Computer aided diagnosis of COVID-19 symptoms using medical sensors
The challenge that currently has arisen because of COVID is that in-person appointments with doctors are not possible and everyone has to use Telemedicine. Though Telemedicine is a great convenience, the problem with current Telemedicine systems is that they cannot be used to virtually examine patients and identify if COVID-19 symptoms are present. The main reason for this is because our current Telemedicine systems lack integration with medical devices that allow capturing physiological signals over the web. We are working towards integrating these medical devices into Telemedicine platforms so that the diagnostic utility of Telemedicine can be improved, and these platforms can be used to virtually assess patients over the web.
Our software platform integrates digital medical devices into Telemedicine video conference platforms that allows doctors to assess COVID-19 symptoms from captured physiological signals and provides large scale machine learning aided COVID screening at home. Imagine Telemedicine appointments where in addition to just consulting with your doctor via video tele-conference you can have them hear your heart/lung sounds, take your temperature, blood pressure, weight, blood oxygenation all in real-time and over the internet. We are building the software infrastructure that will allow Telemedicine platforms to seamlessly integrate the plethora of digital medical devices on the market, which enable this functionality, natively into their software ecosystems. Additionally, our platform also offers an intelligent layer of machine learning software that aids doctors in consolidating patient data, clinical decision making, computer aided diagnosis and carrying out appropriate follow-ups and referrals.
Computer vision powered digital twin for tracking manual manufacturing processes
Over 70% of tasks in manufacturing are still manual; therefore, over 75% of the variation in manufacturing comes from human beings. Human errors were the primary driver behind $22.1 billion in vehicle recalls in 2016. Currently, when plant operators want to gain an understanding of their manual processes, they send out their highly paid industrial engineers to run time studies. These studies produce highly biased and inaccurate data that provides minimal value to manufacturing teams. This project aims to develop a computer vision powered digital twin prototype that is ready to test on the client’s site, which helps manufacturing plant operators gain unprecedented visibility into their manual production operations, allowing them to optimize their worker efficiency while maximizing productivity. This will be done by automated data generation using computer vision, conversion of raw data into useable information, visualization of information using standard Business Intelligence methodologies and lastly, prediction of future plant performance based on historical information, as well as information about other market drivers.
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.
COVID-19 AI based screening and monitoring of COVID-19 respiration patterns using acoustic sensors
This project addresses the pressing need for remote monitoring of long-term care homes to ensure potential cases of COVID-19 are identified early, isolated and treated.
Ryerson University’s Xiao-Ping Zhang, in concert with Altum View Systems Inc., will develop AI-based algorithms and systems to screen and monitor acoustic respiration patterns for COVID-19 in real-time, using customer mobile devices (e.g., mobile phones, wireless headphones, smart wrist-watches, etc.), low-cost electronic stethoscopes, and professional respiration monitor diagnostic devices. The COVID-19 acoustic respiration pattern screening and monitoring system will be incorporated into and complement Altum View Systems Inc.’s current camera-based health monitoring system for home care and long-term care facilities.
COVID-19: Agent-based framework for modelling pandemics in urban environment
The development of COVID-19 pandemic raises important questions on optimal policy design for managing and controlling the number of people affected. In order to answer these questions, one needs to better understand determinants of pandemic dynamics. Indeed, the development of epidemics depends on various factors including the intensity and frequency of social contacts and the amount of care and protection applied during those contacts. In particular, one area where the disease can be transmitted is the urban space of a large city such as Toronto.
The goal of the project is to create an agent-based framework for building virtual models of an urban area. This framework will be used as a virtual laboratory for testing various scenarios and their implications for the development of pandemics. In order for conclusions to be reliable, the models (known in the literature as synthetic population models or digital twins) have to be up to scale, with the number of agents comparable with the population of the city. This, in turn, requires implementations ready to be run in a large-scale distributed computing environment in the cloud as the algorithms behind the engine need high-performance computing power.
The framework will allow us to evaluate different COVID-19 mitigation policy designs. This includes possible decisions such as decreasing proneness to wearing masks, closing down some non-essential, high-contact, social network nodes (for example, hairdressers), limiting the number of people having simultaneous social gatherings or reducing the number of people on streets altogether via promoting actions such as #stayathome.
