KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE
Cirrhosis is one type of liver disease and is caused by forming fibrosis so that changes the liver structure become abnormal. Based on the presence of ascites, varicose veins, and bleeding, cirrhosis is divided into four clinical stages. This study aims to find the best classification model of cirrh...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Udayana
2023-05-01
|
| Series: | E-Jurnal Matematika |
| Online Access: | https://ojs.unud.ac.id/index.php/mtk/article/view/96413 |
| _version_ | 1827895748088299520 |
|---|---|
| author | VANIA RISKASARI YR I PUTU EKA NILA KENCANA I KOMANG GDE SUKARSA |
| author_facet | VANIA RISKASARI YR I PUTU EKA NILA KENCANA I KOMANG GDE SUKARSA |
| author_sort | VANIA RISKASARI YR |
| collection | DOAJ |
| description | Cirrhosis is one type of liver disease and is caused by forming fibrosis so that changes the liver structure become abnormal. Based on the presence of ascites, varicose veins, and bleeding, cirrhosis is divided into four clinical stages. This study aims to find the best classification model of cirrhosis using the support vector machine (SVM). SVM is a supervised learning method that aims to find the hyperplane with the maximum margin. In this study, the resulted model useful for determining the cirrhosis’ stage from patients. The variables to classify are age, gender, ascites status, hepatomegaly status, spiders status, edema status, total bilirubin, total cholesterol, amount of albumin, amount of copper, alkaline phosphatase level test results, SGOT test results, amount of tryglycerides, amount of platelets, and prothrombin time. By applying radial basis function kernel, combination of parameter C and that gives the best accuracy is determined. The final model using SVM with parameters C = 1 and = 0,6 is the best model with the accuracy value of 67,86 percent. |
| first_indexed | 2024-03-12T22:25:09Z |
| format | Article |
| id | doaj.art-ed08925cfbef42b0b1584b9e59328f35 |
| institution | Directory Open Access Journal |
| issn | 2303-1751 |
| language | English |
| last_indexed | 2024-03-12T22:25:09Z |
| publishDate | 2023-05-01 |
| publisher | Universitas Udayana |
| record_format | Article |
| series | E-Jurnal Matematika |
| spelling | doaj.art-ed08925cfbef42b0b1584b9e59328f352023-07-22T06:26:03ZengUniversitas UdayanaE-Jurnal Matematika2303-17512023-05-01122879110.24843/MTK.2023.v12.i02.p40496413KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINEVANIA RISKASARI YRI PUTU EKA NILA KENCANAI KOMANG GDE SUKARSACirrhosis is one type of liver disease and is caused by forming fibrosis so that changes the liver structure become abnormal. Based on the presence of ascites, varicose veins, and bleeding, cirrhosis is divided into four clinical stages. This study aims to find the best classification model of cirrhosis using the support vector machine (SVM). SVM is a supervised learning method that aims to find the hyperplane with the maximum margin. In this study, the resulted model useful for determining the cirrhosis’ stage from patients. The variables to classify are age, gender, ascites status, hepatomegaly status, spiders status, edema status, total bilirubin, total cholesterol, amount of albumin, amount of copper, alkaline phosphatase level test results, SGOT test results, amount of tryglycerides, amount of platelets, and prothrombin time. By applying radial basis function kernel, combination of parameter C and that gives the best accuracy is determined. The final model using SVM with parameters C = 1 and = 0,6 is the best model with the accuracy value of 67,86 percent.https://ojs.unud.ac.id/index.php/mtk/article/view/96413 |
| spellingShingle | VANIA RISKASARI YR I PUTU EKA NILA KENCANA I KOMANG GDE SUKARSA KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE E-Jurnal Matematika |
| title | KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE |
| title_full | KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE |
| title_fullStr | KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE |
| title_full_unstemmed | KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE |
| title_short | KLASIFIKASI PENYAKIT SIROSIS MENGGUNAKAN SUPPORT VECTOR MACHINE |
| title_sort | klasifikasi penyakit sirosis menggunakan support vector machine |
| url | https://ojs.unud.ac.id/index.php/mtk/article/view/96413 |
| work_keys_str_mv | AT vaniariskasariyr klasifikasipenyakitsirosismenggunakansupportvectormachine AT iputuekanilakencana klasifikasipenyakitsirosismenggunakansupportvectormachine AT ikomanggdesukarsa klasifikasipenyakitsirosismenggunakansupportvectormachine |