<![CDATA[ABSTRAKPenyakit kulit atau kanker kulit disebabkan oleh adanya pertumbuhan abnormal sel kulit. Kanker kulit dapat diklasifikasikan menjadi dua kategori yaitu tumor kulit benign (jinak) atau malignant (tumor ganas) dengan karakteristik yang hampir sama. Beberapa metode telah dilakukan untuk membantu deteksi penyakit kulit salah satunya menggunakan computer vision. Pada penelitian ini, dirancang sebuah sistem yang dapat mengklasifikasi penyakit kulit benign dan malignant pada citra dermoskopi dengan menggunakan arsitektur ShuffleNet V2. Eksperimen dilakukan menggunakan 5 varian model ShuffleNet V2 berbeda dengan hyperparameter yaitu optimizer adam, learning rate 0.0001, batch size 16 dan epoch 40. Penelitian ini menunjukkan bahwa model ShuffleNetV2_1.0_1_373 menunjukkan performa terbaik dibandingkan dengan varian model lainnya berdasarkan hasil evaluasi accuracy, precision, recall dan f1-score dengan mencapai skor masing-masing sebesar 87,2%, 87,5%, 87,0%, dan 87,2%.Kata kunci: CNN, Lightweight CNN, ShuffleNet V2, Kanker Kulit, benign, malignantABSTRACTSkin disease, or skin cancer, is caused by the abnormal growth of skin cells. Skin cancer can be classified into two categories, namely benign (benign) or malignant (malignant tumor) skin tumors, with almost the same characteristics. With it, early detection and accurate diagnosis are needed to help identify benign and malignant skin cancer. Several methods have been developed to aid in the detection of skin diseases, one of which is the use of computer vision. In this study, a system was designed that could classify skin diseases on dermoscopy images using the ShuffleNet V2 architecture. In the experimental results, 5 variants of the ShuffleNet V2 model were tested using hyperparameters such as adam optimizer with a learning rate of 0.0001, batch size of 16, and epoch 40. The model with the best performance based on the evaluation results was the ShuffleNetV2_1.0_1_373 model, which obtained 87.2% accuracy, 87.5% precision, 87.0% recalls, and an 87.2% F1 score.Keywords: CNN, Lightweight CNN, ShuffleNet V2, Skin Cancer, benign, malignant]]>