Creating a Predictive Financial Model to Optimize Digital Marketing Budget of SMEs Post COVID-19
In recent years, digital marketing has surpassed offline marketing and made marketing technology (Martech) the number one spending priority of businesses that didn’t exist ten years ago (Johnsen, 2017). Moreover, in the coming months, businesses are going to become more reliant than ever on their digital strategy. Without wanting to sound too alarmist, in many cases it will be the deciding factor in whether they make it through the tough times ahead. One thing is clear: marketers in the post-COVID-19 era will have to rethink what technologies they really need, which ones can help them save money, and which ones can help them transform their businesses that have been altered by this crisis. Data science can help companies acquire more customers, it can tell when, where and how to pitch target audience to maximize yields and minimize waste (it is estimated that on average 26% of marketing budgets are wasted on ineffective channels and strategies (Blake, Nosko, Tadelis, 2015)).
Using the right data sources, we can build simple (and more complex) models to predict impact on the customers’ behaviors and PPC (pay-per-click) conversion rates respectively, if you run a campaign at a certain point in time. These predictive analytics can estimate when the desired action will happen and what can impact it, and what would be the financial value.
The objective of this research is to introduce a predictive financial model to help Genius Camp and other SMEs in the Education industry, which are disrupted by COVID-19 situation, to allocate their digital marketing budget more efficiently. The data-backed solutions from this model will equip them with tools to make more informed decisions about going virtual and their resulting digital marketing initiatives. (i.e. how to structure their social media campaigns to achieve the highest ROI)
FinTech Deep Learning in Financial Modeling
The last four decades saw the development of the financial derivatives valuation technology. Only a few practical models, however, can be solved in closed form, and as most utilize numerical methods such as finite-difference partial differential equation solvers, discrete-time trees, or Monte-Carlo simulators, these traditional methods are quite slow. Running book valuation and risk processes on hundreds of CPU cores requires an overnight process to comply with regulatory and accounting standards. This creates a huge cost(~$10 million/year) and a commensurate environmental and carbon impact. Similar issues are now facing the Insurance industry due to the accounting standard IFRS 17. The key goal of the partnership is to develop deep learning, and more generally machine and reinforcement learning, models to accelerate these processes, and to provide efficient simulation engines for asset prices, volatility surfaces, derivative valuation, and hedging.
Deep Learning with Big Data for Innovation Acceleration
Presently, XLScout hosts data of over 130 million patents and 200+ million research publications occupying approximately 8TB of storage. Searching such a massive database using basic, mostly keyword-based search is very cumbersome and time-consuming. Moreover, it requires domain-specific knowledge about patents. With this project, XLScout aims to alleviate the pain of searching this massive system by employing machine learning (ML) and natural language processing(NL)techniques.Text autocompletion and recommendation will provide a better and smarter way for the end-users to search thismassive database. The auto-completion will be based on the corpus of patent documents and research publication to provide suggestions ofrelevant content. The MLmodel will be trained on that massive corpus taking into consideration language semantics. Techniques such as BERT and GPT 2/3 will be considered together with various pre-processing techniques. The size of the document database, document diversity, together with the subjectivity of desired results will make it challenging to evaluate such a system. We will employ both human-centric and automated evaluation approaches.Document categorization will also be based on the semantics, and it will group documents into labeled categories. Unsupervised techniques will be examined in their ability to do this categorization. However, different companies, XLScout clients, have different preferences in respect to this categorization. Therefore, an approach will be developed for the end-users to express their preferences by providing sample categories. Then, the model will learn from those preferences and carry out categorization. The challenge in this categorization is to enable unsupervised categorizationwhile supporting semi-supervision and customization. This categorization will be client-company specific and the modelwill have to learn from a limited number of example classes identified by the end-user.
