Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Engage Grants Program

Université de Montréal

$25,000.00

Deep Learning for Event Detection in Electrocardiograms

FY 2009-10

Summary
Biomedical signal processing is a crucial component of the development of improved diagnostic technologies, in particular for cardiovascular diseases, which remain a major cause of mortality. Machine learning algorithms can be used to train computers to detect events of interest in signals, and these automated systems can assist medical professionals in the analysis of large volumes of patient data, or raise alerts while the patient is not under (human) medical observation. Although several algorithms have been proposed, they are still very sensitive to many of the variations present among patients and recording conditions. Reducing the number of false positives and false negatives would be very helpful to make such products more practically useful and medically acceptable. For this purpose, we will explore the advantages that may be brought by new advances following a technical breakthrough in 2006 in the area of neural networks and probabilistic graphical models with so-called deep architectures. The plan is to develop new variants of deep architectures for the analysis of electrocardiogram signals. The main innovations proposed involve specifics of these signals: exploiting information about the underlying variations and noise, and about the specific kind of variations and noise in these signals.
Program
Engage Grants Program
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
395931-2009
Name nom
Bengio, Yoshua
Department département
Informatique et recherche opérationnelle
Organization id
63
Institution établissement
Université de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2009
Award amount
25000
Program id
EGP
Program nane en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
1102
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Biomedical engineering
Area of application fr
Génie biomédical
Research subject code
2805
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Learning and inference theories
Research subject fr
Théories de l'apprentissage et l'inférence
Partie
1
Nb partie
1
Application title
Deep Learning for Event Detection in Electrocardiograms
Keyword
NA
Application summary
Biomedical signal processing is a crucial component of the development of improved diagnostic technologies, in particular for cardiovascular diseases, which remain a major cause of mortality. Machine learning algorithms can be used to train computers to detect events of interest in signals, and these automated systems can assist medical professionals in the analysis of large volumes of patient data, or raise alerts while the patient is not under (human) medical observation. Although several algorithms have been proposed, they are still very sensitive to many of the variations present among patients and recording conditions. Reducing the number of false positives and false negatives would be very helpful to make such products more practically useful and medically acceptable. For this purpose, we will explore the advantages that may be brought by new advances following a technical breakthrough in 2006 in the area of neural networks and probabilistic graphical models with so-called deep architectures. The plan is to develop new variants of deep architectures for the analysis of electrocardiogram signals. The main innovations proposed involve specifics of these signals: exploiting information about the underlying variations and noise, and about the specific kind of variations and noise in these signals.