Fajar Ramadhan, . (2026) RANCANG BANGUN APLIKASI PENDETEKSI DEEPFAKE DENGAN DUAL SCALE LARGE RECEPTIVE FIELD NETWORK DAN ADAPTIVE GABOR FILTERS. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (213kB) |
|
Text
AWAL.pdf Download (665kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (255kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (692kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (961kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (889kB) |
|
Text
BAB V.pdf Download (243kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (220kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (176kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (14MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (429kB) |
Abstract
The spread of synthetic media-based misinformation, particularly Deepfakes on TikTok, has emerged as a significant threat and a real issue in society. Based on user research, the younger demographic specifically requires a practical solution to mitigate this threat. Therefore, this research aims to design and develop a Mobile-based Deepfake detection application tailored to user needs, specifically offering fast prediction capabilities, a lightweight application size, result-sharing functionality, and achieving a high level of satisfaction during user testing. The technical solution implemented involves the Dual Scale Large Receptive Field Network with Adaptive Gabor filters (DSLRFN AGFs) architecture, which is specifically optimized for efficient static image prediction, alongside the utilization of Flutter plugins to support sharing functionalities across various social media platforms. Based on the evaluation results, the integrated detection model is capable of completing image inference in under 1 second, with an biggest application size is 45.88 MB. During the final evaluation phase using User Acceptance Testing (UAT), the application consistently achieved the "Satisfied" category across all measurement scales. In conclusion, this research has successfully developed a deepfake detection application that effectively addresses user problems and needs. This is evidenced by the system's high usability and optimal computational efficiency.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2210511097] [Pembimbing 1: Musthofa Galih Pradana] [Pembimbing 2: Radinal Setyadinsa] [Penguji 1: Didit Widiyanto] [Penguji 2: Nurul Afifah Arifuddin] |
| Uncontrolled Keywords: | Deepfake, TikTok, DSLRFN AGFs, Mobile Application |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | FAJAR RAMADHAN |
| Date Deposited: | 04 Sep 2026 07:51 |
| Last Modified: | 04 Sep 2026 07:51 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51516 |
Actions (login required)
 |
View Item |