A comparison of different approaches to target differentiation with sonar

Simple item page
buir.advisorBarshan, Billur
dc.contributor.authorAyrulu (Erdem), Birsel
dc.date.accessioned2016-01-08T18:01:08Z
dc.date.available2016-01-08T18:01:08Z
dc.date.issued2001
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionAnkara : The Department of Electrical and Electronics Engineering and the Institute of Engineering and Science of Bilkent University, 2001.en_US
dc.descriptionThesis (Ph.D.) -- Bilkent University, 2001.en_US
dc.descriptionIncludes bibliographical references leaves 180-197en_US
dc.description.abstractThis study compares the performances of di erent classication schemes and fusion techniques for target di erentiation and localization of commonly encountered features in indoor robot environments using sonar sensing Di erentiation of such features is of interest for intelligent systems in a variety of applications such as system control based on acoustic signal detection and identication map building navigation obstacle avoidance and target tracking The classication schemes employed include the target di erentiation algorithm developed by Ayrulu and Barshan statistical pattern recognition techniques fuzzy c means clustering algorithm and articial neural networks The fusion techniques used are Dempster Shafer evidential reasoning and di erent voting schemes To solve the consistency problem arising in simple ma jority voting di erent voting schemes including preference ordering and reliability measures are proposed and veried experimentally To improve the performance of neural network classiers di erent input signal representations two di erent training algorithms and both modular and non modular network structures are considered The best classication and localization scheme is found to be the neural network classier trained with the wavelet transform of the sonar signals This method is applied to map building in mobile robot environments Physically di erent sensors such as infrared sensors and structured light systems besides sonar sensors are also considered to improve the performance in target classication and localization.en_US
dc.description.degreePh.D.en_US
dc.description.provenanceMade available in DSpace on 2016-01-08T18:01:08Z (GMT). No. of bitstreams: 1 0000782.pdf: 1993114 bytes, checksum: 69cb0844da2a4970292b13f2419e709c (MD5)en
dc.description.statementofresponsibilityAyrulu (Erdem), Birselen_US
dc.format.extent198 leaves, illustrations+ 1 computer disk (3 1/2 in)en_US
dc.identifier.urihttp://hdl.handle.net/11693/14518
dc.language.isoEnglishen_US
dc.publisherBilkent Universityen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectSonar sensingen_US
dc.subjecttarget di erentiationen_US
dc.subjecttarget localizationen_US
dc.subjectarticial neural networksen_US
dc.subjectlearningen_US
dc.subjectfeature extractionen_US
dc.subjectstatistical pattern recognitionen_US
dc.subjectDempster Shafer evidential reasoningen_US
dc.subjectma jority votingen_US
dc.subjectsensing systemsen_US
dc.subjectacoustic signal processingen_US
dc.subjectmobile robotsen_US
dc.subjectmap buildingen_US
dc.subjectVoronoi diagramen_US
dc.subject.lccQC176.8.A3 A97 2001en_US
dc.subject.lcshAcoustic surface waves.en_US
dc.subject.lcshSignal processing.en_US
dc.subject.lcshMobile robots.en_US
dc.subject.lcshArtificial intelligence.en_US
dc.subject.lcshProbabilities.en_US
dc.subject.lcshMathematical statistics.en_US
dc.titleA comparison of different approaches to target differentiation with sonaren_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0000782.pdf
Size:
1.9 MB
Format:
Adobe Portable Document Format
Download

Collections

Dept. of Electrical and Electronics Engineering - Ph.D. / Sc.D.