Teo, Voon Chuan (2022) Gene Selection For Cancer Classification Based On Xgboost Classifier. Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah.
|
Pdf
CB19055.pdf - Accepted Version Download (1MB) | Preview |
Abstract
Gene selection is the technique that applied to the gene selection dataset, such as DNA microarray, which is develop to reduce the less informative gene, so that the selected gene is related to the disease diagnosis. While the cancer classification is a process of identifying the type of cancer, and the extent to which a tumor has grown and spread. XGBoost Classifier is applied in this research, which it is an efficient open-source implementation of the gradient boosted trees algorithm. Gradient boosting is a supervised learning algorithm, which attempts to accurately predict a target variable by combining the estimates of a set of simplifier, weaker models. In today world, cancer is still as a leading cause to death. The problem of having obstacle to making early detection for cancer is still a difficulty for the researcher. Due to this situation, development of the gene selection method has become more important in obtain useful information for cancer classification, and diagnoses for other diseases. Thus, a XGBoost Classifier is proposed in this research, to help to select minimum gene subset that are giving relevant information for cancer classification. By applied the XGBoost Classifier, the accuracy and the performance of the gene selection and cancer classification can be highly improved, and reduce the time and cost for the disease diagnoses. In conclusion, XGBoost Classifier is increasing the performance and accuracy in gene selection for cancer classification.
| Item Type: | Undergraduates Project Papers |
|---|---|
| Additional Information: | SV: Ts. Dr. Kohbalan A/L Moorthy |
| Uncontrolled Keywords: | Gradient boosting, cancer diagnosis |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Faculty/Division: | Faculty of Computing |
| Depositing User: | Mr. Nik Ahmad Nasyrun Nik Abd Malik |
| Date Deposited: | 29 Feb 2024 07:29 |
| Last Modified: | 29 Feb 2024 07:29 |
| URI: | http://umpir.ump.edu.my/id/eprint/40551 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |