Classification with Extreme Learning Machine and Ensemble Algorithms Over Randomly Partitioned Data

TL;DR

This paper explores a distributed ensemble classification approach using Extreme Learning Machine and AdaBoost within a MapReduce framework to improve predictive accuracy on large-scale data sets.

Contribution

It introduces a novel combination of ELM, AdaBoost, and MapReduce for scalable ensemble classification on big data.

Findings

Effective ensemble models built from weak classifiers

Improved classification accuracy on benchmark datasets

Scalable approach suitable for large data sets

Abstract

In this age of Big Data, machine learning based data mining methods are extensively used to inspect large scale data sets. Deriving applicable predictive modeling from these type of data sets is a challenging obstacle because of their high complexity. Opportunity with high data availability levels, automated classification of data sets has become a critical and complicated function. In this paper, the power of applying MapReduce based Distributed AdaBoosting of Extreme Learning Machine (ELM) are explored to build reliable predictive bag of classification models. Thus, (i) dataset ensembles are build; (ii) ELM algorithm is used to build weak classification models; and (iii) build a strong classification model from a set of weak classification models. This training model is applied to the publicly available knowledge discovery and data mining datasets.