A Novel Approach for Missing Value Imputation and Classification of Microarray Dataset

详细信息    查看全文

• 作者：Rajashree Senapti^a ; Kailash Shaw^b ; ^{kailash.shaw@gmail.com} ; Sashikala Mishra^c ; Debahuti Mishra^d
• 关键词：Distance bsed mean method ; Missing value ; Discriminant analysis ; Microarry data set
• 刊名：Procedia Engineering
• 出版年：2012
• 出版时间：2012
• 年：2012
• 卷：38
• 期：Complete
• 页码：1067-1071
• 全文大小：2289 K

文摘

Various machine learning algorithms are used for classification of microarray data. The accuracy of classifier is generally compromised by the missing value in the data set, due to incorrect collection of data values. Those missing data in the microarray data set may contain some relevance information. These missing values can lead to the incorrect analysis of data. Lots of research is carried out to minimize the impact of these missing values. In this paper; a new method has been proposed to elucidate the missing value for different microarray data sets. The proposed method has been compared with the traditional methods like mean method and median method. The proposed model has used principal component analysis (PCA) to deal with curse of dimensionality. To validate the proposed method Linear Discriminant Analysis (LDA) classification technique has been used to achieve the accuracy. The results show that proposed missing value imputation technique gives more accuracy as compared to other missing value methods.