Sweating the Small Stuff: A Simple, Rapid, and Effective Sensor for the Biomonitoring of Fireground Carcinogens in the Sweat of Firefighters

In the line of duty, firefighters are exposed to a range of toxic chemicals, some of which are known to cause cancer. Despite the immediate dangers that accompany the occupation, cancer is the leading cause of line-of-duty deaths in firefighters. There is growing concern that long-term exposures to these chemicals at the fire scene, and during the cleaning of contaminated uniforms, gear, and stations, are contributing to these increased cancer rates. Several markers of exposure to known cancer-causing chemicals have been detected in the body fluids of firefighters.

Real-time food analysis using deep learning for Diabetes Self -Monitoring Phase 2

Our proposed research is to create an algorithm capable of pre-evaluating diabetes patients’ meals before they consume them with the snap of a picture. We are attempting to accomplish this goal by employing AI, machine learning as well as computer vision for real-time analysis. Our goal is to analyse a user's meal to return an accurate carb count and offer portion size adjustments to reduce their blood sugar fluctuations.

New technologies for low frequency photoacoustic imaging

This project is focussed on developing an optical imaging technology called photoacoustic imaging. Photoacoustic imaging is able to distinguish healthy tissue from cancerous tissue during breast surgery and could one day eliminate the need for repeat surgeries. The technology uses a pulsed laser to selectively build up pressure in some tissues and microphones to listen for sound as the pressure dissipates. After reconstruction, the sound recordings are converted back into a pressure map representative of the tissues. The project funds will support two PhD students.

Contactless In-Home Monitoring of Seniors’ Activities and Locations Using Data Fusion

This research study proposed a unique platform that can provide information on location of the seniors inside the home, the type of activities they are performing, the intensity level of their activities and their progress in performing exercises that have been assigned by their therapists, remotely. This platform will combine different types of data
to increase the accuracy of the algorithms and to reduce the false alarms. Different data fusion techniques will be evaluated to provide different packages for the users according to their health status and privacy concerns.

Experimental and modelling investigation on the impact of engineered biochars on the abiotic and biotic removal of hydrogen sulfide in sewer systems

Several problems are associated with the emission of hydrogen sulfide (H2S) from wastewaters including its toxicity, causing corrosion, and the release of odors. Different strategies have been applied for the reduction or removal of hydrogen sulfides, such as the use of air or oxygen, nitrates, metal salts (iron salt), and biological agents for the oxidation of sulfides. Since the costs associated with the current solutions are extremely high, the development of more efficient and economical methods is critical for small to large municipalities.

Generating potent Interleukin-2 variant to specifically enhance NK cell proliferation

A human protein “interleukin-2” plays a key role in immunity. The target of this project is to modify this protein, triggering more immune cells in body, and hence enhancing body defense. At first, the intern will produce normal interleukin-2 in bacteria. The protein will then be mixed with the immune cells. Increase in cell amount indicates the protein is functional. Afterwards, the intern will modify the interleukin-2 at different positions, followed by combining these modifications randomly to create a library of various interleukin-2. They will be tested by using immune cells.

Federated Learning (FL) Interoperability, Access and Latency Optimization on The Edge and Cloud

As the underlying networks transition into 5G and 6G infrastructure, the optimal task performance across different WIoT devices with different energy consumption and computing power require coordination at both the software and hardware levels to maximize accessibility and minimize latency to support emerging applications. The proposed research will explore the various parameter space to determine how federated learning should be optimally executed in real-time, in the edge and cloud, to maximize user experience supported by upcoming 6G networks.

Price Bidding Optimization using the Advances of adversarial machine learning (AML)

Curate Mobile operates a demand site platform (DSP), which is an advertising platform responsible for bidding in real time ad placements from various publishers. This process is a blind auction, happening over 50,000 times a second, and during this bidding process we have less then 100ms to determine which of our clients should bid for this ad placement, how much it might be worth to them, and what price we believe we can win this auction for.

Smart Sheet: Pressure Ulcer Prevention Technology

Pressure ulcers are a major health concern around the world, affecting individuals living with spinal cord injury (SCI) in particular. Pressure ulcers occur when the blood supply to the skin and underlying tissue is compromised, leading to cell death and potentially fatal infections. In this project, we are developing a soft, flexible and stretchable pressure sensing sheet for pressure ulcer prevention. The device is designed for wheelchair use, where it covers the entire seating area over the cushion.

Prediction of preterm birth in twin pregnancies using machine learning

Preterm birth (PTB) is the leading cause of death in twin pregnancies. A variety of parameters, such as cervical length, maternal medical history, demographics, and obstetric characteristics all have been shown to affect the risk of PTB. However, the relationship is not obvious. Early prediction of PTB in these pregnancies can assist physicians in identifying those patients who may benefit from preventive interventions and closer monitoring. This project aims to use machine learning to create an algorithm that predicts which twin pregnancy is at a risk of PTB.