EFFICIENTNET-B3 PADA METODE CONVOLUTIONAL NEURAL NETWORK UNTUK KLASIFIKASI CITRA PENYAKIT KULIT

PUTRA, FASCAL HARYA and Utami, Alvi Syahrini (2025) EFFICIENTNET-B3 PADA METODE CONVOLUTIONAL NEURAL NETWORK UNTUK KLASIFIKASI CITRA PENYAKIT KULIT. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021282126116_cover.jpg] Image
RAMA_55201_09021282126116_cover.jpg - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (4MB)
[thumbnail of RAMA_55201_09021282126116.pdf] Text
RAMA_55201_09021282126116.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_TURNITIN.pdf] Text
RAMA_55201_09021282126116_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (5MB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_01_front_ref.pdf] Text
RAMA_55201_09021282126116_0022127804_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[thumbnail of RAMA_55201_09021282126116_0022127804_02.pdf] Text
RAMA_55201_09021282126116_0022127804_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (537kB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_03.pdf] Text
RAMA_55201_09021282126116_0022127804_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (434kB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_04.pdf] Text
RAMA_55201_09021282126116_0022127804_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (670kB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_05.pdf] Text
RAMA_55201_09021282126116_0022127804_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (692kB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_06.pdf] Text
RAMA_55201_09021282126116_0022127804_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (248kB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_07_ref.pdf] Text
RAMA_55201_09021282126116_0022127804_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (221kB) | Request a copy
[thumbnail of RAMA_55201_09021282126116_0022127804_08_lamp.pdf] Text
RAMA_55201_09021282126116_0022127804_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (266kB) | Request a copy

Abstract

Early and accurate classification of skin diseases is critical given the high global prevalence WHO estimates nearly 900 million cases worldwide, with dermatitis as the most common and the uneven distribution of dermatological expertise. EfficientNet-B3 within a Convolutional Neural Network (CNN) framework was therefore investigated for multiclass classification of skin disease images. A secondary dataset of 5,000 JPG images sourced from two public Kaggle repositories and comprising five categories (eczema, malignant, melanoma, psoriasis, and seborrheic dermatitis) was preprocessed (resized to 256×256 pixels, normalized, and augmented via rotation, flip, and zoom). Three train-validation-test splits (70:15:15, 60:20:20, and 80:10:10) were evaluated under identical training conditions using sparse categorical cross-entropy loss and the Adam optimizer (learning rate 0.001) for up to 50 epochs with early stopping. Model performance was measured via accuracy, precision, recall, and F1-score on both validation and independent test sets. The 70:15:15 split yielded the most balanced results, with validation accuracy of 93.05% and test accuracy of 91.60% (precision, recall, and F1-score all 91.60%). Although the 80:10:10 split achieved the highest test accuracy (92.00%), its smaller test set introduced potential bias. Confusion matrix analysis highlighted robust inter-class classification with minor confusion among visually similar conditions. Overall, the EfficientNet-B3–based CNN demonstrated reliable feature extraction and consistent classification across five skin disease categories, supporting its potential as a decision-support tool in dermatological practice.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Klasifikasi Penyakit Kulit, EfficientNet-B3, Convolutional Neural Network, Deep Learning, Analisis Citra Medis.
Subjects: R Medicine > RZ Other systems of medicine > RZ201-999 Other systems of medicine
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Fascal Harya Putra
Date Deposited: 30 Jun 2025 06:00
Last Modified: 30 Jun 2025 06:00
URI: http://repository.unsri.ac.id/id/eprint/176140

Actions (login required)

View Item View Item