Intelligent identification of hazardous materials using sensor networks
Abstract
The purpose of this thesis is to present and advance a new methodology for the incipient detection of hazardous material in the environment. Specifically, this thesis focuses on new methodologies for improving the performance of individual sensors. New methods of assimilating information from a network of diverse sensors are developed. Intelligent tools that have the ability to adapt, such as neural networks and fuzzy inference systems, are brought to bear on both of these aims. Data from Ion Mobility Spectroscopy, Ion Beam Modulation Ion Mobility Spectroscopy and Cylindrical Ion Trap Mass Spectrometry is used and a plan of testing is developed to demonstrate the merits of the proposed methodology. The release of hazardous chemicals into the environment requires quick action to limit the impact of such a release. Of much concern is the purposeful release of chemicals in order to cause harm. Quickly detecting and identifying an unknown threat is pivotal to limiting harm. Because of the large area covered in either a battlefield or an urban environment, a single sensor is not able to detect all of the activity in the area of concern. For this reason, sensor networks are being developed to create a better response plan. There must be a way to process and clearly present an accurate picture of the threat. The constraints presented by the problem of the early on-set detection of hazardous material in the environment inform and shape the proposed methodology and is one of the main motivations for embedding intelligent tools in signal processing and decision making.
Degree
Ph.D.
Advisors
Tsoukalas, Purdue University.
Subject Area
Nuclear physics|Artificial intelligence
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.