Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

Université de Sherbrooke

$32,000.00

Neuromorphic Wearable Medical Devices

FY 2024-25

Summary
Artificial intelligence (AI) is in the process of revolutionizing medicine and healthcare. Deep learning algorithms can now achieve, and in some cases even surpass, the diagnostic performance health care professionals in a wide range of diagnostic settings. In recent years, radiologist-level detection of pneumonia from chest X-rays, cardiologist-level detection of arrhythmia from electrocardiogram (ECG) signals, and expert-level detection of sleep stages with electroencephalography (EEG) signals have all been achieved using deep learning technologies. However, these deep neural networks require a significant amount of computing power to operate and they cannot yet be used in low-power wearable medical devices. The next major breakthrough in AI-based healthcare technologies will use artificial neural network-based wearable medical devices to provide always-on screening, detection, and monitoring for the diagnosis and treatment of a wide variety of medical conditions. The human brain is remarkably efficient in terms of energy consumption. Individual neurons communicate with one another via short, isolated spikes of electricity or action potentials. Since most neurons can be inactive at any given moment, this results in an extremely efficient approach to information processing. Neuromorphic computing is a nascent field of research that takes inspiration from the efficient processing strategies of the brain in developing novel spiking neural network algorithms and novel custom computing hardware substrates on which to execute them. The resulting neuromorphic processors are fundamentally different from the central processing units (CPUs) and graphics processing units (GPUs) we have relied on until this point. My research program aims to bridge the gap between state-of-the-art deep learning achievements in the medical setting and extremely low-power neural network-based computing solutions for the wearable medical devices of the future. In particular, I will focus on three medical conditions that are detectable from brain waves via EEG signals, for which low-cost wearable sensors are currently available: Alzheimer's disease, epilepsy, and insomnia. Early detection and continuous monitoring of these conditions would provide improved health care outcomes and increased quality of life for the large segment of the population that they touch. HQPs at the Master's and PhD level will be involved in reproducing the state-of-the-art with deep learning methods, developing novel spiking neural network-based approaches to translate these gains to the emerging field of neuromorphic algorithms, and developing neuromorphic hardware implementations of these spiking neural network algorithms. The hardware components of my research program will leverage my existing collaborations as Research Chair in Neuromorphic Computing from the Quebec ministry of economy and innovation (MEI), co-held with a neuromorphic computing hardware specialist.
Program
Discovery Grants Program - Individual
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2023-04985
Name nom
Wood, Sean
Department département
Génie Électrique et Génie Informatique
Organization id
68
Institution établissement
Université de Sherbrooke
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
32000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2514
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Digital signal processing
Research subject fr
Traitement des signaux numériques
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Neuromorphic Wearable Medical Devices
Keywords
neuromorphic computing; machine learning; wearable medical devices; biosignal processing; speech processing; artificial neural networks; computational neuroscience
Application summary
Artificial intelligence (AI) is in the process of revolutionizing medicine and healthcare. Deep learning algorithms can now achieve, and in some cases even surpass, the diagnostic performance health care professionals in a wide range of diagnostic settings. In recent years, radiologist-level detection of pneumonia from chest X-rays, cardiologist-level detection of arrhythmia from electrocardiogram (ECG) signals, and expert-level detection of sleep stages with electroencephalography (EEG) signals have all been achieved using deep learning technologies. However, these deep neural networks require a significant amount of computing power to operate and they cannot yet be used in low-power wearable medical devices. The next major breakthrough in AI-based healthcare technologies will use artificial neural network-based wearable medical devices to provide always-on screening, detection, and monitoring for the diagnosis and treatment of a wide variety of medical conditions. The human brain is remarkably efficient in terms of energy consumption. Individual neurons communicate with one another via short, isolated spikes of electricity or action potentials. Since most neurons can be inactive at any given moment, this results in an extremely efficient approach to information processing. Neuromorphic computing is a nascent field of research that takes inspiration from the efficient processing strategies of the brain in developing novel spiking neural network algorithms and novel custom computing hardware substrates on which to execute them. The resulting neuromorphic processors are fundamentally different from the central processing units (CPUs) and graphics processing units (GPUs) we have relied on until this point. My research program aims to bridge the gap between state-of-the-art deep learning achievements in the medical setting and extremely low-power neural network-based computing solutions for the wearable medical devices of the future. In particular, I will focus on three medical conditions that are detectable from brain waves via EEG signals, for which low-cost wearable sensors are currently available: Alzheimer's disease, epilepsy, and insomnia. Early detection and continuous monitoring of these conditions would provide improved health care outcomes and increased quality of life for the large segment of the population that they touch. HQPs at the Master's and PhD level will be involved in reproducing the state-of-the-art with deep learning methods, developing novel spiking neural network-based approaches to translate these gains to the emerging field of neuromorphic algorithms, and developing neuromorphic hardware implementations of these spiking neural network algorithms. The hardware components of my research program will leverage my existing collaborations as Research Chair in Neuromorphic Computing from the Quebec ministry of economy and innovation (MEI), co-held with a neuromorphic computing hardware specialist.