Semantic labeling of social big media using distributed online robust classification

Abstract

Semantic labeling for image datasets is of significant importance in a wide range of social media. However, social datasets with massive amounts of data require effective technologies to increase the quality of classification. In this study, we propose a novel online robust classification using distributed learning method, in which the diffusion method is used over adaptive networks in order to the parallelization of the training process. The loss function of the suggested method is derived from the logarithm cosine function, being more suitable for impulsive noises. Also, the convergence of the proposed method is discussed theoretically. The Extensive experimental results show that the proposed method outperforms the other robust state-of-the-art classification algorithms in the presence of various scenarios, such as: free noise synthetic data sets, pure Gaussian noise, mixture of two Gaussian noises, impulse noise, and Alpha–Beta noise which are added to the synthetic data sets. In addition, the experiments were repeated for two different types of real data sets with real noises and outliers, i.e., UCI and 500PX social media data sets. The obtained results over UCI and 500px data sets on social media with real outliers and mislabeled samples confirmed the acceptable performance of the proposed method.