Grant: Discovery Grants Program - Individual
University of New Brunswick
$15,000.00
Data interaction models for predictive system in pervasive computing environment
FY 2014-15
Summary
Pervasive computing is an application-driven field which is slowly proliferating into our everyday life. Pervasive systems are complex due to the multidisciplinary nature of the diverse set of applications and lack of standard definitions, algorithms and architectures. Data is collected in various forms over short and long term period from a number of devices, often with wireless and mobile capabilities. The data interaction among these systems requires prudent iterative approach. Besides, most pervasive applications are still in a nascent stage and exist mostly in labs or in specialized environments or in the form of single isolated applications. Hence, research is crucial as these systems mature to address common data interaction models to achieve efficient intelligent pervasive systems. A lot more work is needed before wireless networking can enable configuration-free data interaction between alien devices in pervasive applications. The goal here is to address the challenges in data collection, context aware data association, data aggregation, data integration, data management, and privacy protection in pervasive systems. Data integration models are needed that allow easy interaction of data between the myriad system components so that critical application specific predictions can be obtained quickly. Use of information-flow control models are also required to alleviate privacy concerns. Research will be conducted to study and develop novel data integration models to improve the prediction performance in pervasive environments in the two main application domains that I am currently working, namely, the emergency response system and the non-intrusive patient monitoring system. The performance will be studied in terms of resource saving, improved intelligence, response time, and false predictions. The expected findings will be intelligent predictive models developed from efficient data interaction models for mission-critical applications.
Program
Discovery Grants Program - Individual
Recipient
Location
New Brunswick, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
262759-2010
Name nom
LightThompson, JanetV
Department département
Computer Science and Applied Statistics - Saint John
Organization id
75
Institution établissement
University of New Brunswick
Province en
New Brunswick
Province fr
Nouveau-Brunswick
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2010
Award amount
15000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
804
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Communication systems and services (planning, organization, services)
Area of application fr
Systèmes et services de communications (planification, organisation et services)
Research subject code
2508
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Communications networks
Research subject fr
Réseaux de télécommunications
Partie
5
Nb partie
5
Application title
Data interaction models for predictive system in pervasive computing environment
Keyword
NSERC
Application summary
Pervasive computing is an application-driven field which is slowly proliferating into our everyday life. Pervasive systems are complex due to the multidisciplinary nature of the diverse set of applications and lack of standard definitions, algorithms and architectures. Data is collected in various forms over short and long term period from a number of devices, often with wireless and mobile capabilities. The data interaction among these systems requires prudent iterative approach. Besides, most pervasive applications are still in a nascent stage and exist mostly in labs or in specialized environments or in the form of single isolated applications. Hence, research is crucial as these systems mature to address common data interaction models to achieve efficient intelligent pervasive systems. A lot more work is needed before wireless networking can enable configuration-free data interaction between alien devices in pervasive applications. The goal here is to address the challenges in data collection, context aware data association, data aggregation, data integration, data management, and privacy protection in pervasive systems. Data integration models are needed that allow easy interaction of data between the myriad system components so that critical application specific predictions can be obtained quickly. Use of information-flow control models are also required to alleviate privacy concerns. Research will be conducted to study and develop novel data integration models to improve the prediction performance in pervasive environments in the two main application domains that I am currently working, namely, the emergency response system and the non-intrusive patient monitoring system. The performance will be studied in terms of resource saving, improved intelligence, response time, and false predictions. The expected findings will be intelligent predictive models developed from efficient data interaction models for mission-critical applications.