A clustering-based multi-layer distributed ensemble for neurological diagnostics in cloud services

M. Chowdhury, J. Abawajy, A. Kelarev, H. Jelinek

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper investigates the problem of minimizing data transfer between different data centers of the cloud during the neurological diagnostics of cardiac autonomic neuropathy (CAN). This problem has never been considered in the literature before. All classifiers considered for the diagnostics of CAN previously assume complete access to all data, which would lead to enormous burden of data transfer during training if such classifiers were deployed in the cloud. We introduce a new model of clustering-based multi-layer distributed ensembles (CBMLDE). It is designed to eliminate the need to transfer data between different data centers for training of the classifiers. We conducted experiments utilizing a dataset derived from an extensive DiScRi database. Our comprehensive tests have determined the best combinations of options for setting up CBMLDE classifiers. The results demonstrate that CBMLDE classifiers not only completely eliminate the need in patient data transfer, but also have significantly outperformed all base classifiers and simpler counterpart models in all cloud frameworks.
Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIEEE Transactions on Cloud Computing
Volume4
Issue number2
DOIs
Publication statusPublished - 2016

Fingerprint Dive into the research topics of 'A clustering-based multi-layer distributed ensemble for neurological diagnostics in cloud services'. Together they form a unique fingerprint.

  • Cite this