ACADSTAFF UGM
| Title | : | LDSVM: Leukemia Cancer Classification Using Machine Learning |
| Author | : |
ABDUL KARIM (1) Dr. Azhari, MT. (2) Dr. techn. Khabib Mustofa, S.Si., M.Kom. (3) |
| Date | : | 0 2021 |
| Keyword | : | Leukemia,GSE9476,cancer,genes,classification,machine learning,ensemble LDSVM classifier Leukemia,GSE9476,cancer,genes,classification,machine learning,ensemble LDSVM classifier |
| Abstract | : | Leukemia is blood cancer, including bone marrow and lymphatic tissues, typically involving white blood cells. Leukemia produces an abnormal amount of white blood cells more than normal blood. DNA microarrays provide reliable medical diagnostic services to help more patients find the proposed treatment for infections. The DNA microarray is also known as biochips that consist of microscopic DNA spots attached to the solid glass surface. Nowadays almost difficult to cancer classification through microarray gene datasets. Nearly many data mining techniques have failed due to the small size of samples, becoming more critical for organizations. They are frequently employed by doctors for cancer diagnosis, although they are not highly effective in improving results. The proposed study performs novel base classification using machine learning algorithms based on micro-arrays of the leukemia GSE9476 cells. The main aim is to predict Leukemia disease in the initial stages. Machine learning algorithms such as Decision tree, Naive Bayes, Random Forest, Gradient Boosting Classifier, Linear regression, Support Vector Machine, and Novel ensemble LDSVM are used to classify leukemia in patients and analyze the impacts comparatively. The proposed ensemble LDSVM classifier evaluated better accuracy, precession, recall, and f1 score than the other algorithms. Further, the results are relatively assessed, which shows LDSVM performance. This study aims to successfully predict leukemia in patients and enhance the prediction accuracy in minimum time are achieved. |
| Group of Knowledge | : | Bidang IPA Lain Yang Belum Tercantum |
| Original Language | : | English |
| Level | : | Internasional |
| Status | : |
Published
|
| No | Title | Action |
|---|