Grant: Alliance Grants
University of Calgary
$50,000.00
Tiny, Robust, and Self-Supervised Artificial Intelligence for Low-Power Sensing in 6G IoT Applications
FY 2023-24
Summary
This project aims to address key challenges hindering the adoption of Artificial Intelligence (AI) in real-world Internet of Things (IoT) applications. Despite recent AI advancements, limitations persist in terms of processing power, data requirements, and training inefficiencies of AI on IoT devices. To overcome these challenges, this project will focus on developing lightweight AI models that can efficiently operate on resource-constrained IoT devices. The research will also explore methods to create generalizable AI models without relying on large data samples, by utilizing generative AI and data augmentation techniques. Additionally, the project will investigate innovative approaches to enable self-supervised training of AI models to run directly on IoT devices, eliminating the in-efficiencies of data collection and sample labeling.The developed lightweight and data-centric AI techniques will form the foundation for an integrated AI-IoT platform for resource-constrained devices. This platform will enable intelligent sensing applications to run efficiently in industrial plant sensors, drones, and other IoT sensors operating in remote locations. Moving AI processing closer to the data where it is sensed will reduce latency significantly and ensure the privacy of the data. This is especially pertinent to embed intelligence and automation in Canada's key sectors of smart agriculture, energy, and environmental monitoring where intelligent sensing can offer significant societal and economic benefits. For instance, drones running robust and energy-efficient AI models for precision agriculture and wildfire monitoring will be able to cover vast regions in a reliable and scalable manner. By innovating in this growing market of resource and data-constrained AI, Canada can gain a leadership position and competitive advantage in this market and lead globally.
Program
Alliance Grants
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
590390-2023
Name nom
Abou-Zeid, Hatem H
Department département
Schulich School of Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
50000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
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
2710
Research subject group en
Information technology
Research subject group fr
Information systems design
Research subject en
Technologie de l'information
Research subject fr
Conception de systèmes d'information
Application title
Tiny, Robust, and Self-Supervised Artificial Intelligence for Low-Power Sensing in 6G IoT Applications
Keyword
artificial intelligence; deep learning; edge networks; industrial sensing and applications; internet of things; model compression; self-supervised learning; unsupervised learning
Application summary
This project aims to address key challenges hindering the adoption of Artificial Intelligence (AI) in real-world Internet of Things (IoT) applications. Despite recent AI advancements, limitations persist in terms of processing power, data requirements, and training inefficiencies of AI on IoT devices. To overcome these challenges, this project will focus on developing lightweight AI models that can efficiently operate on resource-constrained IoT devices. The research will also explore methods to create generalizable AI models without relying on large data samples, by utilizing generative AI and data augmentation techniques. Additionally, the project will investigate innovative approaches to enable self-supervised training of AI models to run directly on IoT devices, eliminating the in-efficiencies of data collection and sample labeling.The developed lightweight and data-centric AI techniques will form the foundation for an integrated AI-IoT platform for resource-constrained devices. This platform will enable intelligent sensing applications to run efficiently in industrial plant sensors, drones, and other IoT sensors operating in remote locations. Moving AI processing closer to the data where it is sensed will reduce latency significantly and ensure the privacy of the data. This is especially pertinent to embed intelligence and automation in Canada's key sectors of smart agriculture, energy, and environmental monitoring where intelligent sensing can offer significant societal and economic benefits. For instance, drones running robust and energy-efficient AI models for precision agriculture and wildfire monitoring will be able to cover vast regions in a reliable and scalable manner. By innovating in this growing market of resource and data-constrained AI, Canada can gain a leadership position and competitive advantage in this market and lead globally.