Modifikasi Convolutional Neural Network Arsitektur GoogLeNet dengan Dull Razor Filtering untuk Klasifikasi Kanker Kulit

Saidah, Sofia; Suparta, I Putu Yowan Nugraha; Suhartono, Efri

doi:10.22146/jnteti.v11i2.2739

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Setelah itu dilanjutkan dengan penggunaan metode CNN untuk ekstraksi fitur serta klasifikasi citra agar dapat mengetahui jenis citra termasuk ke dalam kelompok kanker kulit, ganas atau jinak. Kinerja terbaik yang bisa didapatkan sebesar 1,7063 untuk loss dan 97,73% untuk akurasi (Sofia Saidah, Suparta and Suhartono, 2022). Tabel 3 dan 4 merupakan ringkasan yang telah dibahas pada bagian 2 mengenai klasifikasi tipe kulit wajah berdasarkan kadar minyak dan berdasarkan penyakit.…”

Section: Berdasarkan Penyakitunclassified

Analisis Faktor dan Metode untuk Menentukan Tipe Kulit Wajah: Tinjauan Literatur

Kusumaningrum,

Muhimmah

2023

JTIIK

View full text Add to dashboard Cite

Kulit merupakan bagian pelindung terluar yang melapisi sebagian besar dari tubuh manusia. Kulit wajah menjadi bagian kulit paling sensitif sehingga lebih mudah bermasalah dibanding yang lainnya. Perawatan kulit wajah yang tidak tepat dapat menyebabkan timbulnya permasalahan kulit wajah yang baru atau bahkan memperburuk permasalahan sebelumnya. Mendeteksi tipe kulit menjadi langkah awal dalam pengobatan maupun perawatan. Selama ini, penentuan tipe kulit wajah harus dengan keterampilan dokter atau tenaga kesehatan dengan dibantu alat yang mahal dan sulit dimiliki, tetapi dengan adanya perkembangan teknologi saat ini memudahkan seseorang untuk menentukan tipe kulit wajah dengan lebih praktis dan mudah tanpa harus ke dokter. Dari beberapa penelitian yang telah dilakukan sebelumnya, tipe kulit wajah maupun penyakit yang timbul pada area wajah dapat dideteksi melalui pembelajaran citra dengan berbagai macam metode. Data citra yang digunakan sebagai pembelajaran berupa citra digital maupun citra mikroskopis yang kemudian diolah dengan berbagai metode ekstraksi ciri hingga diteruskan dengan klasifikasi tipe kulit. Proses tinjauan literatur menggunakan metode scoping review yang mengidentifikasi setiap literatur secara mendalam. Literatur yang digunakan disesuaikan dengan kriteria yang telah ditentukan seperti topik pembahasan, ketersediaan literatur full text, dan abstrak. Tinjauan literatur ini menunjukkan bahwa akurasi pengolahan citra tidak hanya ditentukan berdasarkan metode, melainkan terdapat faktor lain seperti jumlah dan kualitas dataset yang digunakan serta ekstraksi ciri yang dilakukan. Hasil dari tinjauan literatur ini memberikan gambaran mengenai studi yang relevan dengan topik, perbedaan setiap literatur yang dibahas serta bermanfaat bagi peneliti yang akan mengembangkan teknologi pengolahan citra untuk menentukan tipe kulit wajah. AbstractSkin is the outer protective part that covers most of the human body. Facial skin is the most sensitive part of the skin hence it is more prone to problems than other parts. Improper facial skin care can cause new facial skin problems or even aggravate the previous problems. Detecting on the skin type is the first step in treatment or care. So far, determining the type of facial skin must be with the skills of a doctor or health worker with the help of tools that are expensive and difficult to have, but with current technological developments it makes it easier for someone to determine the type of facial skin more practically and easily without having to see a doctor. From the several previous studies, facial skin types and diseases that emerge in the facial area can be detected through image learning using various methods. Image data used as learning is in the form of digital images and microscopic images which are then processed using various feature extraction methods and then continued with skin type classification. The literature review process uses the scoping review method which identifies each literature in depth. The literature used is adjusted to predetermined the criteria such as the topic of discussion, the availability of full text literature, and the abstraction. This literature review shows that the accuracy of image processing is not only determined based on the method, but there are also other factors such as the number and quality of the datasets used and the feature extraction performed. The results of this literature review provide an overview of studies that are relevant to the topic, the differences in each literature discussed and are useful for researchers who will develop image processing technology to determine the type of facial skin.

