to reduce production cost, and these designs must ensure that the electronic components contained within the hardware can tolerate the same operating conditions without failure. With time continuous research projects are being conducted to produce products with the same quality and lower costs, and this is one of them.
Progress monitoring is an essential task in all construction projects. A proper progress monitoring can minimize the level of project overruns, which is very common among construction projects but incurring significant loss to public and private funds annually. Manual methods of progress tracking are too infrequent to represent continuous and live insights about the workplace. Recent advancements in the area of computer vision and machine learning inspired researchers to use these techniques for development of new automated progress monitoring systems.
Net zero energy building produces as much energy as it consumes, and it has a great potential for energy and carbon reductions. This research will study the design of net zero energy multiunit residential buildings (MURBs), as well as to create a simple Excel tool as an alternative to EnergyPlus for quick assessment. In the previous research, an EnergyPlus model for a real MURB was created and calibrated and strategy for this building to undergo dramatic energy reduction was studied. This project will continue to quantify the trade-offs involved in the design and then create the Excel tool.
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 foundational aspect of deep learning that has garnered great intrigue in recent years is the generalization behavior of neural networks, that is, the ability of a neural network to perform on unseen data.
The proposed project includes 2 objectives: (1) provision of high quality evidence on the effect of specific food sources of sugars on cardiometabolic risk factors by conducting multiple systematic reviews and meta-analyses (SRMAs), to address the effect of replacing sugar-sweetened beverages with either diet pop or water in a randomized controlled clinical trial, and to analyze and report national data from StatsCan on current sugars consumption, and (2) efforts to translate the evidence from these studies both directly to the public and indirectly through communications to clinicians and pub
This project will result in the expansion of an athlete-focused genetic test to include additional genetic markers and algorithms for the purpose of personalized caffeine advice for endurance and other forms of exercise (strength, power, anaerobic-power) through continued analysis of 23 caffeine-associated genes that affect an athleteâs response to caffeine (positive, negative or no effect). The intern has already collected all necessary data, from over 100 athletes, from her previous doctoral research. She has already published some of her caffeine-associated findings.