New multivariate kernel density estimator for uncertain data classification

Uncertainty in data occurs in diverse applications due to measurement errors, data incompleteness, and multiple repeated measurements. Several classifiers for uncertain data have been developed to tackle this uncertainty. However, the existing classifiers do not consider the dependencies among uncertain features, even though this dependency has a critical effect on classification accuracy. Therefore, we propose a new Bayesian classification model that considers the correlation among uncertain features. To handle the uncertainty of data, new multivariate kernel density estimators are developed to estimate the class conditional probability density function of categorical, continuous, and mixed uncertain data. Experimental results with simulated data and real-life data sets show that the proposed approach is better than the existing approaches for classification of uncertain data in terms of classification accuracy.

Automated summary

Uncertainty in data can arise from measurement errors, data incompleteness, and multiple repeated measurements in various applications. A new Bayesian classification model taking into account the correlation among uncertain features has been proposed to improve classification accuracy. New multivariate kernel density estimators have been developed to estimate the class conditional probability density function of uncertain data, leading to better classification accuracy compared to existing approaches.