Cognitively-inspired Architecture for Wireless Sensor Networks: A Model Driven Approach for Data Integration in a Traffic Monitoring System

Simple item page
dc.contributor.authorPhalak, Kashmiraen
dc.contributor.committeechairMarathe, Madhav Vishnuen
dc.contributor.committeememberBarrett, Christopher L.en
dc.contributor.committeememberBisset, Keithen
dc.contributor.committeememberRibbens, Calvin J.en
dc.contributor.departmentComputer Scienceen
dc.date.accessioned2014-03-14T20:40:19Zen
dc.date.adate2006-09-08en
dc.date.available2014-03-14T20:40:19Zen
dc.date.issued2006-06-08en
dc.date.rdate2007-09-08en
dc.date.sdate2006-06-21en
dc.description.abstractWe describe CoSMo, a Cognitively Inspired Service and Model Architecture for situational awareness and monitoring of vehicular traffic in urban transportation systems using a network of wireless sensors. The system architecture combines (i) a cognitively inspired internal representation for analyzing and answering queries concerning the observed system and (ii) a service oriented architecture that facilitates interaction among individual modules, of the internal representation, the observed system and the user. The cognitively inspired model architecture allows effective deductive as well as inductive reasoning by combining simulation based dynamic models for planning with traditional relational databases for knowledge and data representation. On the other hand the service oriented design of interaction allows one to build flexible, extensible and scalable systems that can be deployed in practical settings. To illustrate our concepts and the novel features of our architecture, we have recently completed a prototype implementation of CoSMo. The prototype illustrates advantages of our approach over other traditional approaches for designing scalable software for situational awareness in large complex systems. The basic architecture and its prototype implementation are generic and can be applied for monitoring other complex systems. This thesis describes the design of cognitively-inspired model architecture and its corresponding prototype. Two important contributions include the following: • The cognitively-inspired architecture: In contrast to earlier work in model driven architecture, CoSMo contains a number of cognitively inspired features, including perception, memory and learning. Apart from illustrating interesting trade-offs between computational cost (e.g. access time, memory), and correctness available to a user, it also allows users specified deductive and inductive queries. • Distributed Data Integration and Fusion: In keeping with the cognitively-inspired model-driven approach, the system allows for an efficient data fusion from heterogeneous sensors, simulation based dynamic models and databases that are continually updated with real world and simulated data. It is capable of supporting a rich class of queries.en
dc.description.degreeMaster of Scienceen
dc.identifier.otheretd-06212006-144137en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-06212006-144137/en
dc.identifier.urihttp://hdl.handle.net/10919/33675en
dc.publisherVirginia Techen
dc.relation.haspartKashmira-ETD1.pdfen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectdata integrationen
dc.subjectcognitiveen
dc.subjectmodel drivenen
dc.subjectwireless sensor networksen
dc.subjectmiddlewareen
dc.subjectservice-orienteden
dc.titleCognitively-inspired Architecture for Wireless Sensor Networks: A Model Driven Approach for Data Integration in a Traffic Monitoring Systemen
dc.typeThesisen
thesis.degree.disciplineComputer Scienceen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Kashmira-ETD1.pdf
Size:
1.3 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses