?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=PEMANFAATAN+DEEP+LEARNING+MENGGUNAKAN+ARSITEKTUR%0D%0AGOOGLENET+DAN+INCEPTION-V3+UNTUK+PENGEMBANGAN%0D%0ASISTEM+PRESENSI+BERBASIS+FACE+RECOGNITION&rft.creator=ARIB+%2C+YUSRON+HAMDANI&rft.subject=004+Pemrosesan+data+dan+ilmu+komputer&rft.subject=500+ilmu+pengetahuan+alam+dan+matematika&rft.description=Dalam+dekade+terakhir%2C+terjadi+kemajuan+yang+signifikan+dalam+teknologi%0D%0Apengenalan+biometrik+yaitu+teknologi+face+recognition+yang+menjadi+salah+satu%0D%0Aaspek+yang+paling+menarik+perhatian+dimana+teknologi+ini+mampu+untuk%0D%0Amengidentifikasi+individu+berdasarkan+ciri+wajah.+Meskipun+teknologi+face%0D%0Arecognition+telah+diadopsi+oleh+sejumlah+organisasi+sebagai+solusi+untuk%0D%0Amanajemen+kehadiran%2C+beberapa+tantangan+penting+masih+ada+seperti+variasi+kondisi%0D%0Apencahayaan%2C+variasi+ekspresi+wajah%2C+serta+perubahan+sudut+pandang+yang+dapat%0D%0Amempengaruhi+akurasi+sistem+secara+signifikan.+Oleh+karena+itu%2C+peningkatan%0D%0Aakurasi+dan+ketahanan+terhadap+perubahan+lingkungan+merupakan+kunci+dalam%0D%0Ameningkatkan+efektivitas+teknologi+face+recognition+dalam+manajemen+kehadiran.%0D%0APenelitian+ini+bertujuan+untuk+mengatasi+tantangan-tantangan+yang+masih+ada%0D%0Adalam+manajemen+kehadiran+dengan+menggabungkan+teknologi+face+recognition%0D%0Aberbasis+deep+learning+dengan+menggunakan+2+perbandingan+arsitektur+GoogleNet%0D%0Adan+Inception-V3+dalam+rangka+pengembangan+sistem+presensi+berbasis%0D%0Apengenalan+wajah.+Studi+ini+menggunakan+dataset+yang+dilakukan+augmentasi%2C%0D%0Adataset+diaugmentasi+menjadi+4+bagian%2C+dan+akan+dibedakan+menjadi+3+variasi%0D%0Ahyperparameter%2C+dengan+total+iterasi+12+pelatihan.+Hasil+yang+didapatkan%0D%0Amenunjukkan+bahwa+arsitektur+Inception-V3+mengungguli+performa+arsitektur%0D%0AGoogleNet+dalam+11+dari+12+percobaan.+Dengan+hasil+performa+Inception-V3%0D%0Amencapai+akurasi+maksimum+sebesar+88%25%2C+dibandingkan+dengan+performa+akurasi%0D%0Amaksimum+pada+model+GoogleNet+sebesar+60%25.+Temuan+ini+menunjukkan+bahwa%0D%0Aarsitektur+Inception-V3+lebih+cocok+untuk+pengenalan+wajah+dalam+sistem%0D%0Akehadiran%2C+karena+performa+akurasi+dan+konsistensi+hasil+pelatihan+yang+unggul.%0D%0AStudi+ini+memberikan+wawasan+yang+signifikan+mengenai+pemilihan+arsitektur%0D%0Apembelajaran+mendalam+yang+optimal+untuk+aplikasi+berbasis+pengenalan+wajah.%0D%0AKata+kunci%3A+Deep+Learning%2C+GoogleNet%2C+Inception-V3%2C+Pengenalan+Wajah%2C+Sistem%0D%0APresensi%2C+Perbandingan+Model%2C+Augmentasi+Datasets%2C+Machine+Learning.%0D%0A%0D%0AABSTRACT%0D%0A%0D%0AUTILIZATION+OF+DEEP+LEARNING+USING+GOOGLENET%0D%0AARCHITECTURE+AND+INCEPTION-V3+FOR+DEVELOPMENT+OF+A%0D%0AFACE+RECOGNITION+BASED+PRESENCE+SYSTEM%0D%0A%0D%0ABy%0D%0A%0D%0AARIB+YUSRON+HAMDANI%0D%0A%0D%0AIn+the+last+decade%2C+there+has+been+significant+progress+in+biometric+recognition%0D%0Atechnology%2C+namely+facial+recognition+technology%2C+which+has+become+one+of+the%0D%0Aaspects+that+has+attracted+the+most+attention%2C+where+this+technology+is+able+to+identify%0D%0Aindividuals+based+on+facial+characteristics.