Grant: Engage Grants Program
University of Victoria
$25,000.00
Privacy-protecting cloud processing for medical EEG data sets
FY 2012-13
Summary
EEG data collection typically involves 16 to 128 channels of information---where each channel corresponds to
an EEG sensor placed on a patient's scalp. Currently, ABV Sciences' EEG data cleaning process works
independently across each data channel. ABV Sciences anticipates that the growth in demand over the near
term will require it to process, at peak loads, in the low thousands of mutli-channel patient EEG assessments
per hour, with the goal of sub-minute processing times per-patient assessment. One key challenge is to be able
to provide this kind of functionality, without compromising patient privacy.
Simple solutions such as encrypting EEG data cannot be used to ensure patient privacy as the data cleaning
algorithms must work directly on the raw data. Furthermore, recent studies show that achieving scalability by
parallelization via standard cloud deployments is not trivial due to issues related to I/O, cache interference, and
performance isolation. Purely private cloud platforms also cannot be used as these are not cost-competitive for
ABV Sciences against commercial clouds such as Amazon EC2, Microsoft Azure, etc.
We plan to exploit the fact that individual single channel EEG data signals, when analyzed in isolation, provide
minimal (to nearly zero) private information. This can be leveraged in a novel manner to enable a
privacy-preserving scalable cloud-deployment which addresses ABV Sciences composite needs.
Program
Engage Grants Program
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
446237-2012
Name nom
Coady, Yvonne
Department département
Computer Science
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
25000
Program id
EGP
Program name 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
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
1901
Research subject group en
Biomedical engineering
Research subject group fr
Génie biomédical
Research subject en
Biomedical technology
Research subject fr
Technologie biomédicale
Partie
1
Nb partie
1
Application title
Privacy-protecting cloud processing for medical EEG data sets
Keyword
NSERC
Application summary
EEG data collection typically involves 16 to 128 channels of information---where each channel corresponds to
an EEG sensor placed on a patient's scalp. Currently, ABV Sciences' EEG data cleaning process works
independently across each data channel. ABV Sciences anticipates that the growth in demand over the near
term will require it to process, at peak loads, in the low thousands of mutli-channel patient EEG assessments
per hour, with the goal of sub-minute processing times per-patient assessment. One key challenge is to be able
to provide this kind of functionality, without compromising patient privacy.
Simple solutions such as encrypting EEG data cannot be used to ensure patient privacy as the data cleaning
algorithms must work directly on the raw data. Furthermore, recent studies show that achieving scalability by
parallelization via standard cloud deployments is not trivial due to issues related to I/O, cache interference, and
performance isolation. Purely private cloud platforms also cannot be used as these are not cost-competitive for
ABV Sciences against commercial clouds such as Amazon EC2, Microsoft Azure, etc.
We plan to exploit the fact that individual single channel EEG data signals, when analyzed in isolation, provide
minimal (to nearly zero) private information. This can be leveraged in a novel manner to enable a
privacy-preserving scalable cloud-deployment which addresses ABV Sciences composite needs.