教師資料查詢 | 類別: 會議論文 | 教師: 呂明達 MING-DA LU (瀏覽個人網頁)

標題:Feature Selection for Cancer Classification on Microarray Expression Data
學年97
學期1
發表日期2008/11/26
作品名稱Feature Selection for Cancer Classification on Microarray Expression Data
作品名稱(其他語言)
著者Hsu, Hui-huang; Lu, Ming-da
作品所屬單位淡江大學資訊工程學系
出版者IEEE; International Fuzzy Systems Association; National Kaohsiung University of Applied Sciences
會議名稱Intelligent Systems Design and Applications, 2008. ISDA '08. Eighth International Conference on
會議地點Kaohsiung, Taiwan
摘要Microarray is an important tool in gene analysis research. It can help identify genes that might cause various cancers. In this paper, we use feature selection methods and the support vector machine (SVM) to search for the disease-causing genes in microarray data of three different cancers. The feature selection methods are based on Euclidian distance (ED) and Pearson correlation coefficient(PCC). We investigated the effect on prediction results by training the SVM with different numbers of features and different kinds of kernels. The results show that linear kernel is the fittest kernel for this problem. Also, equal or higher accuracy can be achieved with only 15 to 100 features which are selected from 7129 or more features of the original data sets.
關鍵字Cancer Classification;Feature Selection;Microarray; Pearson Correlation Coefficient;Support Vector Machine
語言英文
收錄於
會議性質國際
校內研討會地點
研討會時間20081126~20081128
通訊作者
國別中華民國
公開徵稿Y
出版型式
出處Proceedings of the Eighth International Conference on Intelligent Systems Design and Applications (ISDA'08) v.3, pp.153-158
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!