Design and Development of Autonomous Disinfecting Embedded Systems for COVID-19
One of the major challenges during the COVID-19 pandemic is frequent disinfecting. This is very critical for places like hospitals and long-term care. In most places, human operators perform the cleaning but it may cause them to be infected with the virus because of the shortages of personal protective equipment (PPE) and many of the unknowns of COVID-19. The aim of thisCOVID-19 project is to improve Cyberworks Robotics’ navigation technology on existing (a) floor disinfection machines (e.g. wet floor scrubbers) of various types used in hospitals, (b) high-intensity UV disinfection machines, and (c) chemical mist disinfection machines. This would allow hospitals to disinfect the hospital surfaces on a more frequent basis than is possible with human cleaners (due to both the cost and availability of human operators) and also simultaneously to increase the quality of cleaning by ensuring that some surfaces are not missed due to human error and neglect
Design of OLED materials for manufacturing and improved product quality
Organic light emitting diodes (OLEDs) present a unique opportunity to produce thinner and more efficient lighting and displays. This will change the way we interact with light. The main barrier to mass adoption of OLEDs is the manufacturing process, due to the need for high throughput while maintaining nanoscale precision. High throughput operation requires materials that can undergo elevated temperature without decomposing. Our objective is to use computational chemistry to model innovative materials that can withstand these elevated temperatures while still providing high performing OLEDs. We will simulate targeted compounds using SOSCIP’s computer cluster examining properties relevant to OLED manufacturing processes. Promising materials will be synthesized and their properties experimentally measured then compared to the simulation results. The most promising materials will then be integrated into OLEDs and characterized by OTI Lumionics in their pilot scale manufacturing line located in Toronto, ON.
Detailed computational fluid dynamics modeling of UV-AOPs photoreactors for micropollutants oxidation in water and wastewater
Micropollutants such as bisphenol-A and N-nitrosodimethylamine pose a significant threat to aquatic life, animals, and humans beings due to their persistent and potentially carcinogenic nature. While most conventional water treatment methods cannot remove these contaminants, ultraviolet-driven (UV) advanced oxidation processes (AOPs) are effective in degrading micropollutants. As UV-AOPs require electrical energy to enable the treatment, energy costs present a barrier to the widespread adoption of this technology. In this project, we focus on the optimization of UV-AOPs-based reactors to enhance their degradation performance while reducing their energy consumption. In this respect, we will develop a detailed numerical model that integrates hydraulics, optics and chemistry to investigate UV-AOP photoreactors in a comprehensive manner.
The resulting information will then be utilized to design the next-generation of UV-AOP photoreactors commercialized by Trojan Technologies. The design space will be explored by high-performance computer simulations of full-scale photoreactors rather than simplified or scaled-down models. This will be accomplished by leveraging opensource software, artificial-intelligence optimization techniques and the second-to-none parallel-computing capabilities offered by Blue Gene/Q. Once the optimization of UVAOPs-based reactors is complete, the advanced modeling results generated using Blue Gene/Q will be utilized in the development of a simplified model for sizing purposes. This will be accomplished through combined use of metamodeling techniques and cloud computing. In brief, the concept is to simplify the detailed model developed earlier so that it can be simulated using hand-held mobile devices, which will allow the company’s sales personnel to market the optimized reactors. Consequently, it will allow the company to increase its competitiveness on global scale as well as to increase the rate of adoption of advanced water treatment technologies by water utilities and end-users.
Development of a COVID-19 in pregnancy data respository and prognostication algorithm
Professors Dafna Sussman & Rasha Kashef of Ryerson University are teaming up with Mount Sinai Hospital to tackle the very difficult problem of achieving successful early intervention for pregnant women diagnosed with COVID-19.
The project aims to support medical professionals who are directly treating COVID-19 pregnancies. A comprehensive, anonymized data repository will be deployed in conjunction with dedicated prediction algorithms to score patients for their risk of severe deterioration. The repository together with the algorithm are expected to radically transform Canadian and, potentially, international healthcare providers’ ability to identify, manage and treat cases of COVID-19 in pregnant patients.
Development of cardiac specific machine learning infrastructure
Analytics for Life, Inc. (A4L) is an early stage medical device company that specializes in the development of technologies to analyze patient physiological signals in order to evaluate cardiac performance, status and risk. A4L’s core competencies include identifying and developing mathematical features from physiological signals and assembling these features into clinically informative formulae using machine learning techniques. A4L has used third party machine learning tools (open source and licensed products) for the formula generation aspect of the product development cycle.
