Faradila, Putri Wanda Yasmine (2024) KLASIFIKASI PENYAKIT KULIT MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK ARSITEKTUR MOBILENET. Undergraduate thesis, UPN VETERAN JAWA TIMUR.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
20083010005 -cover.pdf Download (1MB) |
|
Text (Bab 1)
20083010005 -bab1.pdf Download (48kB) |
|
Text (Bab 2)
20083010005 -bab2.pdf Restricted to Repository staff only until 30 May 2026. Download (407kB) |
|
Text (Bab 3)
20083010005 -bab3.pdf Restricted to Repository staff only until 30 May 2026. Download (114kB) |
|
Text (Bab 4)
20083010005 -bab4.pdf Restricted to Repository staff only until 30 May 2026. Download (878kB) |
|
Text (Bab 5)
20083010005 -bab5.pdf Download (30kB) |
|
Text (Daftar Pustaka)
20083010005 -daftarpustaka.pdf Download (98kB) |
|
Text (Lampiran)
20083010005 -lampiran.pdf Restricted to Repository staff only Download (517kB) |
Abstract
This research aims to implement the MobileNet architecture in skin disease classification. Skin disease is a serious health problem. The most common skin disease is Basal Cell Carcinoma (65.5), followed by Melanoma (7.9%), Squamous Cell Carcinoma (23%) and other skin diseases. The aim of this research is to prevent early skin disease by automating it using image classification with a deep learning method, namely Convolutional Neural Network. This method is often used because it has a high level of accuracy and has good results in recognizing an object in image recognition. In this research, model testing was carried out with different optimizer scenarios (Adam, SGD, Adagrad) and learning rate. From the results of the tests carried out, it was found that the best trained MobileNet model used the Adam optimizer with a learning rate of 0.0001 at 98%, the SGD optimizer with a learning rate of 0.01 at 99%, the Adagrad optimizer with a learning rate of 0.01 at 98%, the model managed to achieve the highest accuracy compared to other models. This shows that this configuration provides optimal performance in producing accurate predictions on the dataset used.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA76.6 Computer Programming | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Putri Wanda Yasmine Faradila | ||||||||||||
| Date Deposited: | 30 May 2024 08:23 | ||||||||||||
| Last Modified: | 30 May 2024 08:23 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/23556 |
Actions (login required)
 |
View Item |