Masters Theses

Author

Kopal Nema

Keywords and Phrases

Humanitarian de-mining; Signal processing; K-Means cluster; Nearest neighbor algorithm

Abstract

"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.

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Beetner, Daryl G.
Moss, Randy Hays, 1953-

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Publisher

University of Missouri--Rolla

Publication Date

Summer 2003

Pagination

viii, 43 pages

Note about bibliography

Includes bibliographical references (page 42).

Rights

© 2003 Kopal Nema, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Subject Headings

Mines (Military explosives) -- Detection
Water jets
Signal processing
Nearest neighbor analysis (Statistics)

Thesis Number

T 8214

Print OCLC #

53188461

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

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.

Share

 
COinS