An economics-aware autonomic management system for big data applications
Recent advancements in software technology, including virtualization, microservices, and cloud computing, have created novel challenges and opportunities on developing and delivering software. Additionally, it has given rise to DevOps, a hybrid team responsible for both developing and managing the software system, and has led to the development of tools that take advantage of the enhanced flexibility and enable the automation of the software management cycle. In this new world characterized by volatility and speed, the Business Operations (BizOps) team is lagging behind and still remains disconnected from the DevOps team. BizOps views software as a product and is responsible for defining the business and economic strategy around it.
The goal of the proposed project is to imbue DevOps tools and processes with BizOps knowledge and metrics through formal models and methods. Currently, BizOps receives the software system or service as a finished product, a black box, on which a price has to be put and be offered to clients. The price and the marketing strategy are usually defined at the beginning of a sales cycle (e.g. a year) and remain the same for the entirety of the cycle. However, this is in contrast to the great volatility of the service itself. In most cases, the strategies are based on the instinct of managers with high acumen and experience and broad marketing surveys or one-to-one negotiations with clients, information that can easily change and may remain disconnected from the software development. The end product of this project is a set of economic and performance models to connect the DevOps and BizOps processes during the software’s life cycle and eventually incorporate them in automated tools to adapt and scale the system in production and enable continuous development, integration and delivery.
Automated cytogenetic dosimetry as a public health emergency medical countermeasure
Biodosimetry is a useful tool for assessing the radiation dose received by an individual when no reliable physical dosimetry is available. Our Automated Dicentric Chromosome Identifier software (ADCI) has been developed to automate dose estimation of gamma and X-ray radiation exposures. Biodosimetry laboratories currently process these data manually, and the capacity to handle more than a few samples at the same time would quickly overwhelm the laboratories. The software has been developed to handle radiation exposure estimation in mass casualty or moderate scale radiation events. Federal biodosimetry and clinical cytogenetic laboratories have automated systems to collect digital chromosome images of cells with and without chromosomes exposed to radiation. We have developed advanced image segmentation and artificial intelligence methods to analyze these images. ADCI identifies dicentric chromosomes (DCC), a widely recognized, gold standard hallmark of radiation damage. The number and distribution of DCCs are determined and compared with a calibration curve of known radiation dose. Our ADCI software can also generate these calibration curves. Our software computes the dose received of one or more test samples and generates a report for the user. The desktop version of ADCI contains an easy-to-use graphical user interface to perform all of these functions. The supercomputer version of this software proposed here will be optimized to determine the dose for many samples simultaneously, which would be essential in the event of a mass casualty.
Continuous vital sign monitoring using intelligent bed sheet
Studio 1 labs developed wireless intelligent bed sheet patient monitoring system that continuously captures client vital signs. In collaboration with Dr. Laura Nicholson and York University’s Faculty of Health, Studio 1 labs will work with SOSCIP infrastructure to match vital signs with gold standards approved medical decides for the highest level of accuracy through clinical validation and scientific evidence. With millions of data points collected from each device to output clinical grade quality information continuously, AI solutions allow modeling to predict health emergencies and diseases. This contributes to efficient health monitoring solutions that are simple and effective for use by older adults and healthcare providers.
High performance computing for assessing and mitigating the effect of extreme wind on building and cities
As the second largest country in the world, Canada’s diverse geography and climate increases our cities exposure to different types of natural hazards, such as snow storms, hurricanes, tornadoes and floods. The insurance industry estimates that insured catastrophic losses in North America average $80B per year. In Toronto (2005), for example. a single tornado event resulted in $500M loss. This is further compounded by changes in climate, population growth and aging infrastructure.
To maintain the prosperity of our communities, it is imperative that a comprehensive framework be developed to assess and mitigate the impacts of extreme climate on cities. The current project aims to develop a multi-scale climate responsive design framework that accounts for the complex interaction between buildings and wind (including hurricane and tornado). This computational framework, at neighborhood scale, models urban micro-climate necessary to assess the impact of changing city topology on the pedestrian level wind, air quality and to generate boundary conditions for small-scale simulations. At building scale, it develops a full numerical aeroealstic model (e.g. building model that flex) immersed in turbulent city flows, for the first time. This frame work when integrated with artificial intelligence based optimization procedures, allow optimizing tall building aerodynamics (shape) and dynamics (structural systems) appropriate for current era of booming tall building construction.
As a result, Ontario will save materials and energy in one of the most resource intensive sector, while enhancing the safety of Ontarians during extreme climate. For successful implementation of the framework, a high performance computing environment and experimental validations are necessary, which will be enabled by two unique research facilities in Ontario, Blue Gene Q and WindEEE Dome, respectively.
Novel approaches and architecture for survivable smart grid
The term smart grid refers to a power grid in which the electricity distribution and management is upgraded by incorporating advanced two-way communications and pervasive computing capabilities for improved control, efficiency, reliability and safety [6]. Today’s power grid systems lack the ability to detect failure in ‘the last mile’ (i.e., in the power line between the user and the last transmission point). For example, during any power outage event, if the problem is within the last mile then the utility company’s operations center is unaware of the outage until notified by customers. Also, inside the power grid core systems, although the operations centre has the ability to detect a failure, their current systems lack the ability to provide an automated power backup facility. This means that when there is a core grid systems failure, their current fault notification systems can identify the failure, technicians are dispatched to diagnose and repair the fault. From the time the systems fails to the time it gets restored, the affected area/community experience power outage. In order to have (a) an automated failure notification systems in the last mile, and (b) a smart resilient system inside the grid’s core, today’s smart grid will require the ability to failure detection in the last mile, and a failure protection ability inside the core.
