<mets:mets OBJID="eprint_32618" LABEL="Eprints Item" xsi:schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd" xmlns:mets="http://www.loc.gov/METS/" xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><mets:metsHdr CREATEDATE="2026-09-14T18:38:48Z"><mets:agent ROLE="CUSTODIAN" TYPE="ORGANIZATION"><mets:name>EPrints Universitas Amikom Yogyakarta</mets:name></mets:agent></mets:metsHdr><mets:dmdSec ID="DMD_eprint_32618_mods"><mets:mdWrap MDTYPE="MODS"><mets:xmlData><mods:titleInfo><mods:title>SEGMENTASI CITRA SPEKTROGRAM SPEKTRUM &#13;
FREKUENSI RADIO MENGGUNAKAN ATTENTION U-NET</mods:title></mods:titleInfo><mods:name type="personal"><mods:namePart type="given">Andreo Yustiantoro</mods:namePart><mods:namePart type="family">Anjaya</mods:namePart><mods:role><mods:roleTerm type="text">author</mods:roleTerm></mods:role></mods:name><mods:abstract>Segmentasi Citra Spektrogram Spektrum Frekuensi Radio Menggunakan&#13;
Attention U-Net. Penelitian ini bertujuan mengembangkan model segmentasi&#13;
berbasis Attention U-Net untuk mendeteksi dan melokalisasi area sinyal pada citra&#13;
spektrogram hasil pemantauan spektrum frekuensi radio serta menguji efektivitas&#13;
strategi pelatihan pretraining-finetuning. Penelitian dibatasi pada citra spektrogram&#13;
dari empat pita frekuensi dengan morfologi sinyal beragam, mulai dari sinyal&#13;
narrowband tipis 1–3 piksel hingga sinyal lebar. Model utama yang dievaluasi&#13;
adalah Attention U-Net yang dilatih pada dataset riil dan Attention U-Net dengan&#13;
strategi pretraining pada dataset sintetis yang dilanjutkan fine-tuning pada dataset&#13;
riil. Model U-Net, SRNet, dan PRMNet digunakan sebagai pembanding. Evaluasi&#13;
dilakukan pada level segmentasi menggunakan IoU, Dice, Precision, dan Recall,&#13;
serta pada level lokalisasi bounding box hasil post-processing mask fill-all. Hasil&#13;
penelitian menunjukkan bahwa Attention U-Net yang dilatih pada dataset riil&#13;
memperoleh IoU 0,7971, Dice 0,8826, Precision 0,8894, dan Recall 0,8864.&#13;
Attention U-Net dengan strategi pretraining–fine-tuning memberikan hasil terbaik&#13;
dengan IoU 0,8046, Dice 0,8877, Precision 0,8899, dan Recall 0,8958. Pada&#13;
evaluasi bounding box, model ini memperoleh F1-score 0,7657, Recall 0,7362, dan&#13;
mIoU 0,5799. Penelitian menyimpulkan bahwa Attention U-Net mampu mendeteksi&#13;
dan melokalisasi area sinyal lintas morfologi pada tingkat piksel, dan strategi&#13;
pretraining–fine-tuning efektif meningkatkan kemampuan generalisasi model pada&#13;
kondisi pemantauan yang heterogen.</mods:abstract><mods:classification authority="lcc">000 Ilmu komputer, informasi dan pekerjaan umum</mods:classification><mods:classification authority="lcc">600 Teknologi</mods:classification><mods:originInfo><mods:dateIssued encoding="iso8061">2026-06-03</mods:dateIssued></mods:originInfo><mods:originInfo><mods:publisher>Universitas AMIKOM Yogyakarta;PJJ Magister Informatika</mods:publisher></mods:originInfo><mods:genre>Thesis</mods:genre></mets:xmlData></mets:mdWrap></mets:dmdSec><mets:amdSec ID="TMD_eprint_32618"><mets:rightsMD ID="rights_eprint_32618_mods"><mets:mdWrap MDTYPE="MODS"><mets:xmlData><mods:useAndReproduction>
<p xmlns="http://www.w3.org/1999/xhtml"><strong>For work being deposited by its own author:</strong> 
In self-archiving this collection of files and associated bibliographic 
metadata, I grant EPrints Universitas Amikom Yogyakarta the right to store 
them and to make them permanently available publicly for free on-line. 
I declare that this material is my own intellectual property and I 
understand that EPrints Universitas Amikom Yogyakarta does not assume any 
responsibility if there is any breach of copyright in distributing these 
files or metadata. (All authors are urged to prominently assert their 
copyright on the title page of their work.)</p>

<p xmlns="http://www.w3.org/1999/xhtml"><strong>For work being deposited by someone other than its 
author:</strong> I hereby declare that the collection of files and 
associated bibliographic metadata that I am archiving at 
EPrints Universitas Amikom Yogyakarta) is in the public domain. If this is 
not the case, I accept full responsibility for any breach of copyright 
that distributing these files or metadata may entail.</p>

<p xmlns="http://www.w3.org/1999/xhtml">Clicking on the deposit button indicates your agreement to these 
terms.</p>
    </mods:useAndReproduction></mets:xmlData></mets:mdWrap></mets:rightsMD></mets:amdSec><mets:fileSec><mets:fileGrp USE="reference"><mets:file ID="eprint_32618_325851_1" SIZE="5607116" OWNERID="https://eprints.amikom.ac.id/id/eprint/32618/1/23.55.2523%20-%20Andreo%20Yustiantoro%20Anjaya.pdf" MIMETYPE="application/pdf"><mets:FLocat LOCTYPE="URL" xlink:type="simple" xlink:href="https://eprints.amikom.ac.id/id/eprint/32618/1/23.55.2523%20-%20Andreo%20Yustiantoro%20Anjaya.pdf"></mets:FLocat></mets:file></mets:fileGrp></mets:fileSec><mets:structMap><mets:div DMDID="DMD_eprint_32618_mods" ADMID="TMD_eprint_32618"><mets:fptr FILEID="eprint_32618_document_325851_1"></mets:fptr></mets:div></mets:structMap></mets:mets>