Adrian Fakhriza Hakim, . (2026) RANCANG BANGUN WEBSITE SINGLE PAGE APPLICATION DETEKSI PENYAKIT ACNE VULGARIS MENGGUNAKAN RESNET-50. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (442kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (489kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (864kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB V.pdf Download (446kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (367kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (145kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (26MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (746kB) |
Abstract
Acne vulgaris is a highly prevalent skin disease in Indonesia that significantly impacts the sufferers' quality of life. The limited access to conventional dermatological services and the lack of public education often lead to misidentification and incorrect early treatment. This study aims to design and develop a Single Page Application (SPA) website-based Acne Vulgaris detection system to accurately classify five common types of acne (Comedones, Papules, Pustules, Nodules, and Cystic) while providing educational treatment recommendations. The inference engine was developed using the ResNet-50 deep learning architecture through a Transfer Learning (Three-Phase Fine-Tuning) approach. The system is integrated into a FastAPI backend server by implementing an advanced computer vision pipeline that combines the overlapping crops algorithm (9 Overlapping Crops), Grad-CAM feature localization, skin color space filtering (HSV), and annotation duplication elimination using Non-Maximum Suppression (NMS). Meanwhile, the client interface (frontend) was built using the React.JS framework. Evaluation on the test dataset proved that the model achieved an overall accuracy of 92.95%. The integration of the localization algorithm effectively eliminated false positive detections and produced accurate bounding boxes. The Black Box testing results showed valid system functionality, and the user satisfaction evaluation (User Acceptance Testing) obtained a "Very Good" category. This confirms that the developed software is not only computationally functional but also interactive, user-centric, and highly reliable as a skin health screening tool.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511050] [Pembimbing 1: Muhammad Adrezo] [Pembimbing 2; I Wayan Rangga Pinastawa] [Penguji 1: Neny Rosmawarni] [Penguji 2: Muhammad Panji Muslim] |
| Uncontrolled Keywords: | Acne Vulgaris, Deep Learning, ResNet-50, Grad-CAM, Single Page Application. |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | ADRIAN FAKHRIZA HAKIM |
| Date Deposited: | 28 Jul 2026 16:06 |
| Last Modified: | 31 Aug 2026 15:49 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51733 |
Actions (login required)
 |
View Item |