This is a joint event from the IEEE Ottawa Section Consultants Network (AICN) and IET Ottawa. The even is open to all and there is no charge to attend. Pre-registration is mandatory as spaces are limited.
Synopsis: We are becoming increasingly reliant on the software embedded in safety-critical medical devices, industrial robots, railway signalling systems, (semi-)autonomous cars, aircraft control systems and soft-drink dispensers (sic!). Producing and verifying these systems is a specialised form of software development and this type of development is currently facing rapidly-changing challenges. In this talk, Chris will outline some of these challenges, including the Safety of the Intended Functionality, the relationship between security and safety, and our exposure to intellectual debt. Although these problems are a long way from being solved, Chris will describe one approach that may become our place of refuge from the storm.
Speaker: Chris Hobbs
Software Safety Specialist – Blackberry QNX
Chris Hobbs works for BlackBerry QNX as a programmer and system designer, specializing in the area of Safety-Critical development. His work includes both helping in the safety certification of QNX’s products and working as a consultant with QNX’s customers, helping them develop safe systems. He has over 50 years of programming experience, most recently in C, Python and Ada, and he is the author of several books including Embedded Software Development for Safety-Critical Systems (second edition). In his spare time Chris sings Schubert Lieder and is a keen pilot.
Digitalize human beings using biosensors to track our complex physiologic system, process the large amount of data generated with artificial intelligence (AI) and change clinical practice towards individualized medicine: these are the goals of digital medicine. In this talk, we discuss how to design AI solutions in the clinical space and what are the key aspects to make a difference. We focus on two critical clinical topics that need AI: 1) atrial fibrillation (AF), and 2) viral illnesses (COVID-19). AF is the most common sustained cardiac arrhythmia, associated with stroke, heart failure and coronary artery disease. AF detection from single-lead electrocardiography (ECG) recordings is still an open problem, as AF events may be episodic and the signal noisy. We conduct a thoughtful analysis of recent convolutional neural network architectures developed in the computer vision field, redesigned to be suitable for a one-dimensional signal, and we evaluate their performance in the detection of AF using 200 thousand seconds of ECG, highlighting the potential and pitfall of this technology. We also discuss how to explain (global and local post hoc explanations) this AI model for AF detection using features that are commonly used by a cardiologist.
To tackle the problem of COVID-19, we start with an overview of continuous, passively monitored vital signs from 200,000 individuals wearing a Fitbit wearable device for 2 years. This large study provides the baseline for DETECT, our app-based, nationwide clinical study enrolling individuals who routinely use a smartwatch or other wireless devices to determine if individualized tracking of changes in heart rate, activity and sleep can provide early diagnosis and self-monitoring for COVID-19. We analyze data from more than 36,000 individuals, showing how we can discriminate (on an individual level) between COVID-19 and other types of infections. We discuss how this can impact both the individual and public health, and how the use of AI can be a game changer in this fight against the virus.
Giorgio Quer is the Director of Artificial Intelligence at the Scripps Research Translational Institute, where he is leading the Data Science and Analytics team within the All of Us Research Programâ€™s Participant Center (NIH).
His research focuses on artificial intelligence and probabilistic modeling applied to heterogeneous data signals, in order to extract key information and make predictions on future occurrences based on past data. He is involved in several digital medicine initiatives within the Scripps Research Digital Trials Center. For the DETECT study, he is developing algorithms to predict COVID-19 and other viral infections from wearable sensor data. He is responsible for collaborations with several industry partners, studying changes in heart rate and sleep data monitored by commercial wearable devices. He is also interested in the detection and modeling of atrial fibrillation from single-lead ECG signals. He is leading the collaboration with the Halicioglu Data Science Institute at UC San Diego towards the development of new AI models for health data.
He received his Ph.D. degree in Information Engineering from the University of Padova, Italy, and he continued his studies as a Postdoctoral researcher with the Qualcomm Institute at the University of California San Diego. He is a Senior Member of the IEEE and a Distinguished Lecturer for the IEEE Communications society.IEEE-ComSocOttawaWebinar-AI_DIG_MED-GiorgioQuer V2
Data is everywhere and can lead to incredibly valuable insights when harnessed correctly. From automating daily tasks to discovering breakthrough science, to making predictions about the future, utilizing data with machine learning is a fast and ever-evolving field of technology. In this talk, Kelsey will discuss her experiences and challenges using machine learning for space applications, focusing on uses for satellites orbiting Earth, how we can better understand our Sun and its interaction with our atmosphere, and how we can incorporate machine learning into future Mars rover missions.
About the speaker:
Kelsey Doerksen is a Space Systems Engineer in satellite operations at Planet, a San Francisco-based company that operates the worldâ€™s largest Earth Observation satellite constellation. In her role, she is responsible for maintaining the health and productivity of 100s of satellites daily and develops software to automate operations and detect anomalous satellite behavior. Kelsey holds a bachelorâ€™s degree from Carleton University in Aerospace Engineering: Space Systems Design and a Masterâ€™s in Electrical and Computer Engineering from the University of Western Ontario. She researches with the Paris Observatory in the fields of Space Weather and Space Debris and has previously interned at the NASA Jet Propulsion Lab with the Machine Learning and Instrument Autonomy Group. Kelsey is beginning her Ph.D. in the Autonomous Intelligent Machines and Systems program at the University of Oxford this Fall, where she will be utilizing machine learning and Earth Observation imagery to research the impacts of climate change on our planet.Poster_ML_Kelsey
Over a dozen LEO satellite constellations are in the planning or launch stages to deliver consumer, IoT, or enterprise access services. The talk will provide an overview of developments in LEO satellites for telecommunications; and explore competitive threats and synergies with the telecom sector, and attempts to answer the question on the economic viability of these constellations.
Frank Rayal is founding partner at Xona Partners, a boutique management and technology advisory firm. His focus is on enabling companies leverage new technologies and market trends to develop new revenues. Frank co-founded BLiNQ Networks and held senior product management and business development positions at Ericsson, Redline, and Metawave. He holds a BS in electrical engineering from Case Western Reserve University, Cleveland, Ohio, and an MASc in electrical engineering and an MBA from the University of Toronto, Canada.
In the digital age, the amount of worldwide data that is being generated on a daily basis is rapidly growing, reaching 175 zettabytes by 2025. These massive volumes of data have led to growing interest in using Machine Learning (ML) algorithms to extract valuable insights from databases. ML techniques can be considered as the foundation of a broad spectrum of next-generation technologies, including medical applications.
In this presentation, the role of ML in medical applications will be discussed. A newly developed data-driven classification algorithm will be explained, and its performance for the classification of biological datasets will be investigated and compared with the well-known classification models.
Behnaz Fakhar Firouzeh is in the final semester of her Ph.D. in Electrical and Computer Engineering at Carleton University. She has been working on signal processing and Compressive Sensing (CS) for over 8 years. She also has 5 years of experience in developing constraint optimization algorithms. Her developed algorithms successfully have been applied in different areas such as signal processing, Machine Learning, and artificial intelligence. Behnaz has (co)authored several articles in different journals and conference proceedings.