Specifically, A4L has used these tools to demonstrate the feasibility of computing left ventricular ejection fraction, cardiac ischemic burden and other cardiac performance/status parameters for simple to collect, non-invasive physiological signals (surface voltage gradients, SPO2, Impedance etc.). As a result of this experience, A4L have learned the benefits and insufficiencies of these tools for A4L’s specific purposes. A4L plans to file with the U.S. Food and Drug Administration (FDA) an application for approval of a physiological signal collection device and will soon afterwards be seeking market clearance for products assessing cardiac health emanating from the machine learning process. A4L believes it can build a machine learning tool specifically tailored for cardiac evaluation based on experience with the tools used to date.
This A4L-specific machine learning paradigm will search only relevant mathematical spaces, cutting down on time and CPU power needed to iterate to solutions and will allow for an assessment of a much wider array of potential solutions. Furthermore, this A4L-specific machine learning paradigm will provide a controlled and validated system that can be audited and evaluated by regulatory bodies, something that is not possible with the current machine learning tool(s). A4L proposes a hybridization of paradigms within a set mathematical space. This will create efficiency in the search, and therefore more searches can be performed in the same period of time. This will lead to more solutions being available for evaluation, resulting in more accurate and efficiently produced end solutions. If successful, this new paradigm will allow for simple, non-invasive, rapid and relatively inexpensive cardiac diagnostic capabilities, bringing tertiary care diagnostics to primary care settings and disrupting the current infrastructure and capital cost-centric model of diagnostic delivery.
Development of severity index of exacerbation for COVID-19 symptoms from abnormal respiratory patterns
Struggling to breathe has been a challenge that existing monitoring devices have faced, for identifying early symptoms of respiratory diseases such as novel Coronavirus (COVID-19). Measuring respiratory rate alone would result in potentially missing if a patient was unable to inhale a full breath.
To overcome this challenge, a novel technology solution invented in Canada is used through an Intelligent Bed Sheet, with the ability to continuously monitor if a patient has normal, shallow, or irregular breathing.
This collaboration with York University will revolve around developing a Severity Index by identifying earlier when a patient is struggling to breathe. Using the most advanced electronic fabric technology, the SOSCIP Platform will support computing challenges by using large amounts of breathing data in a constantly changing environment, to precisely identify before a patient’s breathing becomes more severe.
Distributed and scalable search in enterprise databases
Google search, and other search engines such as Bing and Yahoo!, provide a convenient way to find Webpages that contain various keywords or are related to particular topics. For the purposes of searching, Webpages are essentially loosely structured paragraphs of text. However, much of the world’s high-quality enterprise data are structured into well defined tables containing sets of well-defined columns.
One consequence of structured database design is that information about a single entity may be scattered across many columns in many tables, and must be stitched together in a meaningful way when answering user queries. This turns out to be significantly more difficult than finding Webpages or text documents containing various keywords.
As Dr. Surajit Chadhuri (a Distinguished Scientist at Microsoft Research) recently argued in a keynote talk at the IEEE Data Engineering conference, search over structured databases has fallen behind search over unstructured data. In the proposed research, we will develop a powerful and intuitive search system, akin to Web keyword search, for structured enterprise data. Our system will empower nontechnical users to explore enterprise databases and turn big data into actionable insight, just as Google search has empowered society to explore the Web.
Distributed Deep Learning and Graph Analytics Using IBM Spectrum Computing Solutions
Deep learning is a popular machine learning technique and has been applied to many real-world problems, ranging from computer vision to natural language processing. In most cases deep learning outperformed previous work. However, training a deep neural network is very time-consuming, especially on big data. A popular solution is to distribute and parallel the training process across multiple machines. Indeed, the race is on to parallelize deep learning! Industry and academic research teams around the world are trying to make deep neural networks train as fast as possible on farms of GPU capable servers. We are working with our IBM partners to help develop advanced scheduling and messaging techniques for distributed deep learning. In addition, we will develop two real-world applications of distributed deep learning to demonstrate the efficiency and effectiveness of distributed deep learning. In one application, we address the video surveillance problem of tracking a moving target over a network of video cameras with partial or no overlaps in their coverage. We will use a deep learning approach to identify multiple pedestrians in each video frame, and a particle filter to track moving pedestrians. In the second application, we address the problem of fraud/intrusion detection. We will use graph-based detection that considers relationships between objects or individuals. Graph-based approaches are powerful because they do not operate on objects or individuals in isolation, but also consider their network information. We will emphasize on graph-based fraud detection methods that have a number of applications and potentially large impacts.