Klasifikasi Penyakit kulit dengan convolutional neural network = Skin disease classification with convolutional neural network

Chow, Sammy Sena (2023) Klasifikasi Penyakit kulit dengan convolutional neural network = Skin disease classification with convolutional neural network. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (24kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (202kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (216kB) | Preview
Preview	Text (Chapter 1) Chapter 1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (221kB) | Preview
	Text (Chapter 2) Chapter 2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter 3) Chapter 3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (392kB)
	Text (Chapter 4) Chapter 4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter 5) Chapter 5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (112kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (203kB) | Preview
	Text (Appendices) appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)

Abstract

Penyakit kulit merupakan salah satu penyakit yang paling umum Indonesia, namun masih dianggap remeh. Banyak dari penyakit ini tidak ditangani dengan tepat oleh karena berbagai alasan, membuat mereka menjadi penyakit yang lebih serius. Berbagai penelitian telah menunjukkan bahwa convolutional neural network atau CNN dapat mendeteksi dan mengklasifikasikan penyakit kulit namun, tidak ditemukan konfigurasi model yang optimal secara eksplisit. Dalam penelitian ini, selain dari mengklasifikasikan penyakit kulit yaitu atopic dermatitis, herpes, lyme disease, poison ivy, psoriasis dan rosacea, penelitian ini juga akan berusaha menemukan konfigurasi model yang optimal untuk mendeteksi penyakit kulit dengan bereksperimen pada hyperparameter seperti jumlah lapisan neuron, jumlah dropout layer, dan ukurannya masing-masing. Model CNN dibangun dengan metode transfer learning menggunakan library TensorFlow. Model optimal yang didapat adalah model transfer learning yang ditambah dengan dua dense layer dan tiga dropout layer. / Skin diseases are amongst one of the most common diseases in Indonesia, yet they are still underestimated. A lot of these diseases were left untreated due to various reasons, making them more of a serious disease. Various studies have shown that convolutional neural network can in fact detect and classify skin diseases, but no optimal model configuration has been confidently said. In this study, aside from classifying skin diseases, namely atopic dermatitis, herpes, lyme disease, poison ivy, psoriasis and rosacea, this study will also make an attempt at finding an optimal model configuration for skin disease classification by experimenting with hyperparameters such as neuron layers, drop out layers, and their respective sizes. Transfer learning will be done with a help from the TensorFlow library to make this study’s model possible. The structure of the final model was found to be the transfer learning model followed by two dense layers and three dropout layers.

Actions (login required)

View Item