InsightInsight
IPIC-Ribbon-Horizontal-2-Small
  • About
    • What We Do
    • Governance
    • Equality, Diversity and Inclusion
  • People
    • Work With Us
    • Senior Leadership
    • Principal Investigators
    • Funded Investigators
    • Research and Operations
  • Research
    • Central Bank PhD Programme
    • Excellence
    • Funding Collaboration
    • MSCA Postdoctoral Fellowships
    • National Projects
    • European Projects
  • Industry
    • Collaborate
    • Insight Brochure
    • Commercialisation
    • Contact
  • Public Engagement
    • Meet the Team
    • Highlights
    • Insight Scholarship
  • News
    • Spotlight on Research
    • Events
    • Newsletter
    • Press Releases
  • Contact
  • About
    • What We Do
    • Governance
    • Equality, Diversity and Inclusion
  • People
    • Work With Us
    • Senior Leadership
    • Principal Investigators
    • Funded Investigators
    • Research and Operations
  • Research
    • Central Bank PhD Programme
    • Excellence
    • Funding Collaboration
    • MSCA Postdoctoral Fellowships
    • National Projects
    • European Projects
  • Industry
    • Collaborate
    • Insight Brochure
    • Commercialisation
    • Contact
  • Public Engagement
    • Meet the Team
    • Highlights
    • Insight Scholarship
  • News
    • Spotlight on Research
    • Events
    • Newsletter
    • Press Releases
  • Contact

Edge AI for Anomaly Detection based on Hilbert Space Transformations

Insight>Projects>Edge AI for Anomaly Detection based on Hilbert Space Transformations

Funding Programme or Company Name:

Commercialisation Fund

Funding Body:

Enterprise Ireland – Commercialisation Award

Description:

Background This proposed commercialisation project aims to create a new spin-out company that will develop a library of algorithms, i.e. software libraries, that can be used by application developers of IoT technologies to solve the problem of effective, low power anomaly detection on the edge devices themselves without resort to central server processing. This set of algorithms is derived from innovations in new statistical approximations for distribution estimation through the use of Reproducing Kernel Hilbert spaces and Bayesian optimisation. Problem / Opportunity to be Addressed: The problem of low power anomaly detection is experienced by users of IoT technologies, especially for example users of IoT technologies in asset tracking and security applications where important alert features based on abnormal events are implemented either through uploading of data back to central servers for processing where the underlying IoT technologies support the data bandwidth required or through simplified anomaly detection algorithms tuned for high false positive rates supplemented with high supervisory burden human interventions.

Insight Contact:

Tomas Ward

Application Domain:

Connected Health

Research Group:

Personal Sensing

Associated Theme for Application Domain:

Connected Health-Connecting Health & Life Sciences

Connected Health-Chronic Disease Management & Rehabilitation

Involved Institution:

Dublin City University (DCU

Insight_host_partners_funder
Ireland's European Structural and Investment Funds Programme 2014-2022 logo
European Union European Regional Development Fund logo
  • Privacy Statement
  • Copyright Statement
  • Data Protection Notice
  • Accessibility Statement