show abstract

Section: Berdasarkan Penyakitunclassified

Analisis Faktor dan Metode untuk Menentukan Tipe Kulit Wajah: Tinjauan Literatur

Kusumaningrum,

Muhimmah

2023

JTIIK

View full text Add to dashboard Cite

show abstract

“…The device of microprocessor complexes is more complex and this is associated with several difficulties with their repair. If the electromechanical complex can be disassembled and replaced with a damaged part, then it is possible to repair the microprocessor complex only at the manufacturer [24], [25].…”

Section: Introductionmentioning

confidence: 99%

Development of intelligent protection and automation control systems using fuzzy logic elements

Ansabekova,

Sarsikeyev,

Abdimuratov

et al. 2024

IJECE

View full text Add to dashboard Cite

In this article, the causes of technological disturbances in electrical systems are considered, and several characteristic disadvantages of the protection and automation of elements of electrical systems are highlighted. The tendency to decrease the reliability of relay protection associated with the transition from analog to digital types of protection is substantiated. Based on the studied examples, the use of fuzzy logic in protections, the expediency of using fuzzy logic elements in protection devices, and the automation of electrical systems to identify types of short circuits are justified. This article analyzes the most common damages and presents the results of modeling an electrical system with transformer coupling, where all types of asymmetric short circuits were initiated. The dynamics of changes in the symmetrical components of short-circuit currents of the forward, reverse, and zero sequences are determined. Rules have been created for the identification of asymmetric types of short circuits. An algorithm of protection and automation operation using fuzzy logic elements has been developed. The proposed algorithm of protection and automation will reduce the time to determine the type of damage and trigger protections.

show abstract

“…In Indonesia, melanoma skin cancer is the third most common cancer, with a prevalence rate of 5.9 -7.8% annually, following womb and breast cancer [4]. Cases of malignant skin cancer are more common in Indonesia, accounting for 7.9%, compared to benign skin cancer [5]. In diagnosing skin cancer, doctors generally perform a biopsy, which takes skin samples for a detailed examination [1].…”

Section: Introductionmentioning

confidence: 99%

Investigating The Effectiveness of Various Convolutional Neural Network Model Architectures for Skin Cancer Melanoma Classification

Jatmiko,

Pristyanto

2023

matrik

View full text Add to dashboard Cite

Melanoma is one of the most dangerous types of skin cancer. Since 2018, the number of skin cancer cases in the US has increased and exceeded 100,000. Melanoma is the third most common cancer in Indonesia, following womb cancer and breast cancer. Standard detection of melanoma skin cancer biopsy is costly and time-consuming. The purpose of this research is to build and compare melanoma skin cancer detection using various Convolutional Neural Network method. This research used four CNN model architectures methods, VGG-16, LeNet, Xception, and MobileNet. The dataset for this research is image data that consists of 9605 data divided into benign and malignant classes. The data will be augmented to increase its quantity. After that, the data will be trained using four CNN architecture models and evaluated using the confusion matrix. The result of this study is that Xception model has the best accuracy and the lowest loss, with 93% accuracy and 19% loss, with precision 93%, recall 93,5%, and f1-score 93%. Whereas the other model, VGG-16 gives 90 % accuracy, 27% loss, LeNet 89,7% accuracy, 28% loss, and mobileNet 90,8% accuracy and 22,5% loss.

show abstract

Modifikasi Convolutional Neural Network Arsitektur GoogLeNet dengan Dull Razor Filtering untuk Klasifikasi Kanker Kulit

Cited by 7 publications

References 18 publications

Analisis Faktor dan Metode untuk Menentukan Tipe Kulit Wajah: Tinjauan Literatur

Analisis Faktor dan Metode untuk Menentukan Tipe Kulit Wajah: Tinjauan Literatur

Development of intelligent protection and automation control systems using fuzzy logic elements

Investigating The Effectiveness of Various Convolutional Neural Network Model Architectures for Skin Cancer Melanoma Classification

Contact Info

Product

Resources

About