Text
IMPLEMENTASI ARSITEKTUR VISION TRANSFORMER DENGAN TEKNIK SHIFTED PATCH PADA KLASIFIKASI PENYAKIT KANKER SERVIKS
Cervical cancer is a type of cancer that attacks the cells in the cervix in women which can cause death. Pap smear is a medical method to detect cervical cells affected by cancer. Therefore, this study conducted a classification on cervical cancer. One method for classifying is Vision Transformer (ViT). The advantage of ViT is that it uses little memory but can get very good results in performing classification tasks. The ViT architecture has a patching technique that characterizes the classification process. One of the patching techniques is the shifted patch. This study implements the ViT architecture implementation with the shifted patch technique in the classification of cervical cancer. The cervical cell image data itself consists of 5 labels. The research stage begins with collecting data, pre-processing data, training¸ testing and performance evaluation. The study found the average value of the performance evaluation results of accuracy, sensitivity, specificity, F1-score, and Cohen's kappa are 97.80%, 94.78%, 98.62%, 94.69%, and 93,30%. The value of the proposed work evaluation also shows good results when compared to previous studies that discuss cervical cancer. Based on the results obtained, the Vision Transformer architecture with the shifted patch technique can perform image classification on cervical cancer well.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2207004164 | T78736 | T787362022 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available