This paper presents a novel rough-based feature selection method for gene expression data analysis. It can find the relevant features without requiring the number of clusters to be known a priori and identify the centers that approximate to the correct ones. In this paper, we attempt to introduce a prediction scheme that combines the rough-based feature selection method with radial basis function neural network. For further consider the effect of different feature selection methods and classifiers on this prediction process, we use the NaIve Bayes and linear support vector machine as classifiers, and compare the performance with other feature selection methods, including information gain and principle component analysis. We demonstrate the performance by several published datasets and the results show that our proposed method can achieve high classification accuracy rate.
In recent years, personal health management has been interested to researchers and healthcare practitioners. Recording and analyzing physiological variations in ordinary life could be especially useful to manage health problems and to care individuals. It is widely pointed out that various vital signs are important indicators used to evaluate the wellness of physical bodies. In this study, an Intelligent-Mamdani Inference Scheme (IMIS) based on fuzzy markup language (FML) is proposed to apply to the semantic decision-making for personal health in healthcare applications. The IMIS could provide semantic analysis of personal health status by using the knowledge base and fuzzy inference rules, which are preestablished by domain experts. This scheme is a well-defined composition, including a FML editor, a FML parser, a fuzzy inference mechanism and a semantic decision-making mechanism. The experimental results show that the proposed scheme is feasible for semantic decision of personal health. A person can understand his physical conditions via the generated semantic decision-marking mechanism by the input of vital signs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.