A Novel Multi-Class Ensemble Model for Classifying Imbalanced Biomedical Datasets

International Conference on Materials, Alloys and Experimental Mechanics 2017

材料科学;金属学;机械制造

Bikku, Thulasi^1 ; Sambasiva Rao, N.^2 ; Ananda Rao, Akepogu^3

CSE Department, Vignan's Nirula Institute of Technology and Science for Women, Palakaluru, A.P, India^1

Principal, SRITW, Warangal, Telangana, India^2

Direc. of Academics and Planning, JNTUCEA, Ananthapuramu, India^3

关键词: Decision tree modeling;    Ensemble modeling;    Feature selection and classification;    Map-reduce;    Medical database;    Pre-processing method;    Textual Decision Patterns;    Unstructured documents;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/225/1/012161/pdf
DOI  :  10.1088/1757-899X/225/1/012161

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

This paper mainly focuseson developing aHadoop based framework for feature selection and classification models to classify high dimensionality data in heterogeneous biomedical databases. Wide research has been performing in the fields of Machine learning, Big data and Data mining for identifying patterns. The main challenge is extracting useful features generated from diverse biological systems. The proposed model can be used for predicting diseases in various applications and identifying the features relevant to particular diseases. There is an exponential growth of biomedical repositories such as PubMed and Medline, an accurate predictive model is essential for knowledge discovery in Hadoop environment. Extracting key features from unstructured documents often lead to uncertain results due to outliers and missing values. In this paper, we proposed a two phase map-reduce framework with text preprocessor and classification model. In the first phase, mapper based preprocessing method was designed to eliminate irrelevant features, missing values and outliers from the biomedical data. In the second phase, a Map-Reduce based multi-class ensemble decision tree model was designed and implemented in the preprocessed mapper data to improve the true positive rate and computational time. The experimental results on the complex biomedical datasets show that the performance of our proposed Hadoop based multi-class ensemble model significantly outperforms state-of-the-art baselines.