Skripsi
PENERAPAN METODE ENSEMBLE UNTUK KLASIFIKASI KANKER SERVIKS MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE, MULTILAYER PERCEPTRON DAN K-NEAREST NEIGHBOR
Cervical cancer is a development of abnormal cells in the cervix (mouth of the womb) caused by the Human Pappiloma Virus. The Ensemble method has the ability to overcome the shortcomings of each Single Classification Algorithm by combining a Single Classification Algorithm. This study applies the Ensemble Method by combining the Single Classification Algorithm SVM (Support Vector Machine), MLP (Multilayer Perceptron), and K-NN (K-Naerest Neighbor )to find out how the performance of the Ensemble Method on the Classification of Cervical Cancer in the Herlev dataset for 2 class problems and 7. The results of this study indicate that the application of the Ensemble Method by combining a single Classification Algorithm proved to be effective for Classification of Pap Smear cells in 2 classes, but not good in 7. Classification with the Ensemble Method resulted in the best accuracy for Classification of Normal and Abnormal cells, namely 94.32%, and the results of the Sensitivity and Specificity values are very good, namely 91.8% and 93.45%, while for the 7 class classification it is still not good with the results of Accuracy, Sensitivity, and Specificity below 70%, which is 57%, 61.14% and 62%. Keywords : SVM, MLP, K-NN, Cervical Cancer, Ensemble Method
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107003455 | T58332 | T583322021 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available