+Although+facial+recognition+technology%0D%0Ahas+been+adopted+by+a+number+of+organizations+as+a+solution+for+attendance%0D%0Amanagement%2C+several+important+challenges+still+exist+such+as+variations+in+lighting%0D%0Aconditions%2C+variations+in+facial+expressions%2C+and+changes+in+viewing+angles+that+can%0D%0Asignificantly+affect+system+accuracy.+Therefore%2C+increasing+accuracy+and+resilience%0D%0Ato+environmental+changes+is+key+to+increasing+the+effectiveness+of+facial+recognition%0D%0Atechnology+in+attendance+management.+This+research+aims+to+overcome+the%0D%0A%0D%0Achallenges+that+still+exist+in+attendance+management+by+combining+deep+learning-%0D%0Abased+facial+recognition+technology+using+2+comparisons+of+the+GoogleNet+and%0D%0A%0D%0AInception-V3+architectures+in+the+context+of+developing+a+facial+recognition-based%0D%0Aattendance+system.+This+study+uses+a+dataset+that+has+been+augmented%2C+the+dataset%0D%0Ais+augmented+into+4+parts%2C+and+will+be+divided+into+3+hyperparameter+variations%2C%0D%0A%0D%0Awith+a+total+of+12+training+iterations.+The+results+obtained+show+that+the+Inception-%0D%0AV3+architecture+outperforms+the+GoogleNet+architecture+in+11+out+of+12%0D%0A%0D%0Aexperiments.+With+the+performance+results%2C+Inception-V3+reaches+a+maximum%0D%0Aaccuracy+of+88%25%2C+compared+to+the+maximum+accuracy+performance+on+the%0D%0AGoogleNet+model+of+60%25.+These+findings+indicate+that+the+Inception-V3%0D%0Aarchitecture+is+more+suitable+for+face+recognition+in+presence+systems%2C+due+to+its%0D%0Asuperior+accuracy+performance+and+consistency+of+training+results.+This+study%0D%0Aprovides+significant+insights+into+the+selection+of+optimal+deep+learning%0D%0Aarchitectures+for+facial+recognition-based+applications.%0D%0AKeywords%3A+Deep+Learning%2C+GoogleNet%2C+Inception-V3%2C+Face+Recognition%2C+Presence%0D%0ASystems%2C+Model+Comparison%2C+Datasets+Augmentation%2C+Machine+Learning.&rft.publisher=FAKULTAS+MATEMATIKA+DAN+ILMU+PENGETAHUAN+ALAM&rft.date=2024-06-10&rft.type=Skripsi&rft.type=NonPeerReviewed&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F87018%2F1%2F%255BDraft%255D%2520Abstrak%2520-%25202017051078%2520-%2520Arib%2520Yusron%2520Hamdani.pdf&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F87018%2F2%2F%255BDraft%255D%2520Skripsi%2520-%25202017051078%2520-%2520Full%2520-%2520Arib%2520Yusron%2520Hamdani.pdf&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F87018%2F3%2F%255BDraft%255D%2520Skripsi%2520-%25202017051078%2520-%2520Tanpa%2520Pembahasan%2520-%2520Arib%2520Yusron%2520Hamdani.pdf&rft.identifier=++ARIB+%2C+YUSRON+HAMDANI++(2024)+PEMANFAATAN+DEEP+LEARNING+MENGGUNAKAN+ARSITEKTUR+GOOGLENET+DAN+INCEPTION-V3+UNTUK+PENGEMBANGAN+SISTEM+PRESENSI+BERBASIS+FACE+RECOGNITION.++FAKULTAS+MATEMATIKA+DAN+ILMU+PENGETAHUAN+ALAM%2C+UNIVERSITAS+LAMPUNG.+++++&rft.relation=http%3A%2F%2Fdigilib.unila.ac.id%2F87018%2F