Grant: Research Tools and Instruments
University of Calgary
$139,110.00
Multi-sensor Fusion and Signal Processing for Massive Amount of Data
FY 2017-18
Summary
High resolution sensors are utilized in a wide variety of applications such as environmental monitoring, healthcare, industrial control, automotive systems and smart mobile devices. As the availability of comprehensive data pools increase rapidly, there is a growing trend in analyzing data acquired from various sources to extract useful information. Exploiting the availability of massive heterogeneous data sets to gain better insight on a wide range of problems is one of our current research goals. However, real data comes with a need for computational preprocessing, frequent access, data storage, and security concerns. Alongside algorithmic challenges, the general lack of powerful computational frameworks and a suitable means for data storage and sharing have decelerated our ongoing projects and deter us from implementing new ideas. We request funding for a customized server with high-end multi-GPU capabilities, and large memory capacity that will aid us in data and image processing, as well as train deep learning models efficiently. We seek solutions that are scalable to big data and multiple heterogeneous sources of information. This would empower the lab to develop our algorithms for signal processing and sensor fusion for applications such as continuous sensing of pipelines, bioinformatics and smart cities. Through these projects described, we hope to foster various partnerships across multiple disciplinary research teams and industrial supporters in the energy sector, defence, medicine. We are hoping to contribute advanced algorithms to these fields and apply these approaches to practical applications and real data. A gap exists between practical implementations and theory, as many theoretical algorithms may not be tested on large data sets.These projects would enable the training of HQP in high-demand fields: data analytics, image processing, and deep learning. HQP would also gain exposure to real-world problems, and marketable skills in high performance computing technologies.
Program
Research Tools and Instruments
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RTI-2018-00150
Name nom
Leung, Henry
Department département
Electrical and Computer Engineering - Electrical and Computer 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
2017
Competition year année de concours
2018
Award amount
139110
Program id
RTI
Program name en
Research Tools and Instruments
Program name fr
Outils et instruments de recherche
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1610
Committee name en
Electrical and Computer Engineering (RTI)
Committee name fr
Génie électrique et infomatique (OIR)
Area of application code
703
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Aerospace
Area of application fr
Aérospatial
Research subject code
2510
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Adaptive, learning and evolutionary systems
Research subject fr
Systèmes d'apprentissage adaptatifs et évolutifs
Partie
1
Nb partie
1
Application title
Multi-sensor Fusion and Signal Processing for Massive Amount of Data
Keyword
NSERC
Application summary
High resolution sensors are utilized in a wide variety of applications such as environmental monitoring, healthcare, industrial control, automotive systems and smart mobile devices. As the availability of comprehensive data pools increase rapidly, there is a growing trend in analyzing data acquired from various sources to extract useful information. Exploiting the availability of massive heterogeneous data sets to gain better insight on a wide range of problems is one of our current research goals. However, real data comes with a need for computational preprocessing, frequent access, data storage, and security concerns. Alongside algorithmic challenges, the general lack of powerful computational frameworks and a suitable means for data storage and sharing have decelerated our ongoing projects and deter us from implementing new ideas. We request funding for a customized server with high-end multi-GPU capabilities, and large memory capacity that will aid us in data and image processing, as well as train deep learning models efficiently. We seek solutions that are scalable to big data and multiple heterogeneous sources of information. This would empower the lab to develop our algorithms for signal processing and sensor fusion for applications such as continuous sensing of pipelines, bioinformatics and smart cities. Through these projects described, we hope to foster various partnerships across multiple disciplinary research teams and industrial supporters in the energy sector, defence, medicine. We are hoping to contribute advanced algorithms to these fields and apply these approaches to practical applications and real data. A gap exists between practical implementations and theory, as many theoretical algorithms may not be tested on large data sets.These projects would enable the training of HQP in high-demand fields: data analytics, image processing, and deep learning. HQP would also gain exposure to real-world problems, and marketable skills in high performance computing technologies.