Keywords and Phrases
Humanitarian de-mining; Signal processing; K-Means cluster; Nearest neighbor algorithm
"The research discussed in this thesis focuses on the development of signal analysis techniques for evaluating sound signals acquired from water jet pulses to discriminate landmines from harmless objects, including the soil in isolation. For the sound signals acquired, time domain pre-processing operations were investigated. Weighted density distribution (WDD) function-based features were examined for windowed time domain sound signals for object/no-object and mine/harmless object discrimination. These techniques were developed and evaluated using data sets collected at the UMR Rock Mechanics and Explosives Research Center. These methods were applied to detect real landmines from soil/harmless objects using water jet technology at a government test facility. Receiver operating characteristics curves are presented to show the discrimination capability of the WDD features"--Abstract, page iii.
Stanley, R. Joe
Beetner, Daryl G.
Moss, Randy Hays, 1953-
Electrical and Computer Engineering
M.S. in Electrical Engineering
University of Missouri--Rolla
viii, 43 pages
© 2003 Kopal Nema, All rights reserved.
Thesis - Restricted Access
Mines (Military explosives) -- Detection
Nearest neighbor analysis (Statistics)
Print OCLC #
Link to Catalog Record
Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.http://merlin.lib.umsystem.edu/record=b5002399~S5
Nema, Kopal, "The application of time domain approaches to sound signal analysis from water jet technology for landmine discrimination" (2003). Masters Theses. 2303.
Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.