Cloud-Based Machine Learning Tools for Enhanced Big Data Applications

Abstract

We propose Cloud-based machine learning tools for enhanced Big Data applications, where the main idea is that of predicting the "next" workload occurring against the target Cloud infrastructure via an innovative ensemble-based approach that combine the effectiveness of different well-known classifiers in order to enhance the whole accuracy of the final classification, which is very relevant at now in the specific context of Big Data. So-called workload categorization problem plays a critical role towards improving the efficiency and the reliability of Cloudbased big data applications. Implementation-wise, our method proposes deploying Cloud entities that participate to the distributed classification approach on top of virtual machines, which represent classical "commodity" settings for Cloud-based big data applications. Preliminary experimental assessment and analysis clearly confirm the benefits deriving from our classification framework. 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing 978-1-4799-8006-2/15 $31.00

Affective design using machine learning: a survey and its prospect of conjoining big data

“…Machine learning can be implemented in parallelization systems such as Hadoop and Cloud, in order to perform big data mining. Dai and Ji (Dai and Ji 2014) and He et al (He et al 2013) implemented Hadoop for parallel decision trees and regression; Cuzzocrea et al (Cuzzocrea, Mumolo, and Corona 2015) developed a Cloud-based machine learning tool to predict future data. These parallelization techniques improved the efficiency and the reliability of big data mining (Wu et al 2014) and have the potential to be implemented in machine learning for affective design involving huge amounts of affective data.…”

“…Cybernetic security: An effective data management toolkit is essential to be develop to leverage big data from streaming database systems (Condie, Mineiro, Polyzotis, & Weimer, 2013); Large computational demand: Processing tons of affective data in a faster speed is challenging. An effective parallelization system has to be developed (Cuzzocrea, Mumolo, & Corona, 2015); Algorithmic development: Implementation of machine learning for affective data is challenging. Despite text data, big data is involved with multichannel captures, which is huge in amount and large dimensions (Olvera-López, Carrasco-Ochoa, Martínez-Trinidad, & Kittler, 2010); Data transmission: high transmission is required as the data size is huge and data dimension is large.…”