Maulina, Dian Rizky (2019) Klasifikasi Kadar Toksisitas dan Proteksi Radiasi Menggunakan Neural Network Ensemble dan Random Forest Pada Senyawa Terpenting Gen Supresor p53. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211540000091-Undergraduate_Theses.pdf Download (1MB) | Preview |
Abstract
Kanker merupakan penyakit akibat pertumbuhan tidak normal akibat sel-sel jaringan tubuh yang berubah menjadi sel kanker. Salah satu pengobatan pada kanker adalah radioterapi, namun memiliki efek samping yaitu membunuh sel-sel normal disekitar sel kanker. Penggunaan radioterapi secara terus-terus dengan radiasi yang tinggi juga akan berpengaruh kepada pasien kanker. Sehingga, diperlukan adanya penjustifikasian klasifikasi senyawasenyawa penting gen supresor p53 dengan akurasi yang tinggi dengan menggunakan senyawa-senyawa yang diperoleh dari penelitian sebelumnya yang memperoleh perankingan 20 besar senyawa penting gen supresor p53 yang baik digunakan untuk radioterapi. Klasifikasi kadar toksisitas dan radio proteksif dengan menggunakan metode neural network ensemble lebih baik dibandingkan dengan menggunakan random forest karena didapatkan nilai akurasi yang lebih tinggi.
=================================================================================================================================
Cancer is a disease caused by abnormal growth due to the cells of the body's tissues that turn into cancer cells. One treatment for cancer is radiotherapy, but it has a side effect of killing normal cells around the cancer cells. Continuous by using radiotherapy with high radiation will also affect to the cancer’s patients. So it takes a drug compound that is able to control it. Thus, in this study the classification of important compounds of the p53 suppressor gene was carried out with high accuracy using compounds obtained from previous studies which obtained a ranking of the top 20 important compounds of the p53 suppressor gene which is well used for radiotherapy. Classification of citotoxicity and radioprotective by using neural network ensemble is more better than using random forest because it brings higher accuracy values than than random forest have.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSSt 519.53 Mau k-1 2019 |
| Uncontrolled Keywords: | Cancer, High Dimensional Data, Neural network Ensembles, Radiation Protection, Random forest, Supressor genes p53, Toxicity |
| Subjects: | Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) |
| Divisions: | Faculty of Mathematics and Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Dian Rizky Maulina |
| Date Deposited: | 20 Mar 2024 03:37 |
| Last Modified: | 20 Mar 2024 03:37 |
| URI: | http://repository.its.ac.id/id/eprint/64410 |
Actions (login required)
 |
View Item |