Our research will develop (a) an automatic fault notification systems for the last mile so that the operations center get real time notification of any failure in the last mile and can take measures to restore the outage; and (b) a new smart resilient system which would (during a power outage) automatically re-route its power to an alternate route bypassing the failed components of the grid so that it doesn’t lead to a power outage during a grid failure.
Quantitative analysis of Parkinson’s disease symptoms using whole-body kinematic technology for optimizing deep brain stimulation
Parkinson’s disease (PD) is a degenerative and progressive neurological disorder that can severely affect the mobility, particularly in advanced stages. Deep brain stimulation (DBS) is a surgical procedure used to treat the motor symptoms of Parkinson disease patients by implanting electrodes into the brain. Motor symptoms of PD like slowness of movement, tremor, walking and speech difficulty, and dyskinesia, are the key parameters that are taken into consideration by clinicians to program the DBS device. These motor symptoms differ across the body and are unique to each patient. Moreover, patient variability in terms of medication and non-motor symptoms like sleep and mood makes programming DBS electrode setting a significant challenge. On the other hand, the biomechanics of the whole-body are too complex to accurately assess visually due to the multitude of simultaneous movements. Therefore, a detailed, quantitative method of assessment needs to be employed to make the DBS setting optimization as accurate as possible.
Safe learning-based control for high-precision assembly robots in advanced aerospace manufacturing
Ontario’s aerospace industry has a distinguished history of innovation, and it provides a strong contribution to the Canadian economy with its more than 350 firms employing more than 20,000 Ontarians. Our industrial partner, MDA Robotics and Automation, is a leading company in providing advanced engineering solutions for various industries, including aerospace robotics and manufacturing. Having designed and built the famous Canadarm and Canadarm2 for manipulation in space, building versatile, high-precision assembly robots for aerospace applications on earth (such as airframe assembly for an airplane) is at the top of the company’s current priorities. Potential advantages include lowering the assembly cost, increasing the productivity, and reducing the risk of human error. Unlike high-volume manufacturing processes, for which it pays off to go through the lengthy, possibly month-long, process of manually programming and tuning the robot controls to carry out a limited range of repetitive tasks in a well-defined environment, the diversity of tasks and the uncertainty of the work environment in aerospace manufacturing motivate the need for smarter robots that can safely interact with their unpredictable environment, improve their performance through learning, and more importantly, generalize the knowledge from previous tasks and/or other robots to adapt to new tasks not trained on before.
The objective of the project is to combine advanced methods from control theory, machine learning, and optimization to develop computationally efficient, learning-based control algorithms that improve the assembly robots’ performance in uncertain scenarios. Our strategy includes utilizing (i) well developed algorithms in our group for online, safe learning of robots, and (ii) deep learning for transferring the knowledge learned by one robot in a particular task to other similar tasks and/or robots.
Smart analytics for smart grid
How we use energy reveals vital information about our everyday behaviour – from our work and school schedules to when we are likely to be sleeping, eating and performing simple chores such as laundry or washing dishes. It even reveals when we are on vacation. While this information in the wrong hands could put us at risk, it also plays an important role in reducing our carbon footprint and ensuring the cost of energy is kept relatively low. Power generation companies use information derived from microclimate, small areas within general climate zones, to accurately predict power generation needs. Microclimate information is captured from smart meters, which wirelessly transmits data from our homes to utility companies. Considering that more than one million smart meters have been installed in Ontario homes since 2010 and that number continues to grow, it’s necessary to find a way to ensure the data captured by smart meters is protected and secure from threat.
Visual breadcrumbs for emergency return of unmanned aerial vehicles
Unmanned Aerial Vehicle (UAV) technology has advanced rapidly in the last decade, making wide-ranging applications (e.g., automated remote sensing, precision agriculture, emergency response, reconnaissance & surveillance) a near-term reality. A key building block that is yet to be developed is a solution that enables safe beyondline-of-sight flight, preventing uncontrolled vehicle behaviour in the event of failures such as GPS signal loss. The goal of this project is to develop a vision-based navigation solution that enables UAVs to safely return home when they lose their means of localization (i.e., GPS).
The University of Toronto (UofT) has been developing visual route-following techniques for ground vehicles for the past decade and gained extensive experience in practical deployments during field trials. This project will require major extensions including the adaptation of the ground-based visual navigation framework to aerial applications and the development of new techniques for path planning and localization that guarantee robust path-tracking and safe return. Moreover, safety solutions as proposed here will help to accelerate the development of a regulatory framework for the commercial use of UAVs in beyond-line-of-sight applications.
Wire-free continuous respiratory monitoring using functional bed sheet
Apnea is a temporary stop in breathing and the most common type of apnea is Obstructive Sleep Apnea (OSA), which is a disturbance in sleep that is a leading cause in health problems such as heart disease, diabetes, high blood pressure, and Parkinson’s disease if left unnoticed or untreated. Importantly, 80% of people affected by OSA remain undiagnosed. In infants, a stop in breathing for 20 seconds becomes fatal. Current methods of detection of respiration in hospital settings are either quite invasive, with wires and electrodes attached on the body, or are very time-consuming, such as manual counting method and listening of changes in breathing patterns.
What if abnormal respiratory patterns can be detected non-invasively and provide early prediction of emergencies before they occur? This is the goal of Studio 1 Labs, a health technology company that has developed a responsive bed sheet using a noninvasive method of monitoring respiration patterns and changes in respiratory rate. Capturing millions of data points across a range of sensors, Studio 1 Labs is collaborating with Dr. Plinio Morita from the University of Waterloo, to develop a machine-learning algorithm for detection of respiration changes and to translate big data analysis into useful information, to provide patient-centered care for hospitals and homes.